Search

Narratives posted on the internet by patients contain a vast amount of information about various concerns. This study aimed to extract multiple concerns from interviews with breast cancer patients using the natural language processing (NLP) model bidirectional encoder representations from transformers (BERT). A total of 508 interview transcriptions of breast cancer patients written in Japanese were labeled with five types of concern labels: "treatment," "physical," "psychological," "work/financial," and "family/friends." The labeled texts were used to create a multi-label classifier by fine-tuning a pre-trained BERT model. Prior to fine-tuning, we also created several classifiers with domain adaptation using (1) breast cancer patients' blog articles and (2) breast cancer patients' interview transcriptions. The performance of the classifiers was evaluated in terms of precision through 5-fold cross-validation. The multi-label classifiers with only fine-tuning had precision values of over 0.80 for "physical" and "work/financial" out of the five concerns. On the other hand, precision for "treatment" was low at approximately 0.25. However, for the classifiers using domain adaptation, the precision of this label took a range of 0.40-0.51, with some cases improving by more than 0.2. This study showed combining domain adaptation with a multi-label classifier on target data made it possible to efficiently extract multiple concerns from interviews., Competing Interests: HY is the CEO of Mediaid Corporation, which operates LifePalette. The other authors declare no competing. This does not alter our adherence to PLOS ONE policies on sharing data and materials., (Copyright: © 2024 Watabe et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.)

Narratives posted on the internet by patients contain a vast amount of information about various concerns. This study aimed to extract multiple concerns from interviews with breast cancer patients using the natural language processing (NLP) model bidirectional encoder representations from transformers (BERT). A total of 508 interview transcriptions of breast cancer patients written in Japanese were labeled with five types of concern labels: "treatment," "physical," "psychological," "work/financial," and "family/friends." The labeled texts were used to create a multi-label classifier by fine-tuning a pre-trained BERT model. Prior to fine-tuning, we also created several classifiers with domain adaptation using (1) breast cancer patients' blog articles and (2) breast cancer patients' interview transcriptions. The performance of the classifiers was evaluated in terms of precision through 5-fold cross-validation. The multi-label classifiers with only fine-tuning had precision values of over 0.80 for "physical" and "work/financial" out of the five concerns. On the other hand, precision for "treatment" was low at approximately 0.25. However, for the classifiers using domain adaptation, the precision of this label took a range of 0.40-0.51, with some cases improving by more than 0.2. This study showed combining domain adaptation with a multi-label classifier on target data made it possible to efficiently extract multiple concerns from interviews.

Vocabulary tests, once a cornerstone of language modeling evaluation, have been largely overlooked in the current landscape of Large Language Models (LLMs) like Llama 2, Mistral, and GPT. While most LLM evaluation benchmarks focus on specific tasks or domain-specific knowledge, they often neglect the fundamental linguistic aspects of language understanding. In this paper, we advocate for the revival of vocabulary tests as a valuable tool for assessing LLM performance. We evaluate seven LLMs using two vocabulary test formats across two languages and uncover surprising gaps in their lexical knowledge. These findings shed light on the intricacies of LLM word representations, their learning mechanisms, and performance variations across models and languages. Moreover, the ability to automatically generate and perform vocabulary tests offers new opportunities to expand the approach and provide a more complete picture of LLMs' language skills. [ABSTRACT FROM AUTHOR]

Automatic Urdu handwritten text recognition is a challenging task in the OCR industry. Unlike printed text, Urdu handwriting lacks a uniform font and structure. This lack of uniformity causes data inconsistencies and recognition issues. Different writing styles, cursive scripts, and limited data make Urdu text recognition a complicated task. Major languages, such as English, have experienced advances in automated recognition, whereas low-resource languages, such as Urdu, still lag. Transformer-based models are promising for automated recognition in high- and low-resource languages such as Urdu. This paper presents a transformer-based method called ET-Network that integrates self-attention into EfficientNet for feature extraction and a transformer for language modeling. The use of self-attention layers in EfficientNet helps to extract global and local features that capture long-range dependencies. These features proceeded into a vanilla transformer to generate text, and a prefix beam search is used for the finest outcome. NUST-UHWR, UPTI2.0, and MMU-OCR-21 are three datasets used to train and test the ET Network for a handwritten Urdu script. The ET-Network improved the character error rate by 4% and the word error rate by 1.55%, while establishing a new state-of-the-art character error rate of 5.27% and a word error rate of 19.09% for Urdu handwritten text. [ABSTRACT FROM AUTHOR]

Recent research has demonstrated that large pre-trained language models reflect societal biases expressed in natural language. The present paper introduces a simple method for probing language models to conduct a multilingual study of gender bias towards politicians. We quantify the usage of adjectives and verbs generated by language models surrounding the names of politicians as a function of their gender. To this end, we curate a dataset of 250k politicians worldwide, including their names and gender. Our study is conducted in seven languages across six different language modeling architectures. The results demonstrate that pre-trained language models' stance towards politicians varies strongly across analyzed languages. We find that while some words such as dead, and designated are associated with both male and female politicians, a few specific words such as beautiful and divorced are predominantly associated with female politicians. Finally, and contrary to previous findings, our study suggests that larger language models do not tend to be significantly more gender-biased than smaller ones. [ABSTRACT FROM AUTHOR]

Randomized controlled trials (RCTs) play a major role in aiding biomedical research and practices. To inform this research, the demand for highly accurate retrieval of scientific articles on RCT research has grown in recent decades. However, correctly identifying all published RCTs in a given domain is a non-trivial task, which has motivated computer scientists to develop methods for identifying papers involving RCTs. Although existing studies have provided invaluable insights into how RCT tags can be predicted for biomedicine research articles, they used datasets from different sources in varying sizes and timeframes and their models and findings cannot be compared across studies. In addition, as datasets and code are rarely shared, researchers who conduct RCT classification have to write code from scratch, reinventing the wheel. In this paper, we present Bat4RCT, a suite of data and an integrated method to serve as a strong baseline for RCT classification, which includes the use of BERT-based models in comparison with conventional machine learning techniques. To validate our approach, all models are applied on 500,000 paper records in MEDLINE. The BERT-based models showed consistently higher recall scores than conventional machine learning and CNN models while producing slightly better or similar precision scores. The best performance was achieved by the BioBERT model when trained on both title and abstract texts, with the F1 score of 90.85%. This infrastructure of dataset and code will provide a competitive baseline for the evaluation and comparison of new methods and the convenience of future benchmarking. To our best knowledge, our study is the first work to apply BERT-based language modeling techniques to RCT classification tasks and to share dataset and code in order to promote reproducibility and improvement in text classification in biomedicine research. [ABSTRACT FROM AUTHOR]

Visual Question Answering (VQA) is a learning task that combines computer vision with natural language processing. In VQA, it is important to understand the alignment between visual concepts and linguistic semantics. In this paper, we proposed a Pre-training Model Based on Parallel Cross-Modality Fusion Layer (P-PCFL) to learn the fine-grained relationship between vision and language. The P-PCFL model is composed of three Encoders: Object Encoder, Language Encoder, and Parallel Cross-Modality Fusion Encoder, with Transformer as the core. We use four different Pre-training missions, namely, Cross-Modality Mask Language Modeling, Cross-Modality Mask Region Modeling, Image-Text Matching, and Image-Text Q&A, to pre-train the P-PCFL model and improve its reasoning and universality, which help to learn the relationship between Intra-modality and Inter-modality. Experimental results on the platform of Visual Question Answering dataset VQA v2.0 show that the Pre-trained P-PCFL model has a good effect after fine-tuning the parameters. In addition, we also conduct ablation experiments and provide some results of Attention visualization to verify the effectiveness of P-PCFL model. [ABSTRACT FROM AUTHOR]

