Search

Cycling is an eco-friendly and sustainable mode of transportation. Despite its benefits, the cyclists’ risk of collision is still high when interacting with other road users. This study analyzed self-reported near-miss and collision event descriptions for the United States provided by the crowdsourcing platform, BikeMaps.org. Innovative and efficient analytic methods are needed to generate useful information from unstructured textual data sources in the transportation domain. In this study, explorative text mining, topic modeling, and machine learning are utilized to gain insights from the unstructured textual descriptions of crowdsourced near-miss and collision events. The approaches are used to unveil prevalent words and word associations for near-miss and collision events. Structural Topic Modeling (STM) is deployed to autogenerate latent themes or topics from the event descriptions. The generated topic proportions are used as input in Artificial Neural Networks (ANN) to estimate the cyclist’s propensity to a collision. It was found that cyclists had a higher propensity to a collision in topics that articulated vehicle encroachment to the bike lane, on-street parking close or into the bike lane resulting in dooring, and drivers’ violations at the crosswalk. The results and methodology used in this study can assist engineers, policymakers, and law enforcement officers to proactively reduce potential cyclist collisions, prioritizing areas where cyclist safety improvements are needed, and ultimately promoting bicycle ridership in our communities.

Ranked keyword search has gained increasing attention due to its attractive advantages such as flexibility and accessibility. However, most existing ranked keyword search schemes ignore the semantic associations between the documents and queries. To solve this challenging issue in cloud-assisted edge computing, we first design the Semantic-aware Ranked Multi-keyword \textbf{S}earch (SRMS) scheme by adopting the Latent Dirichlet Allocation (LDA) topic model and the Chinese Remainder Theorem (CRT)-based secret sharing mechanism. Considering that the cloud server may be malicious, we implement a basic verification mechanism in SRMS to verify the correctness and completeness of search results and extend this verification mechanism in cloud-assisted edge computing scenarios. Formal security analysis proves that SRMS and extended result verification mechanisms are secure in both the known ciphertext model and the known background model. Extensive experiments using the real-world dataset demonstrate that SRMS is efficient and feasible in practical applications.

For multimodal representation learning, traditional black-box approaches often fall short of extracting interpretable multilayer hidden structures, which contribute to visualize the connections between different modalities at multiple semantic levels. To extract interpretable multimodal latent representations and visualize the hierarchial semantic relationships between different modalities, based on deep topic models, we develop a novel multimodal Poisson gamma belief network (mPGBN) that tightly couples the observations of different modalities via imposing sparse connections between their modality-specific hidden layers. To alleviate the time-consuming Gibbs sampler adopted by traditional topic models in the testing stage, we construct a Weibull-based variational inference network (encoder) to directly map the observations to their latent representations, and further combine it with the mPGBN (decoder), resulting in a novel multimodal Weibull variational autoencoder (MWVAE), which is fast in out-of-sample prediction and can handle large-scale multimodal datasets. Qualitative evaluations on bimodal data consisting of image-text pairs show that the developed MWVAE can successfully extract expressive multimodal latent representations for downstream tasks like missing modality imputation and multimodal retrieval. Further extensive quantitative results demonstrate that both MWVAE and its supervised extension sMWVAE achieve state-of-the-art performance on various multimodal benchmarks.

Traditional searchable encryption schemes based on the Term Frequency-Inverse Document Frequency (TF-IDF) model adopt the presence of keywords to measure the relevance of documents to queries, which ignores the latent semantic meanings that are concealed in the context. Latent Dirichlet Allocation (LDA) topic model can be utilized for modeling the semantics among texts to achieve semantic-aware multi-keyword search. However, the LDA topic model treats queries and documents from the perspective of topics, and the keywords information is ignored. In this paper, we propose a privacy-preserving searchable encryption scheme based on the LDA topic model and the query likelihood model. We extract the feature keywords from the document using the LDA-based Information Gain (IG) and Topic Frequency-Inverse Topic Frequency (TF-ITF) model. With feature keyword extraction and the query likelihood model, our scheme can achieve a more accurate semantic-aware keyword search. A special index tree is used to enhance search efficiency. The secure inner product operation is utilized to implement the privacy-preserving ranked search. The experiments on real-world datasets demonstrate the effectiveness of our scheme.

Deliberative systems theorists have for some time emphasised the distributed nature of deliberative values; they therefore do not focus exclusively on ‘deliberation’ but on all sorts of communication that advance deliberative democratic values, including everyday political talk in informal settings. However, such talk has been impossible to capture inductively at scale. This article discusses an electronic approach, Structural Topic Modelling, and applies it to a recent case: the Scottish independence debate of 2012–2014. The case provides the first empirical test of the claim that a deliberative system can capture the full ‘pool of perspectives’ on an issue, and shows that citizens can hold each other to deliberative standards even in mass, online discussion. It also shows that, in deliberative terms, the major cleavage in the ‘indyref’ debate was not so much between Yes and No, but between formal and informal venues.

Topic modeling is a significant branch of natural language processing and machine learning focused on inferring the generative process of text. Traditionally, algorithms for estimating topic models have relied on Bayesian inference and Gibbs sampling. This paper proposes a novel “acceptable set” framework for formulating topic modeling problems inspired by ideas from discrete component analysis and data-driven robust optimization. Our approach not only simplifies the design and inference of topic models, but also allows for extensions and generalizations that are challenging to integrate into traditional approaches. Different restrictions (e.g., sparsity) and assumptions (e.g., alternative generative processes) can be easily incorporated into our formulations through additional or modified constraints. Our formulations also naturally control a widely used metric of model quality, perplexity. We adapt state-of-the-art stochastic gradient methods to find good local optima for the optimization formulations. The algorithms are efficient, scaling to realistic problem sizes with runtimes comparable to existing methods. Through extensive computational experiments, we show that our methods have improved solution quality compared to baseline methods and reconstruct more reliably the underlying generative models. Our framework overcomes known vulnerabilities of traditional topic modeling algorithms: our methods are effective in low-data settings, register good out-of-sample performance, and perform well for a variety of initial assumptions on input parameter values.

