Search

Sentiment analysis of financial texts provides valuable insights into market dynamics, but relies on domain-specific dictionaries. Inquiry letters as particular financial texts lack tailored sentiment dictionaries, limiting research in the important domain. This study develops an Inquiry Letter Sentiment Dictionary (ILSD) using innovative integration of semantic orientation pointwise mutual information (SO-PMI), word2vec, and manual screening. The ILSD leverages co-occurrence and contextual information to expand coverage and sentiment word capture capabilities beyond existing general and financial dictionaries. We collected 1754 inquiry letters from the Shanghai Stock Exchange (SSE). The experiment results indicate that the ILSD performs better than other sentiment dictionaries according to coverage, accuracy (ACC), F1 weighted score (F1Weighted), Matthews correlation (MCC), and geometric mean (G-mean), which proves the effectiveness of the ILSD in practice.

Copyright of Przegląd Socjologii Jakościowej is the property of Redakcja Przegladu Socjologii Jakosciowej and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

There are many natural language processing methods that can be used to analyze audio, image, and video captions and improve the accuracy of multimedia understanding tools. Linguistic phenomena are considered as one of the most effective factors in changing the initial score of sentiment words. Lacking accurate attention to the impact of intensifiers and their position in a sentiment component and neglecting the mutual effect between the polarity of sentiment words and intensifiers reduce the efficiency of sentiment dictionaries. To solve these problems, in the proposed method, a new high coverage semi-supervised sentiment dictionary was made from a combination of sentimental words and several intensifiers. The dictionary has several advantages, including assigning four fuzzy coefficients to intensifiers based on their position in sentiment compounds and the polarity of sentiment words. Sentimental word scores were extracted from the manual VADER dictionary, and the intensifiers coefficients were extracted automatically using a hybrid fuzzy-statistical method based on the intensifier location and the sentiment word polarity. The simulation results show the proposed dictionary has at least 9% improvement compared to the latest sentiment dictionaries at standard databases. [ABSTRACT FROM AUTHOR]

This study explores the relationship between Environmental, Social, and Governance (ESG) practices and the market value of companies, with a focus on Brazil's largest corporations. Recognizing the limitations of existing research tools for analyzing the impact of ESG factors, we introduce an innovative, open-source Dictionary of ESG Terms. This tool is designed to classify news content into the detailed categories established by the Sustainability Accounting Standards Board (SASB), thereby facilitating a nuanced analysis of ESG-related news and its subsequent effects on stock prices. Our analysis reveals that stock prices exhibit significant positive reactions to favorable ESG news and negative reactions to adverse ESG developments. Crucially, our findings underscore the discernment of investors, who appear to prioritize financially material ESG information over news bearing solely reputational or non-pecuniary significance. This distinction highlights the critical role of financial materiality in shaping market responses to ESG news. By providing empirical evidence from the Brazilian market, this study contributes to the broader discourse on ESG factors in corporate valuation. It offers practical tools and insights for investors, companies, and regulators aiming to better understand the complexities of ESG investment strategies. Through the application of our comprehensive ESG Dictionary, we shed light on the diverse dimensions of ESG impact, suggesting an approach to evaluate how ESG practices influence corporate market value in emerging economies. [ABSTRACT FROM AUTHOR]

This work considers implementation of a diachronic predictor of valence, arousal and dominance ratings of English words. The estimation of affective ratings is based on data on word co-occurrence statistics in the large diachronic Google Books Ngram corpus. Affective ratings from the NRC VAD dictionary are used as target values for training. When tested on synchronic data, the obtained Pearson‘s correlation coefficients between human affective ratings and their machine ratings are 0.843, 0.779 and 0.792 for valence, aroused and dominance, respectively. We also provide a detailed analysis of the accuracy of the predictor on diachronic data. The main result of the work is creation of a diachronic affective dictionary of English words. Several examples are considered that illustrate jumps in the time series of affective ratings when a word gains a new meaning. This indicates that changes in affective ratings can serve as markers of lexical-semantic changes. [ABSTRACT FROM AUTHOR]