The recent advances in language modeling significantly improved the generative capabilities of deep neural models: in 2019 OpenAI released GPT-2, a pre-trained language model that can autonomously generate coherent, non-trivial and human-like text samples. Since then, ever more powerful text generative models have been developed. Adversaries can exploit these tremendous generative capabilities to enhance social bots that will have the ability to write plausible deepfake messages, hoping to contaminate public debate. To prevent this, it is crucial to develop deepfake social media messages detection systems. However, to the best of our knowledge no one has ever addressed the detection of machine-generated texts on social networks like Twitter or Facebook. With the aim of helping the research in this detection field, we collected the first dataset of real deepfake tweets, TweepFake. It is real in the sense that each deepfake tweet was actually posted on Twitter. We collected tweets from a total of 23 bots, imitating 17 human accounts. The bots are based on various generation techniques, i.e., Markov Chains, RNN, RNN+Markov, LSTM, GPT-2. We also randomly selected tweets from the humans imitated by the bots to have an overall balanced dataset of 25,572 tweets (half human and half bots generated). The dataset is publicly available on Kaggle. Lastly, we evaluated 13 deepfake text detection methods (based on various state-of-the-art approaches) to both demonstrate the challenges that Tweepfake poses and create a solid baseline of detection techniques. We hope that TweepFake can offer the opportunity to tackle the deepfake detection on social media messages as well. [ABSTRACT FROM AUTHOR]

This work is intended as a voice in the discussion over previous claims that a pretrained large language model (LLM) based on the Transformer model architecture can be sentient. Such claims have been made concerning the LaMDA model and also concerning the current wave of LLM-powered chatbots, such as ChatGPT. This claim, if confirmed, would have serious ramifications in the Natural Language Processing (NLP) community due to wide-spread use of similar models. However, here we take the position that such a large language model cannot be conscious, and that LaMDA in particular exhibits no advances over other similar models that would qualify it. We justify this by analysing the Transformer architecture through Integrated Information Theory of consciousness. We see the claims of sentience as part of a wider tendency to use anthropomorphic language in NLP reporting. Regardless of the veracity of the claims, we consider this an opportune moment to take stock of progress in language modelling and consider the ethical implications of the task. In order to make this work helpful for readers outside the NLP community, we also present the necessary background in language modelling. [ABSTRACT FROM AUTHOR]

The musculoskeletal network is a complex system of different types of nodes and edges interacting with each other. Although there is a wealth of knowledge about the anatomical components of the human body and the connections between them, the interdependence of these components as a system remains largely unexplored. This study aims to understand the structure of musculoskeletal networks by using hypergraphs as a model of the musculoskeletal system with many-to-many connections. We used both pairwise and hypergraph-based embedding methods to learn the connectivity of muscles. Experiments demonstrated the superiority of the proposed hypergraph-based method over pairwise methods in distinguishing the specific roles of the muscles connecting different body parts. [ABSTRACT FROM AUTHOR]

In this study, from the perspective of image processing, we propose the iDNA-ITLM model, using a novel data enhance strategy by continuously self-replicating a short DNA sequence into a longer DNA sequence and then embedding it into a high-dimensional matrix to enlarge the receptive field, for identifying DNA methylation sites. Our model consistently outperforms the current state-of-the-art sequence-based DNA methylation site recognition methods when evaluated on 17 benchmark datasets that cover multiple species and include three DNA methylation modifications (4mC, 5hmC, and 6mA). The experimental results demonstrate the robustness and superior performance of our model across these datasets. In addition, our model can transfer learning to RNA methylation sequences and produce good results without modifying the hyperparameters in the model. The proposed iDNA-ITLM model can be considered a universal predictor across DNA and RNA methylation species. [ABSTRACT FROM AUTHOR]

Over the last four years, each successive wave of the COVID-19 pandemic has been caused by variants with mutations that improve the transmissibility of the virus. Despite this, we still lack tools for predicting clinically important features of the virus. In this study, we show that it is possible to predict the PCR cycle threshold (Ct) values from clinical detection assays using sequence data. Ct values often correspond with patient viral load and the epidemiological trajectory of the pandemic. Using a collection of 36,335 high quality genomes, we built models from SARS-CoV-2 intrahost single nucleotide variant (iSNV) data, computing XGBoost models from the frequencies of A, T, G, C, insertions, and deletions at each position relative to the Wuhan-Hu-1 reference genome. Our best model had an R2 of 0.604 [0.593–0.616, 95% confidence interval] and a Root Mean Square Error (RMSE) of 5.247 [5.156–5.337], demonstrating modest predictive power. Overall, we show that the results are stable relative to an external holdout set of genomes selected from SRA and are robust to patient status and the detection instruments that were used. This study highlights the importance of developing modeling strategies that can be applied to publicly available genome sequence data for use in disease prevention and control. [ABSTRACT FROM AUTHOR]

Wind power forecasting has complex nonlinear features and behavioral patterns across time scales, which is a severe test for traditional forecasting techniques. To address the multi-scale problem in wind power forecasting, this paper innovatively proposes an ultra-short-term forecasting model LFformer based on Legendre-Fourier, which firstly focuses on the important information in the input sequences by using the encoder-decoder architecture, and then scales the range of the original data with the Devlin normalization method, and then utilizes the Legendre polynomials to The data sequence is projected into a bounded dimensional space, the historical data is compressed using feature representation, then feature selection is performed using the low-rank approximation method of Fourier Transform, the prediction is inputted into the multilayer perceptron through the multi-scale mixing mechanism, and finally the results are outputted after back-normalization. The experimental results show that compared with the existing prediction methods, the model realizes the improvement of prediction accuracy and stability, especially in the ultra-short-term prediction scenario, with obvious advantages. The research results are not only valuable for improving the overall operational efficiency of the wind power system, but also help to enhance the stable operation of the power grid, which provides strong technical support and guarantee for wind power enterprises to improve the competitiveness of bidding for Internet access in the power market competition. [ABSTRACT FROM AUTHOR]

People use search engines for various topics and items, from daily essentials to more aspirational and specialized objects. Therefore, search engines have taken over as people's preferred resource. The "How To" prefix has become familiar and widely used in various search styles to find solutions to particular problems. This search allows people to find sequential instructions by providing detailed guidelines to accomplish specific tasks. Categorizing instructional text is also essential for task-oriented learning and creating knowledge bases. This study uses the "How To" articles to determine the multi-label instruction category. We have brought this work with a dataset comprising 11,121 observations from wikiHow, where each record has multiple categories. To find out the multi-label category meticulously, we employ some transformer-based deep neural architectures, such as Generalized Autoregressive Pretraining for Language Understanding (XLNet), Bidirectional Encoder Representation from Transformers (BERT), etc. In our multi-label instruction classification process, we have reckoned our proposed architectures using accuracy and macro f1-score as the performance metrics. This thorough evaluation showed us much about our strategy's strengths and drawbacks. Specifically, our implementation of the XLNet architecture has demonstrated unprecedented performance, achieving an accuracy of 97.30% and micro and macro average scores of 89.02% and 93%, a noteworthy accomplishment in multi-label classification. This high level of accuracy and macro average score is a testament to the effectiveness of the XLNet architecture in our proposed 'InstructNet' approach. By employing a multi-level strategy in our evaluation process, we have gained a more comprehensive knowledge of the effectiveness of our proposed architectures and identified areas for forthcoming improvement and refinement. [ABSTRACT FROM AUTHOR]