In the era of social networks, the rapid growth of data mining in information retrieval and natural language processing makes automatic text summarization necessary. Currently, pretrained word embedding and sequence to sequence models can be effectively adapted in social network summarization to extract significant information with strong encoding capability. However, how to tackle the long text dependence and utilize the latent topic mapping has become an increasingly crucial challenge for these models. In this article, we propose a topic-aware extractive and abstractive summarization model named T-BERTSum, based on Bidirectional Encoder Representations from Transformers (BERTs). This is an improvement over previous models, in which the proposed approach can simultaneously infer topics and generate summarization from social texts. First, the encoded latent topic representation, through the neural topic model (NTM), is matched with the embedded representation of BERT, to guide the generation with the topic. Second, the long-term dependencies are learned through the transformer network to jointly explore topic inference and text summarization in an end-to-end manner. Third, the long short-term memory (LSTM) network layers are stacked on the extractive model to capture sequence timing information, and the effective information is further filtered on the abstractive model through a gated network. In addition, a two-stage extractive-abstractive model is constructed to share the information. Compared with the previous work, the proposed model T-BERTSum focuses on pretrained external knowledge and topic mining to capture more accurate contextual representations. Experimental results on the CNN/Daily mail and XSum datasets demonstrate that our proposed model achieves new state-of-the-art results while generating consistent topics compared with the most advanced method.

Currently, the world is in the midst of a severe global pandemic, which has affected all aspects of people's lives. As a result, there is a deluge of COVID-related digital media articles published in the United States, due to the disparate effects of the pandemic. This large volume of information is difficult to consume by the audience in a reasonable amount of time. In this paper, we develop a Natural Language Processing (NLP) pipeline that is capable of automatically distilling various digital articles into manageable pieces of information, while also modelling the progression topics discussed over time in order to aid readers in rapidly gaining holistic perspectives on pressing issues (i.e., the COVID-19 pandemic) from a diverse array of sources. We achieve these goals by first collecting a large corpus of COVID-related articles during the onset of the pandemic. After, we apply unsupervised and semi-supervised learning procedures to summarize articles, then cluster them based on their similarities using the community detection methods. Next, we identify the topic of each cluster of articles using the BART algorithm. Finally, we provide a detailed digital media analysis based on the NLP-pipeline outputs and show how the conversation surrounding COVID-19 evolved over time.

Deep learning models have achieved high performance across different domains, such as medical decision-making, autonomous vehicles, decision support systems, among many others. However, despite this success, the inner mechanisms of these models are opaque because their internal representations are too complex for a human to understand. This opacity makes it hard to understand the how or the why of the predictions of deep learning models. There has been a growing interest in model-agnostic methods that make deep learning models more transparent and explainable to humans. Some researchers recently argued that for a machine to achieve human-level explainability, this machine needs to provide human causally understandable explanations, also known as causability. A specific class of algorithms that have the potential to provide causability are counterfactuals. This paper presents an in-depth systematic review of the diverse existing literature on counterfactuals and causability for explainable artificial intelligence (AI). We performed a Latent Dirichlet topic modeling analysis (LDA) under a Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) framework to find the most relevant literature articles. This analysis yielded a novel taxonomy that considers the grounding theories of the surveyed algorithms, together with their underlying properties and applications to real-world data. Our research suggests that current model-agnostic counterfactual algorithms for explainable AI are not grounded on a causal theoretical formalism and, consequently, cannot promote causability to a human decision-maker. Furthermore, our findings suggest that the explanations derived from popular algorithms in the literature provide spurious correlations rather than cause/effects relationships, leading to sub-optimal, erroneous, or even biased explanations. Thus, this paper also advances the literature with new directions and challenges on promoting causability in model-agnostic approaches for explainable AI.

Document clustering allows a user to group semantically similar documents. It has been an interesting research area for the past many years and various methods and techniques have been developed. However, the research has primarily been limited to English and other high resource languages. For low-resource languages, such as Urdu, the area of document clustering is open to contributions. This work presents an experimental evaluation of clustering techniques on Urdu tweets. It is a challenging task to semantically cluster tweets due to their very short length. In this paper, various features, including sentence and phrase-level embeddings, TF-IDF features and document embeddings are extracted from tweets and clustering is performed using three different algorithms: K-Means, Bisecting K-Means, and Affinity Propagation algorithms. Furthermore, a comparison is performed with the traditional topic modeling approach. The results indicate that the TF-IDF features combined with the K-means clustering algorithm outperformed the adopted clustering techniques.

Probabilistic topic models, such as latent Dirichlet allocation (LDA), are often used to discover hidden semantic structure of a collection of documents. In recent years, various inference algorithms have been developed to cope with learning of topic models, among which Gibbs sampling methods remain a popular choice. In this paper, we aim to improve the inference of topic models based on the Gibbs sampling framework. We extend a state augmentation based Gibbs sampling method by maximizing the replications of latent states, and propose a new generic deterministic inference method, named maximal latent state replication (MAX), for learning of a family of probabilistic topic models. One key benefit of the proposed method lies in the deterministic nature for inference, which may help to improve its running efficiency as well as predictive perplexity. We have conducted extensive experiments on real-life publicly available datasets, and the results have validated that our proposed method MAX significantly outperforms state-of-the-art baselines for inference of existing well-known topic models.