Through advances in neural language modeling, it has become possible to generate artificial texts in a variety of genres and styles. While the semantic coherence of such texts should not be over-estimated, the grammatical correctness and stylistic qualities of these artificial texts are at times remarkably convincing. In this paper, we report a study into crowd-sourced authenticity judgments for such artificially generated texts. As a case study, we have turned to rap lyrics, an established sub-genre of present-day popular music, known for its explicit content and unique rhythmical delivery of lyrics. The empirical basis of our study is an experiment carried out in the context of a large, mainstream contemporary music festival in the Netherlands. Apart from more generic factors, we model a diverse set of linguistic characteristics of the input that might have functioned as authenticity cues. It is shown that participants are only marginally capable of distinguishing between authentic and generated materials. By scrutinizing the linguistic features that influence the participants' authenticity judgments, it is shown that linguistic properties such as 'syntactic complexity', 'lexical diversity' and 'rhyme density' add to the user's perception of texts being authentic. This research contributes to the improvement of the quality and credibility of generated text. Additionally, it enhances our understanding of the perception of authentic and artificial art. [ABSTRACT FROM AUTHOR]

Recent studies on machine learning technology have reported successful performances in some visual and auditory recognition tasks, while little has been reported in the field of olfaction. In this paper we report computational methods to predict the odor impression of a chemical from its physicochemical properties. Our predictive model utilizes nonlinear dimensionality reduction on mass spectra data and performs the clustering of descriptors by natural language processing. Sensory evaluation is widely used to measure human impressions to smell or taste by using verbal descriptors, such as “spicy” and “sweet”. However, as it requires significant amounts of time and human resources, a large-scale sensory evaluation test is difficult to perform. Our model successfully predicts a group of descriptors for a target chemical through a series of computer simulations. Although the training text data used in the language modeling is not specialized for olfaction, the experimental results show that our method is useful for analyzing sensory datasets. This is the first report to combine machine olfaction with natural language processing for odor character prediction. [ABSTRACT FROM AUTHOR]

Over the last ten years, social media has become a crucial data source for businesses and researchers, providing a space where people can express their opinions and emotions. To analyze this data and classify emotions and their polarity in texts, natural language processing (NLP) techniques such as emotion analysis (EA) and sentiment analysis (SA) are employed. However, the effectiveness of these tasks using machine learning (ML) and deep learning (DL) methods depends on large labeled datasets, which are scarce in languages like Spanish. To address this challenge, researchers use data augmentation (DA) techniques to artificially expand small datasets. This study aims to investigate whether DA techniques can improve classification results using ML and DL algorithms for sentiment and emotion analysis of Spanish texts. Various text manipulation techniques were applied, including transformations, paraphrasing (back-translation), and text generation using generative adversarial networks, to small datasets such as song lyrics, social media comments, headlines from national newspapers in Chile, and survey responses from higher education students. The findings show that the Convolutional Neural Network (CNN) classifier achieved the most significant improvement, with an 18% increase using the Generative Adversarial Networks for Sentiment Text (SentiGan) on the Aggressiveness (Seriousness) dataset. Additionally, the same classifier model showed an 11% improvement using the Easy Data Augmentation (EDA) on the Gender-Based Violence dataset. The performance of the Bidirectional Encoder Representations from Transformers (BETO) also improved by 10% on the back-translation augmented version of the October 18 dataset, and by 4% on the EDA augmented version of the Teaching survey dataset. These results suggest that data augmentation techniques enhance performance by transforming text and adapting it to the specific characteristics of the dataset. Through experimentation with various augmentation techniques, this research provides valuable insights into the analysis of subjectivity in Spanish texts and offers guidance for selecting algorithms and techniques based on dataset features. [ABSTRACT FROM AUTHOR]

Conversations encompass continuous exchanges of verbal and nonverbal information. Previous research has demonstrated that gestures dynamically entrain each other and that speakers tend to align their vocal properties. While gesture and speech are known to synchronize at the intrapersonal level, few studies have investigated the multimodal dynamics of gesture/speech between individuals. The present study aims to extend our comprehension of unimodal dynamics of speech and gesture to multimodal speech/gesture dynamics. We used an online dataset of 14 dyads engaged in unstructured conversation. Speech and gesture synchronization was measured with cross-wavelets at different timescales. Results supported previous research on intrapersonal speech/gesture coordination, finding synchronization at all timescales of the conversation. Extending the literature, we also found interpersonal synchronization between speech and gesture. Given that the unimodal and multimodal synchronization occurred at similar timescales, we suggest that synchronization likely depends on the vocal channel, particularly on the turn-taking dynamics of the conversation. [ABSTRACT FROM AUTHOR]

Large language models such as ChatGPT have been shown to excel in solving complex math problems. However, they cannot solve basic arithmetic problems such as 758*639 = 484,362. This makes us ponder if LLMs have been trained to solve math and science problems in the right way. When a student learns math at school, she or he starts with arithmetic, then moves to word problems, polynomials, and calculus. Each skill she or he acquires will be used in the next stage to solve more advanced problems. In this paper we propose Scaffolding Learning for LLMs, which imitates how a student learns a subject in a step-by-step manner. For example, we first train an LLM to perform highly specific operations such as multiplication and division, and then apply such "skills" in a more generic task such as solving word problems. This is related to Curriculum Training, which trains a model on tasks following a specific order, such as training on easy tasks first and then gradually increases the difficulty. Our proposed approach goes from specific tasks to generic ones, which can be considered as a special case of Curriculum Training. Our empirical studies show that when an LLM has "mastered" a specific skill, only a small amount of training is required to teach it to apply the skill to a more generic application. [ABSTRACT FROM AUTHOR]

In recent years, the surge in reviews and comments on newspapers and social media has made sentiment analysis a focal point of interest for researchers. Sentiment analysis is also gaining popularity in the Bengali language. However, Aspect-Based Sentiment Analysis is considered a difficult task in the Bengali language due to the shortage of perfectly labeled datasets and the complex variations in the Bengali language. This study used two open-source benchmark datasets of the Bengali language, Cricket, and Restaurant, for our Aspect-Based Sentiment Analysis task. The original work was based on the Random Forest, Support Vector Machine, K-Nearest Neighbors, and Convolutional Neural Network models. In this work, we used the Bidirectional Encoder Representations from Transformers, the Robustly Optimized BERT Approach, and our proposed hybrid transformative Random Forest and Bidirectional Encoder Representations from Transformers (tRF-BERT) models to compare the results with the existing work. After comparing the results, we can clearly see that all the models used in our work achieved better results than any of the previous works on the same dataset. Amongst them, our proposed transformative Random Forest and Bidirectional Encoder Representations from Transformers achieved the highest F1 score and accuracy. The accuracy and F1 score of aspect detection for the Cricket dataset were 0.89 and 0.85, respectively, and for the Restaurant dataset were 0.92 and 0.89 respectively. [ABSTRACT FROM AUTHOR]

Short texts on social platforms often suffer from insufficient emotional semantic expressions, sparse features, and polysemy. To enhance the accuracy achieved by sentiment analysis for short texts, this paper proposes an emoji-based multifeature fusion sentiment analysis model (EMFSA). The model mines the sentiments of emojis, topics, and text features. Initially, a pretraining method for feature extraction is employed to enhance the semantic expressions of emotions in text by extracting contextual semantic information from emojis. Following this, a sentiment- and emoji-masked language model is designed to prioritize the masking of emojis and words with implicit sentiments, focusing on learning the emotional semantics contained in text. Additionally, we proposed a multifeature fusion method based on a cross-attention mechanism by determining the importance of each word in a text from a topic perspective. Next, this method is integrated with the original semantic information of emojis and the enhanced text features, attaining improved sentiment representation accuracy for short texts. Comparative experiments conducted with the state-of-the-art baseline methods on three public datasets demonstrate that the proposed model achieves accuracy improvements of 2.3%, 10.9%, and 2.7%, respectively, validating its effectiveness. [ABSTRACT FROM AUTHOR]