The widespread use of positioning devices has given rise to many trajectories, with each having three explicit attributes: user ID, location ID, and time-stamp and an implicit attribute: activity type (akin to “topic” in text mining). To model these trajectories, existing works learn different attribute representations by either introducing latent activity types based on topic models or transforming the location and time context into a low-dimensional space via embedding techniques. In this paper, we propose a holistic approach named Human Mobility Representation Model (HMRM) to simultaneously produce the vector representations of all four (explicit and implicit) attributes. The merits of HMRM lie in that: (1) it models the latent activity types and learns trajectory attribute embeddings in an integrated manner, and (2) it connects the activity-related distributions and these attributes embeddings by adding a newly designed collaborative learning component, and makes them mutually exchanged to take the best of both worlds. We apply HMRM to both unsupervised and supervised tasks including two activity evaluation tasks and two embedding evaluation tasks, on two real check-in datasets collected from Foursquare. Experimental results show that HMRM could not only improve the performance of capturing latent activity types, but also learn better trajectory embeddings.

With the prevalence of smartphones, people have left abundant behavior records in cyberspace. Discovering and understanding individuals' cyber activities can provide useful implications for policymakers, service providers, and app developers. In this paper, we propose a framework to discover daily cyber activity patterns across people's mobile app usage. We first segment app usage traces into small time windows and then design a probabilistic topic model to infer users' cyber activities of each window. By exploring the coherence of users' activity sequences, the daily patterns of individuals are identified. Next, we recognize the common patterns across diverse groups of individuals using a hierarchical clustering algorithm. We then apply our framework on a large-scale and real-world dataset, consisting of 653,092 users with 971,818,946 usage records of 2,000 popular mobile apps. Our analysis shows that people usually obey yesterday's activity patterns, but the patterns tend to deviate as the time-lapse increases. We also discover five common daily cyber activity patterns, including afternoon reading, nightly entertainment, pervasive socializing, commuting, and nightly socializing. Our findings have profound implications on identifying the demographics of users and their lifestyles, habits, service requirements, and further detecting other disrupting trends such as working overtime and addiction to the game and social media.

Recently, advances in neural network approaches have achieved many successes in both sentiment classification and probabilistic topic modelling. On the one hand, latent topics derived from the global context of documents could be helpful in capturing more accurate word semantics and hence could potentially improve the sentiment classification accuracy. On the other hand, the word-level attention vectors obtained during the learning of sentiment classifiers could carry word-level polarity information and can be used to guide the discovery of topics in topic modelling. This paper proposes a multi-task learning framework which jointly learns a sentiment classifier and a topic model by making the word-level latent topic distributions in the topic model to be similar to the word-level attention vectors in the classifier through mutual learning. Experimental results on the Yelp and IMDB datasets verify the superior performance of the proposed framework over strong baselines on both sentiment classification accuracy and topic modelling evaluation results including perplexity and topic coherence measures. The proposed framework also extracts more interpretable topics compared to other conventional topic models and neural topic models.

We introduce and assess the use of supervised learning in cross-domain topic classification. In this approach, an algorithm learns to classify topics in a labeled source corpus and then extrapolates topics in an unlabeled target corpus from another domain. The ability to use existing training data makes this method significantly more efficient than within-domain supervised learning. It also has three advantages over unsupervised topic models: the method can be more specifically targeted to a research question and the resulting topics are easier to validate and interpret. We demonstrate the method using the case of labeled party platforms (source corpus) and unlabeled parliamentary speeches (target corpus). In addition to the standard within-domain error metrics, we further validate the cross-domain performance by labeling a subset of target-corpus documents. We find that the classifier accurately assigns topics in the parliamentary speeches, although accuracy varies substantially by topic. We also propose tools diagnosing cross-domain classification. To illustrate the usefulness of the method, we present two case studies on how electoral rules and the gender of parliamentarians influence the choice of speech topics., Political Analysis, 31 (1), ISSN:1047-1987, ISSN:1476-4989

With the rapid growth of social network users, the social network has accumulated massive social network topics. However, due to the randomness of content, it becomes sparse and noisy, accompanied by many daily chats and meaningless topics, which brings challenges to bursty topics discovery. To deal with these problems, this paper proposes the spatial-temporal topic model with sparse prior and recurrent neural networks (RNN) prior for bursty topic discovering (ST-SRTM). The semantic relationship of words is learned through RNN to alleviate the sparsity. The spatial-temporal areas information is introduced to focus on bursty topics for further weakening the semantic sparsity of social network context. Besides, we introduced the “Spike and Slab” prior to decouple the sparseness and smoothness. Simultaneously, we realized the automatic discovery of social network bursts by introducing the burstiness of words as the prior and binary switching variables. We constructed multiple sets of comparative experiments to verify the performance of ST-SRTM by leveraging different evaluation indicators on real Sina Weibo data sets. The experimental results confirm the superiority of our ST-SRTM.

Analyzing short texts infers discriminative and coherent latent topics that is a critical and fundamental task since many real-world applications require semantic understanding of short texts. Traditional long text topic modeling algorithms (e.g., PLSA and LDA) based on word co-occurrences cannot solve this problem very well since only very limited word co-occurrence information is available in short texts. Therefore, short text topic modeling has already attracted much attention from the machine learning research community in recent years, which aims at overcoming the problem of sparseness in short texts. In this survey, we conduct a comprehensive review of various short text topic modeling techniques proposed in the literature. We present three categories of methods based on Dirichlet multinomial mixture, global word co-occurrences, and self-aggregation, with example of representative approaches in each category and analysis of their performance on various tasks. We develop the first comprehensive open-source library, called STTM, for use in Java that integrates all surveyed algorithms within a unified interface, benchmark datasets, to facilitate the expansion of new methods in this research field. Finally, we evaluate these state-of-the-art methods on many real-world datasets and compare their performance against one another and versus long text topic modeling algorithm., arXiv admin note: text overlap with arXiv:1808.02215 by other authors