Forecasting the weather in an area characterized by erratic weather patterns and unpredictable climate change is a challenging endeavour. The weather is classified as a non-linear system since it is influenced by various factors that contribute to climate change, such as humidity, average temperature, sea level pressure, and rainfall. A reliable forecasting system is crucial in several industries, including transportation, agriculture, tourism, & development. This study showcases the effectiveness of data mining, meteorological analysis, and machine learning techniques such as RNN-LSTM, TensorFlow Decision Forest (TFDF), and model stacking (including ElasticNet, GradientBoost, KRR, and Lasso) in improving the precision and dependability of weather forecasting. The stacking model strategy entails aggregating multiple base models into a meta-model to address issues of overfitting and underfitting, hence improving the accuracy of the prediction model. To carry out the study, a comprehensive 60-year meteorological record from Bangladesh was gathered, encompassing data on rainfall, humidity, average temperature, and sea level pressure. The results of this study suggest that the stacking average model outperforms the TFDF and RNN-LSTM models in predicting average temperature. The stacking average model achieves an RMSLE of 1.3002, which is a 10.906% improvement compared to the TFDF model. It is worth noting that the TFDF model had previously outperformed the RNN-LSTM model. The performance of the individual stacking model is not as impressive as that of the average model, with the validation results being better in TFDF. [ABSTRACT FROM AUTHOR]

The task of question matching/retrieval focuses on determining whether two questions are semantically equivalent. It has garnered significant attention in the field of natural language processing (NLP) due to its commercial value. While neural network models have made great strides and achieved human-level accuracy, they still face challenges when handling complex scenarios. In this paper, we delve into the utilization of different specializations encoded in different layers of large-scale pre-trained language models (PTMs). We propose a novel attention-based model called ERNIE-ATT that effectively integrates the diverse levels of semantics acquired by PTMs, thereby enhancing robustness. Experimental evaluations on two challenging datasets showcase the superior performance of our proposed model. It outperforms not only traditional models that do not use PTMs but also exhibits a significant improvement over strong PTM-based models. These findings demonstrate the effectiveness of our approach in enhancing the robustness of question matching/retrieval systems. [ABSTRACT FROM AUTHOR]

The COVID-19 pandemic and influenza outbreaks have underscored the critical need for predictive models that can effectively integrate spatial and temporal dynamics to enable accurate epidemic forecasting. Traditional time-series analysis approaches have fallen short in capturing the intricate interplay between these factors. Recent advancements have witnessed the incorporation of graph neural networks and machine learning techniques to bridge this gap, enhancing predictive accuracy and providing novel insights into disease spread mechanisms. Notable endeavors include leveraging human mobility data, employing transfer learning, and integrating advanced models such as Transformers and Graph Convolutional Networks (GCNs) to improve forecasting performance across diverse geographies for both influenza and COVID-19. However, these models often face challenges related to data quality, model transferability, and potential overfitting, highlighting the necessity for more adaptable and robust approaches. This paper introduces the Graph Attention-based Spatial Temporal (GAST) model, which employs graph attention networks (GATs) to overcome these limitations by providing a nuanced understanding of epidemic dynamics through a sophisticated spatio-temporal analysis framework. Our contributions include the development and validation of the GAST model, demonstrating its superior forecasting capabilities for influenza and COVID-19 spread, with a particular focus on short-term, daily predictions. The model's application to both influenza and COVID-19 datasets showcases its versatility and potential to inform public health interventions across a range of infectious diseases. [ABSTRACT FROM AUTHOR]

Artificial intelligence (AI) has the potential to revolutionize various domains by automating language-driven tasks. This study evaluates the effectiveness of an AI-assisted methodology, called the "POP Title AI Five-Step Optimization Method," in optimizing content titles on the RED social media platform. By leveraging advancements in natural language generation, this methodology aims to enhance the impact of titles by incorporating emotional sophistication and cultural proficiency, addressing existing gaps in AI capabilities. The methodology entails training generative models using human-authored examples that align with the aspirations of the target audience. By incorporating popular keywords derived from user searches, the relevance and discoverability of titles are enhanced. Audience-centric filtering is subsequently employed to further refine the generated outputs. Furthermore, human oversight is introduced to provide essential intuition that AI systems alone may lack. A total of one thousand titles, generated by AI, underwent linguistic and engagement analyses. Qualitatively, 65% of the titles exhibited intrigue and conveyed meaning comparable to those generated by humans. However, attaining full emotional sophistication remained a challenge. Quantitatively, titles emphasizing curiosity and contrast demonstrated positive correlations with user interactions, thus validating the efficacy of these techniques. Consequently, the machine-generated titles achieved coherence on par with 65% of human-generated titles, signifying significant progress and potential for further refinement. Nevertheless, achieving socio-cultural awareness is vital to match human understanding across diverse contexts, thus presenting a critical avenue for future improvement in the methodology. Continuous advancements in AI can enhance adaptability and reduce subjectivity by promoting flexibility instead of relying solely on manual reviews. As AI gains a deeper understanding of humanity, opportunities for its application across various industries through experiential reasoning abilities emerge. This case study exemplifies the nurturing of AI's potential by refining its skills through an evolutionary process. [ABSTRACT FROM AUTHOR]

To explore the application effect of the deep learning (DL) network model in the Internet of Things (IoT) database query and optimization. This study first analyzes the architecture of IoT database queries, then explores the DL network model, and finally optimizes the DL network model through optimization strategies. The advantages of the optimized model in this study are verified through experiments. Experimental results show that the optimized model has higher efficiency than other models in the model training and parameter optimization stages. Especially when the data volume is 2000, the model training time and parameter optimization time of the optimized model are remarkably lower than that of the traditional model. In terms of resource consumption, the Central Processing Unit and Graphics Processing Unit usage and memory usage of all models have increased as the data volume rises. However, the optimized model exhibits better performance on energy consumption. In throughput analysis, the optimized model can maintain high transaction numbers and data volumes per second when handling large data requests, especially at 4000 data volumes, and its peak time processing capacity exceeds that of other models. Regarding latency, although the latency of all models increases with data volume, the optimized model performs better in database query response time and data processing latency. The results of this study not only reveal the optimized model's superior performance in processing IoT database queries and their optimization but also provide a valuable reference for IoT data processing and DL model optimization. These findings help to promote the application of DL technology in the IoT field, especially in the need to deal with large-scale data and require efficient processing scenarios, and offer a vital reference for the research and practice in related fields. [ABSTRACT FROM AUTHOR]

THIS ARTICLE USES WORDS OR LANGUAGE THAT IS CONSIDERED PROFANE, VULGAR, OR OFFENSIVE BY SOME READERS. Different types of abusive content such as offensive language, hate speech, aggression, etc. have become prevalent in social media and many efforts have been dedicated to automatically detect this phenomenon in different resource-rich languages such as English. This is mainly due to the comparative lack of annotated data related to offensive language in low-resource languages, especially the ones spoken in Asian countries. To reduce the vulnerability among social media users from these regions, it is crucial to address the problem of offensive language in such low-resource languages. Hence, we present a new corpus of Persian offensive language consisting of 6,000 out of 520,000 randomly sampled micro-blog posts from X (Twitter) to deal with offensive language detection in Persian as a low-resource language in this area. We introduce a method for creating the corpus and annotating it according to the annotation practices of recent efforts for some benchmark datasets in other languages which results in categorizing offensive language and the target of offense as well. We perform extensive experiments with three classifiers in different levels of annotation with a number of classical Machine Learning (ML), Deep learning (DL), and transformer-based neural networks including monolingual and multilingual pre-trained language models. Furthermore, we propose an ensemble model integrating the aforementioned models to boost the performance of our offensive language detection task. Initial results on single models indicate that SVM trained on character or word n-grams are the best performing models accompanying monolingual transformer-based pre-trained language model ParsBERT in identifying offensive vs non-offensive content, targeted vs untargeted offense, and offensive towards individual or group. In addition, the stacking ensemble model outperforms the single models by a substantial margin, obtaining 5% respective macro F1-score improvement for three levels of annotation. [ABSTRACT FROM AUTHOR]