The amount of digital text-based consumer review data has increased dramatically and there exist many machine learning approaches for automated text-based sentiment analysis. Marketing researchers have employed various methods for analyzing text reviews but lack a comprehensive comparison of their performance to guide method selection in future applications. We focus on the fundamental relationship between a consumer’s overall empirical evaluation, and the text-based explanation of their evaluation. We study the empirical tradeoff between predictive and diagnostic abilities, in applying various methods to estimate this fundamental relationship. We incorporate methods previously employed in the marketing literature, and methods that are so far less common in the marketing literature. For generalizability, we analyze 25,119 products in nine product categories, and 260,489 reviews across five review platforms. We find that neural network-based machine learning methods, in particular pre-trained versions, offer the most accurate predictions, while topic models such as Latent Dirichlet Allocation offer deeper diagnostics. However, neural network models are not suited for diagnostic purposes and topic models are ill equipped for making predictions. Consequently, future selection of methods to process text reviews is likely to be based on analysts’ goals of prediction versus diagnostics.

Agenda setting and issue framing research investigates how frames impact public attention, policy decisions, and political outcomes. Social media sites, such as Twitter, provide opportunities to study framing dynamics in an important area of political discourse. We present a method for identifying frames in tweets and measuring their effectiveness. We use topic modeling combined with manual validation to identify recurrent problem frames and topics in thousands of tweets by gun rights and gun control groups following the Marjory Stoneman Douglas High School in Parkland, Florida, shooting. We find that each side used Twitter to advance policy narratives about the problem in Parkland. Gun rights groups’ narratives implied that more gun restrictions were not the solution. Their most effective frame focused on officials’ failures to enforce existing laws. In contrast, gun control groups portrayed easy access to guns as the problem and emphasized the importance of mobilizing politically to force change.

Sentiment analysis systems can collect and automatically structure unstructured information by collecting public views of services, products, policy, brands, etc. This information is of major value in the fields of marketing analysis, public relations, product reviews, net promoter evaluations, customer feedback and client reviews. Literary works, on the other hand, are less susceptible to computational analysis because there are no immediate commercial incentives. However, similar techniques can be used to evaluate literary work, comprehend the underlying social network, and obtain or validate literary work. This project is about analyzing the book's characters and predicting their characteristics and relationships with one another. A lot of human effort is expended during the adaptation of a novel/book in any form, which is inconvenient and undesirable. Furthermore, the human brain has a tendency to overlook a number of minor details about the events/characters in the book. The scenario described above can frequently result in inaccuracies in the adaptation's plot. As a result, the project is an innovation that aims to aid in the easy and accurate adaptation of a book, making the process much simpler and precise. Machine learning (supervised and unattended) and lexical approaches include the current sentiment analysis techniques. The model's goal is to scan the massive amounts of text in the book. Following digitization, the model will display interesting ideas derived from the given book using a combination of natural language processing, feelings and emotions analysis, and social network analysis methodology.

Generating explanations within a local and model-agnostic explanation scenario for text classification is often accompanied by a local approximation task. In order to create a local neighborhood for a document, whose classification shall be explained, sampling techniques are used that most often treat the according features at least semantically independent from each other. Hence, contextual as well as semantic information is lost and therefore cannot be used to update a human’s mental model within the according explanation task. In case of dependent features, such explanation techniques are prone to extrapolation to feature areas with low data density, therefore causing misleading interpretations. Additionally, the ”the whole is greater than the sum of its parts” phenomenon is disregarded when using explanations that treat the according words independently from each other. In this paper, an architecture named CaSE is proposed that either uses Semantic Feature Arrangements or Semantic Interrogations to overcome these drawbacks. Combined with a modified version of Local interpretable model-agnostic explanations (LIME), a state of the art local explanation framework, it is capable of generating meaningful and coherent explanations. The approach utilizes contextual and semantic knowledge from unsupervised topic models in order to enable realistic and semantic sampling and based on that generate understandable explanations for any text classifier. The key concepts of CaSE that are deemed essential for providing humans with high quality explanations are derived from findings of psychology. In a nutshell, CaSE shall enable Semantic Alignment between humans and machines and thus further improve the basis for Interactive Machine Learning. An extensive experimental validation of CaSE is conducted, showing its effectiveness by generating reliable and meaningful explanations whose elements are made of contextually coherent words and therefore are suitable to update human mental models in an appropriate way. In the course of a quantitative analysis, the proposed architecture is evaluated w.r.t. a consistency property and to Local Fidelity of the resulting explanation models. According to that, CaSE generates more realistic explanation models leading to higher Local Fidelity compared to LIME.

Social media have shown great potential for producing significant changes in behavior and have become the cornerstone for many public health and agency efforts. The nonprofit sector -including blood collection agencies- has adopted social media to aid their cause and reach their goals. However, despite the tremendous impact of social media on society and its promising role for donor recruitment and retention, it has been overlooked in donor research. This study therefore sought to map the social media landscape around blood donation. We showcase an inductive computational method to make sense of vast amounts of dynamic unstructured blood donation text data that exists on social media. With this method, we display what is discussed about blood donation on social media, how these topics are distributed on Facebook and Twitter, and how the prevalence of these topics changes over time. We applied structural topic modeling on 7 years of Dutch blood donation Facebook and Twitter data by the general public. We found 25 topics clustered in 6 distinct clusters. Over time, there is a substantial reduction of messages in which donors announce their donations. Topics that emphasize the positives of blood donation, including donor identity-related topics, are rising. In addition, the findings show a clear social media platform contrast. Topics related to campaigns and controversial policies were found more on Twitter and positive donation topics and topics related to the donation process more on Facebook. To make optimal use of social media for recruitment and retention campaigns and efforts, blood collection agencies should recognize the turbulent environment in which they take place. Monitoring public opinions about blood donation will help blood collection agencies make strategic choices and utilize social media more effectively.

The agricultural futures prices are generally considered difficult to forecast because the causes of fluctuations are incredibly complicated. We propose a text-based forecasting framework, which can effectively identify and quantify factors affecting agricultural futures based on massive online news headlines. A comprehensive list of influential factors can be formed using a text mining method called topic modeling. A new sentiment-analysis-based way is designed to quantify the factors such as the weather and policies that are important yet difficult to quantify. The proposed framework is empirically tested at forecasting soybean futures prices in the Chinese market. Testing was based on 9715 online news headlines from July 19, 2012 to July 9, 2018. The results show that the identified influential factors and sentiment-based variables are effective, and the proposed framework performs significantly better in medium-term and long-term forecasting than the benchmark model.

Learning hidden topics from data streams has become absolutely necessary but posed challenging problems such as concept drift as well as short and noisy data. Using prior knowledge to enrich a topic model is one of potential solutions to cope with these challenges. Prior knowledge that is derived from human knowledge (e.g. Wordnet) or a pre-trained model (e.g. Word2vec) is very valuable and useful to help topic models work better. However, in a streaming environment where data arrives continually and infinitely, existing studies are limited to exploiting these resources effectively. Especially, a knowledge graph, that contains meaningful word relations, is ignored. In this paper, to aim at exploiting a knowledge graph effectively, we propose a novel graph convolutional topic model (GCTM) which integrates graph convolutional networks (GCN) into a topic model and a learning method which learns the networks and the topic model simultaneously for data streams. In each minibatch, our method not only can exploit an external knowledge graph but also can balance the external and old knowledge to perform well on new data. We conduct extensive experiments to evaluate our method with both a human knowledge graph (Wordnet) and a graph built from pre-trained word embeddings (Word2vec). The experimental results show that our method achieves significantly better performances than state-of-the-art baselines in terms of probabilistic predictive measure and topic coherence. In particular, our method can work well when dealing with short texts as well as concept drift. The implementation of GCTM is available at \url{https://github.com/bachtranxuan/GCTM.git}.

Hyperspectral unmixing (HU) has been one of the hot spots in hyperspectral remote sensing research and has great potential in many applications. In recent years, the employment of the probabilistic topic model to mine latent topics in hyperspectral images has been an effective way for spectral unmixing. However, these methods fail to fully exploit the potential of topic models in uncovering image semantics and need extra sparsity constraints, which greatly increases the complexity of the model. In addition, the spatial information which can provide the correlation of features in adjacent pixels is usually ignored in topic model-based HU. To solve these problems, a spectral-spatial unmixing framework of hyperspectral imagery based on a sparse topic relaxation-clustering model (S³TRM) is proposed. In S³TRM, the topic model combined with implied sparse prior constraints are introduced, and the sparse characteristics of S³TRM are used to capture the semantic representation of the spectrum. With the proposed relaxation-clustering strategy, multiple possible spectral representations of features can be obtained, which further alleviates the influence caused by endmember variability. Group clustering is used to locate the endmember quickly and accurately. Moreover, superpixel segmentation is considered to supplement the spatial distribution information of features, thereby improving the fractional abundance. Experiments on a synthetic dataset and three well-known real hyperspectral datasets confirm the excellent performance of the proposed framework in both qualitative assessment and quantitative evaluation, compared with the other state-of-the-art methods.

Aiming at disclosing a general research landscape of structural engineering in the twenty-first century, this study applies the latent Dirichlet allocation (LDA), a topic modeling approach, to analyze 51,346 article abstracts from 23 prestigious journals in structural engineering with a publication period from 2000 to 2020. The LDA analyzes the literature inventory by extracting 50 distinguishable wordclouds, each centered around one distinct research theme and assigned a unique topic name. Subsequently, various measures have been proposed to integrate the posterior distributions of these research topics with article information such as publication year, journal name, and correspondence address. The increase index identifies five cold and hot topics, which reflect the shift of research interests in the community. Emerging research topics such as seismic risk assessment and composite material have received much more attention in recent years. Moreover, advanced metrics have been proposed to analyze the research similarity and evolution across different journals and countries/regions. As discussed in the paper, analysis findings would enable community stakeholders (e.g., students, engineers, researchers, conference organizers, journal editors, funding agencies) to explore the state of the research and develop viable strategies to further foster the healthy growth of the community. Such strategies can be (1) researchers submitting a paper to the most appropriate journal; (2) journal editors adjusting the journal focus to enhance its impact; and (3) funding agencies prioritizing research supports that best fit regional needs and circumstances, among others.

Blood pressure (BP) is an important indicator of an individual's health status and is closely related to daily behaviors. Thus, a continuous daily measurement of BP is critical for hypertension control. To assist continuous measurement, BP prediction based on non-physiological data (ubiquitous mobile phone data) was studied in the research. An algorithm was proposed that predicts BP based on patients’ daily routine, which includes activities such as sleep, work, and commuting. The aim of the research is to provide insight into the application of mobile data in telemonitoring and the continuous unobtrusive daily measurement of BP. A half-year data set from October 2017 of 320 individuals, including telecom data and BP measurement data, was analyzed. Two hierarchical Bayesian topic models were used to extract individuals’ location-driven daily routine patterns (topics) and calculate probabilities among these topics from their day-level mobile trajectories. Based on the topic probability distribution and patients’ contextual data, their BP were predicted using different models. The prediction model comparison shows that the long short-term memory (LSTM) method exceeds others when the data has a high dependency. Otherwise, the Random Forest regression model outperforms the LSTM method. Also, the experimental results validate the effectiveness of the topics in BP prediction.