Engineering change (EC) risk may negatively impact project schedule, cost, quality, and stakeholder satisfaction. However, existing methods for managing EC risk have certain shortcomings in evidence selection and do not adequately consider the quality and reliability of evidence associated with EC risks. Evidence grading plays a crucial role in ensuring the reliability of decisions related to EC risks and can provide essential scientific and reliability support for decision-making. In order to explore the potential risks associated with architectural engineering changes (ECs) and identify the most significant ones, this study proposed a methodology that combines evidence grading theory and Latent Dirichlet Allocation (LDA) topic analysis means. Initially, the evidence-based grading theory served as the creation of a grading table for evidence sources related to EC risk. Specifically, we categorized the evidence sources into three levels based on their credibility. Subsequently, we selected evidence with higher credibility levels for textual analysis, utilizing the LDA topic model. This involved analyzing regulations, industry standards, and judgment documents related to EC, ultimately identifying the themes associated with EC risks. In addition, by combining EC risk topics with relevant literature, we identified factors influencing EC risks. Subsequently, we designed an expert survey questionnaire to determine the key risks and important risk topics associated with potential risks. The results show that by synthesizing information from both Class A and B evidence, a total of five prominent risk themes were identified, namely contract, technology, funds, personnel, and other hazards. Among them, the technical risk has the highest value, so it implies that the risk is the most important, and the key risks are engineering design defects, errors, and omissions. [ABSTRACT FROM AUTHOR]

This paper presents an analysis on information disorder in social media platforms. The study employed methods such as Natural Language Processing, Topic Modeling, and Knowledge Graph building to gain new insights into the phenomenon of fake news and its impact on critical thinking and knowledge management. The analysis focused on four research questions: 1) the distribution of misinformation, disinformation, and malinformation across different platforms; 2) recurring themes in fake news and their visibility; 3) the role of artificial intelligence as an authoritative and/or spreader agent; and 4) strategies for combating information disorder. The role of AI was highlighted, both as a tool for fact-checking and building truthiness identification bots, and as a potential amplifier of false narratives. Strategies proposed for combating information disorder include improving digital literacy skills and promoting critical thinking among social media users. [ABSTRACT FROM AUTHOR]

Due to the recent advances in the Internet and communication technologies, network systems and data have evolved rapidly. The emergence of new attacks jeopardizes network security and make it really challenging to detect intrusions. Multiple network attacks by an intruder are unavoidable. Our research targets the critical issue of class imbalance in intrusion detection, a reflection of the real-world scenario where legitimate network activities significantly out number malicious ones. This imbalance can adversely affect the learning process of predictive models, often resulting in high false-negative rates, a major concern in Intrusion Detection Systems (IDS). By focusing on datasets with this imbalance, we aim to develop and refine advanced algorithms and techniques, such as anomaly detection, cost-sensitive learning, and oversampling methods, to effectively handle such disparities. The primary goal is to create models that are highly sensitive to intrusions while minimizing false alarms, an essential aspect of effective IDS. This approach is not only practical for real-world applications but also enhances the theoretical understanding of managing class imbalance in machine learning. Our research, by addressing these significant challenges, is positioned to make substantial contributions to cybersecurity, providing valuable insights and applicable solutions in the fight against digital threats and ensuring robustness and relevance in IDS development. An intrusion detection system (IDS) checks network traffic for security, availability, and being non-shared. Despite the efforts of many researchers, contemporary IDSs still need to further improve detection accuracy, reduce false alarms, and detect new intrusions. The mean convolutional layer (MCL), feature-weighted attention (FWA) learning, a bidirectional long short-term memory (BILSTM) network, and the random forest algorithm are all parts of our unique hybrid model called MCL-FWA-BILSTM. The CNN-MCL layer for feature extraction receives data after preprocessing. After convolution, pooling, and flattening phases, feature vectors are obtained. The BI-LSTM and self-attention feature weights are used in the suggested method to mitigate the effects of class imbalance. The attention layer and the BI-LSTM features are concatenated to create mapped features before feeding them to the random forest algorithm for classification. Our methodology and model performance were validated using NSL-KDD and UNSW-NB-15, two widely available IDS datasets. The suggested model's accuracies on binary and multi-class classification tasks using the NSL-KDD dataset are 99.67% and 99.88%, respectively. The model's binary and multi-class classification accuracies on the UNSW-NB15 dataset are 99.56% and 99.45%, respectively. Further, we compared the suggested approach with other previous machine learning and deep learning models and found it to outperform them in detection rate, FPR, and F-score. For both binary and multiclass classifications, the proposed method reduces false positives while increasing the number of true positives. The model proficiently identifies diverse network intrusions on computer networks and accomplishes its intended purpose. The suggested model will be helpful in a variety of network security research fields and applications. [ABSTRACT FROM AUTHOR]

In the dynamic domain of logistics, effective communication is essential for streamlined operations. Our innovative solution, the Multi-Labeling Ensemble (MLEn), tackles the intricate task of extracting multi-labeled data, employing advanced techniques for accurate preprocessing of textual data through the NLTK toolkit. This approach is carefully tailored to the prevailing language used in logistics communication. MLEn utilizes innovative methods, including sentiment intensity analysis, Word2Vec, and Doc2Vec, ensuring comprehensive feature extraction. This proves particularly suitable for logistics in e-commerce, capturing nuanced communication essential for efficient operations. Ethical considerations are a cornerstone in logistics communication, and MLEn plays a pivotal role in detecting and categorizing inappropriate language, aligning inherently with ethical norms. Leveraging Tf-IDF and Vader for feature enhancement, MLEn adeptly discerns and labels ethically sensitive content in logistics communication. Across diverse datasets, including Emotions, MLEn consistently achieves impressive accuracy levels ranging from 92% to 97%, establishing its superiority in the logistics context. Particularly, our proposed method, DenseNet-EHO, outperforms BERT by 8% and surpasses other techniques by a 15-25% efficiency. A comprehensive analysis, considering metrics such as precision, recall, F1-score, Ranking Loss, Jaccard Similarity, AUC-ROC, sensitivity, and time complexity, underscores DenseNet-EHO's efficiency, aligning with the practical demands within the logistics track. Our research significantly contributes to enhancing precision, diversity, and computational efficiency in aspect-based sentiment analysis within logistics. By integrating cutting-edge preprocessing, sentiment intensity analysis, and vectorization, MLEn emerges as a robust framework for multi-label datasets, consistently outperforming conventional approaches and giving outstanding precision, accuracy, and efficiency in the logistics field. [ABSTRACT FROM AUTHOR]

Recognition of the key text of the Chinese seal can speed up the approval of documents, and improve the office efficiency of enterprises or government administrative departments. Due to image blurring and occlusion, the accuracy of Chinese seal recognition is low. In addition, the real dataset is very limited. In order to solve these problems, we improve the differentiable binarization detection algorithm (DBnet) to construct a model DB-ECA for text region detection, and propose a model named LSTR (Lightweight Seal Text Recognition) for text recognition. The efficient channel attention module is added to the differentiable binarization network to solve the feature pyramid conflict, and the convolutional layer network structure is improved to delay downsampling for reducing semantic feature loss. LSTR uses a lightweight CNN more suitable for small-sample generalization, and dynamically fuses positional and visual information through a self-attention-based inference layer to predict the label distribution of feature sequences in parallel. The inference layer not only solves the weak discriminative power of CNN in the shallow layer, but also facilitates CTC (Connectionist Temporal Classification) to accurately align the feature region with the target character. Experiments on the homemade dataset in this paper, DB-ECA compared with the other five commonly used detection models, the precision, recall, F-measure are the best effect of 90.29, 85.17, 87.65, respectively. LSTR compared with the other five kinds of recognition models in the last three years, to achieve the highest effect of accuracy 91.29%, and has the advantages of a small number of parameters and fast inference. The experimental results fully prove the innovation and effectiveness of our model. [ABSTRACT FROM AUTHOR]

Suicide-related media content has preventive or harmful effects depending on the specific content. Proactive media screening for suicide prevention is hampered by the scarcity of machine learning approaches to detect specific characteristics in news reports. This study applied machine learning to label large quantities of broadcast (TV and radio) media data according to media recommendations reporting suicide. We manually labeled 2519 English transcripts from 44 broadcast sources in Oregon and Washington, USA, published between April 2019 and March 2020. We conducted a content analysis of media reports regarding content characteristics. We trained a benchmark of machine learning models including a majority classifier, approaches based on word frequency (TF-IDF with a linear SVM) and a deep learning model (BERT). We applied these models to a selection of more simple (e.g., focus on a suicide death), and subsequently to putatively more complex tasks (e.g., determining the main focus of a text from 14 categories). Tf-idf with SVM and BERT were clearly better than the naive majority classifier for all characteristics. In a test dataset not used during model training, F1-scores (i.e., the harmonic mean of precision and recall) ranged from 0.90 for celebrity suicide down to 0.58 for the identification of the main focus of the media item. Model performance depended strongly on the number of training samples available, and much less on assumed difficulty of the classification task. This study demonstrates that machine learning models can achieve very satisfactory results for classifying suicide-related broadcast media content, including multi-class characteristics, as long as enough training samples are available. The developed models enable future large-scale screening and investigations of broadcast media. [ABSTRACT FROM AUTHOR]

The development of believable, natural, and interactive digital artificial agents is a field of growing interest. Theoretical uncertainties and technical barriers present considerable challenges to the field, particularly with regards to developing agents that effectively simulate human emotions. Large language models (LLMs) might address these issues by tapping common patterns in situational appraisal. In three empirical experiments, this study tests the capabilities of LLMs to solve emotional intelligence tasks and to simulate emotions. It presents and evaluates a new Chain-of-Emotion architecture for emotion simulation within video games, based on psychological appraisal research. Results show that it outperforms control LLM architectures on a range of user experience and content analysis metrics. This study therefore provides early evidence of how to construct and test affective agents based on cognitive processes represented in language models. [ABSTRACT FROM AUTHOR]

Our study aims to investigate the interdependence between international stock markets and sentiments from financial news in stock forecasting. We adopt the Temporal Fusion Transformers (TFT) to incorporate intra and inter-market correlations and the interaction between the information flow, i.e. causality, of financial news sentiment and the dynamics of the stock market. The current study distinguishes itself from existing research by adopting Dynamic Transfer Entropy (DTE) to establish an accurate information flow propagation between stock and sentiments. DTE has the advantage of providing time series that mine information flow propagation paths between certain parts of the time series, highlighting marginal events such as spikes or sudden jumps, which are crucial in financial time series. The proposed methodological approach involves the following elements: a FinBERT-based textual analysis of financial news articles to extract sentiment time series, the use of the Transfer Entropy and corresponding heat maps to analyze the net information flows, the calculation of the DTE time series, which are considered as co-occurring covariates of stock Price, and TFT-based stock forecasting. The Dow Jones Industrial Average index of 13 countries, along with daily financial news data obtained through the New York Times API, are used to demonstrate the validity and superiority of the proposed DTE-based causality method along with TFT for accurate stock Price and Return forecasting compared to state-of-the-art time series forecasting methods. [ABSTRACT FROM AUTHOR]

The explosive growth of dialogue data has aroused significant interest among scholars in abstractive dialogue summarization. In this paper, we propose a novel sequence-to-sequence framework called DS-SS (Dialogue Summarization with Factual-Statement Fusion and Dialogue Segmentation) for summarizing dialogues. The novelty of the DS-SS framework mainly lies in two aspects: 1) Factual statements are extracted from the source dialogue and combined with the source dialogue to perform the further dialogue encoding; and 2) A dialogue segmenter is trained and used to separate a dialogue to be encoded into several topic-coherent segments. Thanks to these two aspects, the proposed framework may better encode dialogues, thereby generating summaries exhibiting higher factual consistency and informativeness. Experimental results on two large-scale datasets SAMSum and DialogSum demonstrate the superiority of our framework over strong baselines, as evidenced by both automatic evaluation metrics and human evaluation. [ABSTRACT FROM AUTHOR]

Social networks often involve the users rating each other based on their beliefs, abilities, and other characteristics. This is particularly common in e-commerce platforms where buyers rate sellers based on their trustworthiness. However, the rating tends to vary between users due to differences in their individual scoring criteria. For example, in a transaction network, a positive user may give a high rating unless the transaction was unsatisfactory while a neutral user may give a mid-rating, consequently giving the same numeric score to different levels of satisfaction. In this paper, we propose a novel method called user tendency-based rating scaling, which adjusts the current rating (its score) based on the pattern of past ratings. We investigate whether this rating scaling method can classify between "good users" and "bad users" in online trade social networks better when compared with using the original rating scores without scaling. Classifying between good users and bad users is especially important for anonymous rating networks like Bitcoin transaction networks, where users' reputations must be recorded to preclude fraudulent and risky users. We evaluate the proposed rating scaling method by performing user classification, link prediction, and clustering tasks, using three real-world online rating network datasets. We use both the original ratings and the scaled ratings as weights of graphs and use a weighted graph embedding method to find node representations that reflect users' positive and negative information. The experimental results showed that using the proposed rating scaling method outperformed using the original (i.e., unscaled) ratings by up to 17% in classification accuracy, and by up to 2.5% in link prediction based on the AUC ROC measure, and by up to 21% in the clustering tasks based on the Dunn-index. [ABSTRACT FROM AUTHOR]

Natural disasters, like pandemics and earthquakes, are some of the main causes of distress and casualties. Governmental crisis management processes are crucial when dealing with these types of problems. Social media platforms are among the main sources of information regarding current events and public opinion. So, they have been used extensively to aid disaster detection and prevention efforts. Therefore, there is always a need for better automatic systems that can detect and classify disaster data of social media. In this work, we propose enhanced Arabic disaster data classification models. The suggested models utilize domain adaptation to provide state-of-the-art accuracy. We used a standard dataset of Arabic disaster data collected from Twitter for testing the proposed models. Experimental results show that the provided models significantly outperform the previous state-of-the-art results. [ABSTRACT FROM AUTHOR]