Sparse and short news headlines can be arbitrary, noisy, and ambiguous, making it difficult for classic topic model LDA (latent Dirichlet allocation) designed for accommodating long text to discover knowledge from them. Nonetheless, some of the existing research about text-based crude oil forecasting employs LDA to explore topics from news headlines, resulting in a mismatch between the short text and the topic model and further affecting the forecasting performance. Exploiting advanced and appropriate methods to construct high-quality features from news headlines becomes crucial in crude oil forecasting. This paper introduces two novel indicators of topic and sentiment for the short and sparse text data to tackle this issue. Empirical experiments show that AdaBoost.RT with our proposed text indicators, with a more comprehensive view and characterization of the short and sparse text data, outperforms the other benchmarks. Another significant merit is that our method also yields good forecasting performance when applied to other futures commodities.

In this paper, we perform sentiment analysis and topic modeling on Twitter and Facebook posts of nine public sector organizations operating in Northeast US. The study objective is to compare and contrast message sentiment, content and topics of discussion on social media. We discover that sentiment and frequency of messages on social media is indeed affected by nature of organization’s operations. We also discover that organizations either use Twitter for broadcasting or one-to-one communication with public. Finally we found discussion topics of organizations – identified through unsupervised machine learning – that engaged in similar areas of public service having similar topics and keywords in their public messages. Our analysis also indicates missed opportunities by these organizations when communication with public. Findings from this study can be used by public sector entities to understand and improve their social media engagement with citizens.

Introducción Amelia SANZ CABRERIZO

PurposeThis study aims to explore knowledge structure and research trends in the domain of digital humanities (DH) in the recent decade. The study identified prevailing topics and then, analyzed trends of such topics over time in the DH field.Design/methodology/approachResearch bibliographic data in the area of DH were collected from scholarly databases. Multiple text mining techniques were used to identify prevailing research topics and trends, such as keyword co-occurrences, bigram analysis, structural topic models and bi-term topic models.FindingsTerm-level analysis revealed that cultural heritage, geographic information, semantic web, linked data and digital media were among the most popular topics in the recent decade. Structural topic models identified that linked open data, text mining, semantic web and ontology, text digitization and social network analysis received increased attention in the DH field.Originality/valueThis study applied existent text mining techniques to understand the research domain in DH. The study collected a large set of bibliographic text, representing the area of DH from multiple academic databases and explored research trends based on structural topic models.

The content of a government’s website is an important source of information about policy priorities, procedures, and services. Existing research on government websites has relied on manual methods ...

Recently, topic modeling has been upgraded by neural variational inference, which simultaneously allows the model structures deeper and proposes efficient update rules with the reparameterization trick. We formally call this recent new art as neural topic model. In this paper, we investigate a problem of neural topic models, where they formulate topic embeddings and measure the word weights within topics by linear transformation between topic and word embeddings, resulting in redundant and inaccurate topic representations. To solve this problem, we propose a novel neural topic model, namely G enerative M odel with N onlinear N eural T opics (GMnnt). The insight of GMnnt is to replace the topic embeddings with neural networks of topics, named neural topic, so as to capture nonlinear relationships between words in the embedding space, enabling to induce more accurate topic representations. We derive the inference process of GMnnt under the framework of neural variational inference. Extensive empirical studies have been conducted on several widely used collections of documents, including datasets of both short texts and normal long texts. The experimental results validate that GMnnt can output more semantically coherent topics compared with traditional topic models and neural topic models.

PurposeThe purpose of this work is to survey the body of research revolving around big data (BD) and analytics in hospitality and tourism, by detecting macro topical areas, research streams and gaps and to develop an agenda for future research.Design/methodology/approachThis research is based on a systematic literature review of academic papers indexed in the Scopus and Web of Science databases published up to 31 December 2020. The outputs were analyzed using bibliometric techniques, network analysis and topic modeling.FindingsThe number of scientific outputs in research with hospitality and tourism settings has been expanding over the period 2015–2020, with a substantial stability of the areas examined. The vast majority are published in academic journals where the main reference area is neither hospitality nor tourism. The body of research is rather fragmented and studies on relevant aspects, such as BD analytics capabilities, are virtually missing. Most of the outputs are empirical. Moreover, many of the articles collected relatively small quantities of records and, regardless of the time period considered, only a handful of articles mix a number of different techniques.Originality/valueThis work sheds new light on the emergence of a body of research at the intersection of hospitality and tourism management and data science. It enriches and complements extant literature reviews on BD and analytics, combining these two interconnected topics.

Video accounts for a large proportion of traffic on the Internet. Understanding its geographical viewing patterns is extremely valuable for the design of Internet ecosystems for content delivery, recommendation and ads. While previous works have addressed this problem at coarse-grain scales (e.g., national), the urban-scale geographical patterns of video access have never been revealed. To this end, this article aims to investigate the problem that whether there exists distinct viewing patterns among the neighborhoods of a large-scale city. To achieve this, we need to address several challenges including unknown of patterns profiles, complicate urban neighborhoods, and comprehensive viewing features. The contributions of this article include two aspects. First, we design a framework to automatically identify geographical video viewing patterns in urban neighborhoods. Second, by using a dataset of two months real video requests in Shanghai collected from one major ISP of China, we make a rigorous analysis of video viewing patterns in Shanghai. Our study reveals the following important observations. First, there exists four prevalent and distinct patterns of video access behavior in urban neighborhoods, which are corresponding to four different geographical contexts: downtown residential, office, suburb residential and hybrid regions. Second, there exists significant features that distinguish different patterns, e.g., the probabilities of viewing TV plays at midnight, and viewing cartoons at weekends can distinguish the two viewing patterns corresponding to downtown and suburb regions.

It is necessary to reduce the cognitive overhead of interpreting the native topic term list of the Latent Dirichlet Allocation (LDA) style topic model. In this regard, automatic topic labeling has become an effective approach to generate meaningful alternative representations of topics discovered for end-users. In this study, we introduced a novel two-phase neural embedding framework with the redundancy-aware graph-based ranking process. It demonstrated how pre-trained neural embedding could be usefully applied in topic terms, sentence presentations, and automatic topic labeling tasks. Moreover, reranking the topic terms optimized the discovered topics with fewer yet more representative terms while retaining the topic information integrality and fidelity. It further decreased the burden of computation caused by neural embedding and improved the overall effectiveness of the labeling system. Compared with the prevailing state-of-the-art and classical labeling systems, our efficient model boosted the quality of the topic labels generated and discovered more meaningful topic labels.