Machine learning techniques that rely on textual features or sentiment lexicons can lead to erroneous sentiment analysis. These techniques are especially vulnerable to domain-related difficulties, especially when dealing in Big data. In addition, labeling is time-consuming and supervised machine learning algorithms often lack labeled data. Transfer learning can help save time and obtain high performance with fewer datasets in this field. To cope this, we used a transfer learning-based Multi-Domain Sentiment Classification (MDSC) technique. We are able to identify the sentiment polarity of text in a target domain that is unlabeled by looking at reviews in a labelled source domain. This research aims to evaluate the impact of domain adaptation and measure the extent to which transfer learning enhances sentiment analysis outcomes. We employed transfer learning models BERT, RoBERTa, ELECTRA, and ULMFiT to improve the performance in sentiment analysis. We analyzed sentiment through various transformer models and compared the performance of LSTM and CNN. The experiments are carried on five publicly available sentiment analysis datasets, namely Hotel Reviews (HR), Movie Reviews (MR), Sentiment140 Tweets (ST), Citation Sentiment Corpus (CSC), and Bioinformatics Citation Corpus (BCC), to adapt multi-target domains. The performance of numerous models employing transfer learning from diverse datasets demonstrating how various factors influence the outputs. [ABSTRACT FROM AUTHOR]

In this article, we present the Brazilian Portuguese Lexicon, a new word-based corpus for psycholinguistic and computational linguistic research in Brazilian Portuguese. We describe the corpus development, the specific characteristics on the internet site and database for user access. We also perform distributional analyses of the corpus and comparisons to other current databases. Our main objective was to provide a large, reliable, and useful word-based corpus with a dynamic, easy-to-use, and intuitive interface with free internet access for word and word-criteria searches. We used the Núcleo Interinstitucional de Linguística Computacional’s corpus as the basic data source and developed the Brazilian Portuguese Lexicon by deriving and adding metalinguistic and psycholinguistic information about Brazilian Portuguese words. We obtained a final corpus with more than 30 million word tokens, 215 thousand word types and 25 categories of information about each word. This corpus was made available on the internet via a free-access site with two search engines: a simple search and a complex search. The simple engine basically searches for a list of words, while the complex engine accepts all types of criteria in the corpus categories. The output result presents all entries found in the corpus with the criteria specified in the input search and can be downloaded as a.csv file. We created a module in the results that delivers basic statistics about each search. The Brazilian Portuguese Lexicon also provides a pseudoword engine and specific tools for linguistic and statistical analysis. Therefore, the Brazilian Portuguese Lexicon is a convenient instrument for stimulus search, selection, control, and manipulation in psycholinguistic experiments, as also it is a powerful database for computational linguistics research and language modeling related to lexicon distribution, functioning, and behavior. [ABSTRACT FROM AUTHOR]

In the dynamic landscape of financial markets, accurate forecasting of stock indices remains a pivotal yet challenging task, essential for investors and policymakers alike. This study is motivated by the need to enhance the precision of predicting the Shanghai Composite Index's opening price spread, a critical measure reflecting market volatility and investor sentiment. Traditional time series models like ARIMA have shown limitations in capturing the complex, nonlinear patterns inherent in stock price movements, prompting the exploration of advanced methodologies. The aim of this research is to bridge the gap in forecasting accuracy by developing a hybrid model that integrates the strengths of ARIMA with deep learning techniques, specifically Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) networks. This novel approach leverages the ARIMA model's proficiency in linear trend analysis and the deep learning models' capability in modeling nonlinear dependencies, aiming to provide a comprehensive tool for market prediction. Utilizing a comprehensive dataset covering the period from December 20, 1990, to June 2, 2023, the study develops and assesses the efficacy of ARIMA, LSTM, GRU, ARIMA-LSTM, and ARIMA-GRU models in forecasting the Shanghai Composite Index's opening price spread. The evaluation of these models is based on key statistical metrics, including Mean Squared Error (MSE) and Mean Absolute Error (MAE), to gauge their predictive accuracy. The findings indicate that the hybrid models, ARIMA-LSTM and ARIMA-GRU, perform better in forecasting the opening price spread of the Shanghai Composite Index than their standalone counterparts. This outcome suggests that combining traditional statistical methods with advanced deep learning algorithms can enhance stock market prediction. The research contributes to the field by providing evidence of the potential benefits of integrating different modeling approaches for financial forecasting, offering insights that could inform investment strategies and financial decision-making. [ABSTRACT FROM AUTHOR]

Today, with the advent of Large-scale generative Language Models (LLMs) it is now possible to simulate free responses to interview questions such as those traditionally analyzed using qualitative research methods. Qualitative methodology encompasses a broad family of techniques involving manual analysis of open-ended interviews or conversations conducted freely in natural language. Here we consider whether artificial "silicon participants" generated by LLMs may be productively studied using qualitative analysis methods in such a way as to generate insights that could generalize to real human populations. The key concept in our analysis is algorithmic fidelity, a validity concept capturing the degree to which LLM-generated outputs mirror human sub-populations' beliefs and attitudes. By definition, high algorithmic fidelity suggests that latent beliefs elicited from LLMs may generalize to real humans, whereas low algorithmic fidelity renders such research invalid. Here we used an LLM to generate interviews with "silicon participants" matching specific demographic characteristics one-for-one with a set of human participants. Using framework-based qualitative analysis, we showed the key themes obtained from both human and silicon participants were strikingly similar. However, when we analyzed the structure and tone of the interviews we found even more striking differences. We also found evidence of a hyper-accuracy distortion. We conclude that the LLM we tested (GPT-3.5) does not have sufficient algorithmic fidelity to expect in silico research on it to generalize to real human populations. However, rapid advances in artificial intelligence raise the possibility that algorithmic fidelity may improve in the future. Thus we stress the need to establish epistemic norms now around how to assess the validity of LLM-based qualitative research, especially concerning the need to ensure the representation of heterogeneous lived experiences. [ABSTRACT FROM AUTHOR]

A crucial part of sentiment classification is featuring extraction because it involves extracting valuable information from text data, which affects the model's performance. The goal of this paper is to help in selecting a suitable feature extraction method to enhance the performance of sentiment analysis tasks. In order to provide directions for future machine learning and feature extraction research, it is important to analyze and summarize feature extraction techniques methodically from a machine learning standpoint. There are several methods under consideration, including Bag-of-words (BOW), Word2Vector, N-gram, Term Frequency- Inverse Document Frequency (TF-IDF), Hashing Vectorizer (HV), and Global vector for word representation (GloVe). To prove the ability of each feature extractor, we applied it to the Twitter US airlines and Amazon musical instrument reviews datasets. Finally, we trained a random forest classifier using 70% of the training data and 30% of the testing data, enabling us to evaluate and compare the performance using different metrics. Based on our results, we find that the TD-IDF technique demonstrates superior performance, with an accuracy of 99% in the Amazon reviews dataset and 96% in the Twitter US airlines dataset. This study underscores the paramount significance of feature extraction in sentiment analysis, endowing pragmatic insights to elevate model performance and steer future research pursuits. [ABSTRACT FROM AUTHOR]

Code clones, referring to code fragments that are either similar or identical and are copied and pasted within software systems, have negative effects on both software quality and maintenance. The objective of this work is to systematically review and analyze recurrent neural network techniques used to detect code clones to shed light on the current techniques and offer valuable knowledge to the research community. Upon applying the review protocol, we have successfully identified 20 primary studies within this field from a total of 2099 studies. A deep investigation of these studies reveals that nine recurrent neural network techniques have been utilized for code clone detection, with a notable preference for LSTM techniques. These techniques have demonstrated their efficacy in detecting both syntactic and semantic clones, often utilizing abstract syntax trees for source code representation. Moreover, we observed that most studies applied evaluation metrics like F-score, precision, and recall. Additionally, these studies frequently utilized datasets extracted from open-source systems coded in Java and C programming languages. Notably, the Graph-LSTM technique exhibited superior performance. PyTorch and TensorFlow emerged as popular tools for implementing RNN models. To advance code clone detection research, further exploration of techniques like parallel LSTM, sentence-level LSTM, and Tree-Structured GRU is imperative. In addition, more research is needed to investigate the capabilities of the recurrent neural network techniques for identifying semantic clones across different programming languages and binary codes. The development of standardized benchmarks for languages like Python, Scratch, and C#, along with cross-language comparisons, is essential. Therefore, the utilization of recurrent neural network techniques for clone identification is a promising area that demands further research. [ABSTRACT FROM AUTHOR]