Learning from past incidents is critical to achieving and maintaining high process safety performance. Accident and incident records provide one way for learning; however, these are usually in the form of unstructured texts, which makes analysis difficult. Recently, text mining methods based on supervised learning have been proposed for analyzing accident reports; however, they require an impractically large number of labeled records as training examples. This paper proposes an automated, semi-supervised, domain-independent approach for analyzing accident reports. Given a set of user-defined classification topics and domain literature such as handbooks, glossaries, and Wikipedia articles, the method can identify domain-specific keywords and group them into topics with minimal expert involvement. These keywords and topics can then be used for various data mining purposes, including classification. The proposed approach is demonstrated using two different case studies across domains: (1) in aviation to identify the stage of flight when an accident occurs, and (2) in the process industry domain to identify the cause of pipeline accidents. The average classification accuracy of the proposed method was 80% which is comparable to that of supervised learning methods. The key benefits of this approach are that it can generate domain-specific predictive models with limited manual intervention.

The increasing importance of online distribution channels is paralleled by a rising interest in gaining insights into the customer journey and browsing behavior. We evaluate several machine learning methods (latent Dirichlet allocation, correlated topic model, structural topic model, replicated softmax model) with respect to their ability to reproduce the browsing behavior of households across websites. In addition, we compare these machine learning methods to a related classical technique, singular value decomposition. In our study, the replicated softmax model outperforms latent Dirichlet allocation, but the correlated topic model attains the overall best performance. Compared to singular value decomposition both the correlated topic model and the replicated softmax model lead to a more efficient compression of web browsing data. On the other hand, singular value decomposition surpasses latent Dirichlet allocation. We interpret results of the correlated topic model and the replicated softmax model by determining combinations of topics or hidden variables that are heterogeneous with respect to visited websites. We show that decision makers should not rely on bivariate measures of site visits, as these do not agree with measures of interdependences between sites that can be inferred from the correlated topic model or the replicated softmax model. We investigate how well topics or hidden variables measured by these methods predict yearly household expenditures. The correlated topic model leads to the best predictive performance, followed by the replicated softmax model. We also discuss how the replicated softmax model can be used to support online marketing decisions of websites.

Online social media provides rich and varied information reflecting the significant concerns of the public during the coronavirus pandemic. Analyzing what the public is concerned with from social media information can support policy-makers to maintain the stability of the social economy and life of the society. In this article, we focus on the detection of the network public opinions during the coronavirus pandemic. We propose a novel Relational Topic Model for Short texts (RTMS) to draw opinion topics from social media data. RTMS exploits the feature of texts in online social media and the opinion propagation patterns among individuals. Moreover, a dynamic version of RTMS (DRTMS) is proposed to capture the evolution of public opinions. Our experiment is conducted on a real-world dataset which includes 67,592 comments from 14,992 users. The results demonstrate that, compared with the benchmark methods, the proposed RTMS and DRTMS models can detect meaningful public opinions by leveraging the feature of social media data. It can also effectively capture the evolution of public concerns during different phases of the coronavirus pandemic.

Objectives A thread is the most common information aggregation unit in a health forum, so effective thread recommendation is critical for improving the user experience in an online health community (OHC). This paper proposes an OHC thread recommendation method based on topic model and network embedding, which recommends threads to users by training a classifier and predicting user reply behavior. Methods The proposed model uses the network structure to describe valid information in OHCs and treats a recommendation as the task of predicting links between users and threads in the network. Topic nodes are added to the information network to better represent the features of users and threads. The results of the latent Dirichlet allocation (LDA) model describe thread topics and user interests from the perspectives of consumer health vocabulary in OHCs and social support types. The large-scale information network embedding technology LINE is used to mine the node's contextual information from the network structure to obtain the low-dimensional vectors of nodes. We optimize the representation method and similarity calculation of network nodes and enrich the network structure information contained in the recommended features to improve the recommendation effect. Results To verify the proposed model, we collected data from the diabetes forum “Sweet Home.” The experimental results show that the proposed model can effectively extract user interests in threads from the information network and optimize thread recommendation in OHCs.

PurposeThis paper provides a structured literature review of blockchain in accounting. The authors identify current trends, analyse and critique the key topics of research and discuss the future of this nascent field of inquiry.Design/methodology/approachThis study’s analysis combined a structured literature review with citation analysis, topic modelling using a machine learning approach and a manual review of selected articles. The corpus comprised 153 academic papers from two ranked journal lists, the Association of Business Schools (ABS) and the Australian Business Deans Council (ABDC), and from the Social Science Research Network (SSRN). From this, the authors analysed and critiqued the current and future research trends in the four most predominant topics of research in blockchain for accounting.FindingsBlockchain is not yet a mainstream accounting topic, and most of the current literature is normative. The four most commonly discussed areas of blockchain include the changing role of accountants; new challenges for auditors; opportunities and challenges of blockchain technology application; and the regulation of cryptoassets. While blockchain will likely be disruptive to accounting and auditing, there will still be a need for these roles. With the sheer volume of information that blockchain records, both professions may shift out of the back-office toward higher-profile advisory roles where accountants try to align competitive intelligence with business strategy, and auditors are called on ex ante to verify transactions and even whole ecosystems.Research limitations/implicationsThe authors identify several challenges that will need to be examined in future research. Challenges include skilling up for a new paradigm, the logistical issues associated with managing and monitoring multiple parties all contributing to various public and private blockchains, and the pressing need for legal frameworks to regulate cryptoassets.Practical implicationsThe possibilities that blockchain brings to information disclosure, fraud detection and overcoming the threat of shadow dealings in developing countries all contribute to the importance of further investigation into blockchain in accounting.Originality/valueThe authors’ structured literature review uniquely identifies critical research topics for developing future research directions related to blockchain in accounting.

Despite the rising popularity of big data, there is speculation that evaluators have been slow adopters of these new statistical approaches. Several possible reasons have been offered for why this is the case: ethical concerns, institutional capacity, and evaluator capacity and values. In this method note, we address one of these barriers and aim to build evaluator capacity to integrate big data analytics into their studies. We focus our efforts on a specific topic modeling technique referred to as latent Dirichlet allocation (LDA) because of the ubiquitousness of qualitative textual data in evaluation. Given current equity debates, both within evaluation and the communities in which we practice, we analyze 1,796 tweets that use the hashtag #equity with the R packages topicmodels and ldatuning to illustrate the use of LDA. Furthermore, a freely available workbook for implementing LDA topic modeling is provided as Supplemental Material Online.

Topic models have been widely used for learning the latent explainable representation of documents, but most of the existing approaches discover topics in a flat structure. In this study, we propose an effective hierarchical neural topic model with strong interpretability. Unlike the previous neural topic models, we explicitly model the dependency between layers of a network, and then combine latent variables of different layers to reconstruct documents. Utilizing this network structure, our model can extract a tree-shaped topic hierarchy with low redundancy and good explainability by exploiting dependency matrices. Furthermore, we introduce manifold regularization into the proposed method to improve the robustness of topic modeling. Experiments on real-world datasets validate that our model outperforms other topic models in several widely used metrics with much fewer computation costs.

In order to reach a compromise between adhering to the traditional culture and embracing the modern lifestyle, more and more Asian moms are heading towards postpartum care centres for postpartum recovery. However, research regarding the quality of care of these postpartum care centres is nearly missing from the literature. This paper investigated the status quo of the postpartum care centres in Shanghai, China from mothers’ perspectives by means of analysing the 34280 pairs of ratings and reviews posted by postpartum care centre customers on the internet with machine learning and text mining. Results show that the mothers are generally satisfied with the studied care centres. Meanwhile, the 13 major topics in the customer online reviews were identified, which provide an overview of the interaction between a mother and a care centre. In addition, weight of topic analysis suggests that the studied care centres can further improve in the areas of support team, environment, and facility.

PurposeDo consumers rate reviews describing other consumers' sensory experience of a product (touch, smell, sight, hear and taste) as helpful or do they rate reviews describing more practical properties (product performance and characteristics/features) as more helpful? What is the effect of review helpfulness on purchase intention? Furthermore, why do consumers perceive sensory and non-sensory reviews differently? This study answers these questions.Design/methodology/approachThe authors analyze 447,792 Amazon reviews and perform a topic modeling analysis to extract the main topics that consumers express in their reviews. Then, the topics were used as regressors to predict the number of consumers who found the review helpful. Finally, a lab experiment was conducted to replicate the results in a more controlled environment to test the serial mediation effect.FindingsContrary to the overwhelming evidence supporting the positive effects of sensory elicitation in marketing, this study shows that sensory reviews are less likely to be helpful than non-sensory reviews. Moreover, a key reason why sensory reviews are less effective is that they decrease the objective perception of the review, a less objective review then decreases the level of helpfulness, which decreases purchase intention.Originality/valueThis study contributes to the interactive marketing field by investigating customer behavior and interactivity in online shopping sites and to the sensory marketing literature by identifying a boundary condition, the authors’ data suggest that sensory elicitations might not be processed positively by consumers when they are not directly experienced, but instead communicated by another consumer. Moreover, this study indicates how companies can encourage consumers to share more effective and helpful reviews.

BACKGROUND/OBJECTIVES Coronavirus disease 2019 (COVID-19) cases were first reported in December 2019, in China, and an increasing number of cases have since been detected all over the world. The purpose of this study was to collect significant news media reports on food services during the COVID-19 crisis and identify public communication and significant concerns regarding COVID-19 for suggesting future directions for the food industry and services. SUBJECTS/METHODS News articles pertaining to food services were extracted from the home pages of major news media websites such as BBC, CNN, and Fox News between March 2020 and February 2021. The retrieved data was sorted and analyzed using Python software. RESULTS The results of text analytics were presented in the format of the topic label and category for individual topics. The food and health category presented the effects of the COVID-19 pandemic on food and health, such as an increase in delivery services. The policy category was indicative of a change in government policy. The lifestyle change category addressed topics such as an increase in social media usage. CONCLUSIONS This study is the first to analyze major news media (i.e., BBC, CNN, and Fox News) data related to food services in the context of the COVID-19 pandemic. Text analytics research on the food services domain revealed different categories such as food and health, policy, and lifestyle change. Therefore, this study contributes to the body of knowledge on food services research, through the use of text analytics to elicit findings from media sources.

Party competition in Western Europe is increasingly focused on “issue competition”, which is the selective emphasis on issues by parties. The aim of this paper is to contribute methodologically to the increasing number of studies that deal with different aspects of parties’ issue competition and communication. We systematically compare the value and shortcomings of three exploratory text representation approaches to study the issue communication of parties on Twitter. More specifically, we analyze which issues separate the online communication of one party from that of the other parties and how consistent party communication is. Our analysis was performed on two years of Twitter data from six Belgian political parties, comprising of over 56,000 political tweets. The results indicate that our exploratory approach is useful to study how political parties profile themselves on Twitter and which strategies are at play. Second, our method allows to analyze communication of individual politicians which contributes to classical literature on party unity and party discipline. A comparison of our three methods shows a clear trade-off between interpretability and discriminative power, where a combination of all three simultaneously provides the best insights.