Every day thousands of news are published on the web and filtering tools can be used to extract knowledge on specific topics. The categorization of news into a predefined set of topics is a subject widely studied in the literature, however, most works are restricted to documents in English. In this work, we make two contributions. First, we introduce a Portuguese news dataset collected from WikiNews an open-source media that provide news from different sources. Since there is a lack of datasets for Portuguese, and an existing one is from a single news channel, we aim to introduce a dataset from different news channels. The availability of comprehensive datasets plays a key role in advancing research. Second, we compare different architectures for Portuguese news classification, exploring different text representations (BoW, TF-IDF, Embedding) and classification techniques (SVM, CNN, DJINN, BERT) for documents in Portuguese, covering classical methods and current technologies. We show the trade-off between accuracy and training time for this application. We aim to show the capabilities of available algorithms and the challenges faced in the area. [ABSTRACT FROM AUTHOR]

Long short-term memory (LSTM) has been effectively used to represent sequential data in recent years. However, LSTM still struggles with capturing the long-term temporal dependencies. In this paper, we propose an hourglass-shaped LSTM that is able to capture long-term temporal correlations by reducing the feature resolutions without data loss. We have used skip connections in non-adjacent layers to avoid gradient decay. In addition, an attention process is incorporated into skip connections to emphasize the essential spectral features and spectral regions. The proposed LSTM model is applied to speech enhancement and recognition applications. The proposed LSTM model uses no future information, resulting in a causal system suitable for real-time processing. The combined spectral feature sets are used to train the LSTM model for improved performance. Using the proposed model, the ideal ratio mask (IRM) is estimated as a training objective. The experimental evaluations using short-time objective intelligibility (STOI) and perceptual evaluation of speech quality (PESQ) have demonstrated that the proposed model with robust feature representation obtained higher speech intelligibility and perceptual quality. With the TIMIT, LibriSpeech, and VoiceBank datasets, the proposed model improved STOI by 16.21%, 16.41%, and 18.33% over noisy speech, whereas PESQ is improved by 31.1%, 32.9%, and 32%. In seen and unseen noisy situations, the proposed model outperformed existing deep neural networks (DNNs), including baseline LSTM, feedforward neural network (FDNN), convolutional neural network (CNN), and generative adversarial network (GAN). With the Kaldi toolkit for automated speech recognition (ASR), the proposed model significantly reduced the word error rates (WERs) and reached an average WER of 15.13% in noisy backgrounds. [ABSTRACT FROM AUTHOR]

To enhance our ability to model long-range semantical dependencies, we introduce a novel approach for linguistic steganography through English translation. This method leverages attention mechanisms and probability distribution theory, known as NMT-stega (Neural Machine Translation-steganography). Specifically, to optimize translation accuracy and make full use of valuable source text information, we employ an attention-based NMT model as our translation technique. To address potential issues related to the degradation of text quality due to secret information embedding, we have devised a dynamic word pick policy based on probability variance. This policy adaptively constructs an alternative set and dynamically adjusts embedding capacity at each time step, guided by variance thresholds. Additionally, we have incorporated prior knowledge into the model by introducing a hyper-parameter that balances the contributions of the source and target text when predicting the embedded words. Extensive ablation experiments and comparative analyses, conducted on a large-scale Chinese-English corpus, validate the effectiveness of the proposed method across several critical aspects, including embedding rate, text quality, anti-steganography, and semantical distance. Notably, our numerical results demonstrate that the NMT-stega method outperforms alternative approaches in anti-steganography tasks, achieving the highest scores in two steganalysis models, NFZ-WDA (with score of 53) and LS-CNN (with score of 56.4). This underscores the superiority of NMT-stega in the anti-steganography attack task. Furthermore, even when generating longer sentences, with average lengths reaching 47 words, our method maintains strong semantical relationships, as evidenced by a semantic distance of 87.916. Moreover, we evaluate the proposed method using two metrics, Bilingual Evaluation Understudy and Perplexity, and achieve impressive scores of 42.103 and 23.592, respectively, highlighting its exceptional performance in the machine translation task. [ABSTRACT FROM AUTHOR]

Vocabulary tests, once a cornerstone of language modeling evaluation, have been largely overlooked in the current landscape of Large Language Models (LLMs) like Llama 2, Mistral, and GPT. While most LLM evaluation benchmarks focus on specific tasks or domain-specific knowledge, they often neglect the fundamental linguistic aspects of language understanding. In this paper, we advocate for the revival of vocabulary tests as a valuable tool for assessing LLM performance. We evaluate seven LLMs using two vocabulary test formats across two languages and uncover surprising gaps in their lexical knowledge. These findings shed light on the intricacies of LLM word representations, their learning mechanisms, and performance variations across models and languages. Moreover, the ability to automatically generate and perform vocabulary tests offers new opportunities to expand the approach and provide a more complete picture of LLMs' language skills.

Automatic Urdu handwritten text recognition is a challenging task in the OCR industry. Unlike printed text, Urdu handwriting lacks a uniform font and structure. This lack of uniformity causes data inconsistencies and recognition issues. Different writing styles, cursive scripts, and limited data make Urdu text recognition a complicated task. Major languages, such as English, have experienced advances in automated recognition, whereas low-resource languages, such as Urdu, still lag. Transformer-based models are promising for automated recognition in high- and low-resource languages such as Urdu. This paper presents a transformer-based method called ET-Network that integrates self-attention into EfficientNet for feature extraction and a transformer for language modeling. The use of self-attention layers in EfficientNet helps to extract global and local features that capture long-range dependencies. These features proceeded into a vanilla transformer to generate text, and a prefix beam search is used for the finest outcome. NUST-UHWR, UPTI2.0, and MMU-OCR-21 are three datasets used to train and test the ET Network for a handwritten Urdu script. The ET-Network improved the character error rate by 4% and the word error rate by 1.55%, while establishing a new state-of-the-art character error rate of 5.27% and a word error rate of 19.09% for Urdu handwritten text.

Recent work on transformer-based neural networks has led to impressive advances on multiple-choice natural language processing (NLP) problems, such as Question Answering (QA) and abductive reasoning. Despite these advances, there is limited work still on systematically evaluating such models in ambiguous situations where (for example) no correct answer exists for a given prompt among the provided set of choices. Such ambiguous situations are not infrequent in real world applications. We design and conduct an experimental study of this phenomenon using three probes that aim to 'confuse' the model by perturbing QA instances in a consistent and well-defined manner. Using a detailed set of results based on an established transformer-based multiple-choice QA system on two established benchmark datasets, we show that the model's confidence in its results is very different from that of an expected model that is 'agnostic' to all choices that are incorrect. Our results suggest that high performance on idealized QA instances should not be used to infer or extrapolate similarly high performance on more ambiguous instances. Auxiliary results suggest that the model may not be able to distinguish between these two situations with sufficient certainty. Stronger testing protocols and benchmarking may hence be necessary before such models are deployed in front-facing systems or ambiguous decision making with significant human impact. [ABSTRACT FROM AUTHOR]