Amidst the ongoing wave of economic globalization, the societal demand for English proficiency is escalating, particularly for individuals adept in practical applications of the language. Recognizing the pivotal role of English reading as a cornerstone in language acquisition, there arises a need for personalized approaches tailored to individual interests, thereby necessitating an in-depth analysis of text emotions. Addressing the challenges in text classification within English reading courses, this study presents a novel method for text emotion analysis. Integrating sentiment dictionaries with BI-GRU networks, the proposed approach significantly enhances the efficiency of text emotion recognition while simultaneously fostering students’ engagement. By segmenting the emotion dictionary based on polarity and extracting pertinent features, the study amalgamates these with BI-GRU features at the feature level. This fusion facilitates emotion classification within reading texts through sophisticated activation functions. Notably, the precision of recognizing positive, negative, and neutral emotions reaches an impressive 92.5%, marking a notable improvement over methods devoid of dictionary feature integration. This framework offers novel insights for future English reading material development and intelligent learning strategies to bolster student enthusiasm and chart a promising trajectory for cultivating practical English talents.

Stock investments play a crucial role in deciding the global economic growth of the country. Investors can optimize profit and avoid risk through accurate stock value prediction models, which motivates researchers to work on various aspects of correlated features and predictive models for stock value prediction. The existing stock value prediction models used data like Twitter, microblogs, price history, and Google trends. On the other hand, Domain-specific dictionary-based deep learning evolved as a competitive model for alternative models in stock value prediction. But accuracy of these models depends on the quality of the input, the correlation among the features, and the correctness of the sentiment scores generated for the dictionary terms. Financial news sentiment analysis for stock value prediction with dictionary-based learning needs attention in improving the quality of the input and dictionary term's sentiment score generation. The present research aims to develop a Blended soft computing model for stock value prediction (BSCM) with cooperative fusion and dictionary-based deep learning. In the current work, six Indian stocks that cover uptrend, sideways, and downtrends characteristics are considered with stock price histories and news headlines from 8th August 2016 to 31st March 2023, i.e., 2427 days. The number of records in the price history dataset is 14,562, and the news headlines dataset is 46,213. The performance of the stock value prediction can be improved by taking advantage of multi-source information and context-aware learning. The present research aims to achieve three objectives: 1. Apply cooperative fusion to combine the news headlines and price history of stocks collected from multiple sources to improve the quality of the input with correlated features. 2. Build a dictionary, FNSentiment, with a novel strategy. 3. Predict stock values using FNSentiment and News Sentiment Prediction Model (NSPM) integration. In the experimentation, the proposed model outperformed the state-of-the-art models with an accuracy of 91.11, RMSE of 10.35, MAPE of 0.02, and MAE of 2.74. [JJCIT 2023; 9(3.000): 249-260]

Stock investments play a crucial role in deciding the global economic growth of the country. Investors can optimize profit and avoid risk through accurate stock-value prediction models, which motivates researchers to work on various aspects of correlated features and predictive models for stock-value prediction. The existing stock-value prediction models used data like Twitter, microblogs, price history and Google trends. On the other hand, domainspecific dictionary-based deep learning evolved as a competitive model for alternative models in stock value prediction. But, the accuracy of these models depends on the quality of the input, the correlation among the features and the correctness of the sentiment scores generated for the dictionary terms. Financial-news sentiment analysis for stock-value prediction with dictionary-based learning needs attention in improving the quality of the input and dictionary terms' sentiment score generation. The present research aims to develop a blended softcomputing model for stock-value prediction (BSCM) with cooperative fusion and dictionary-based deep learning. In the current work, six Indian stocks that cover uptrend, sideways and downtrend characteristics are considered with stock-price histories and news headlines from 8th August 2016 to 31st March 2023, i.e., 2427 days. The number of records in price-history dataset is 14,562 and in the news headlines dataset is 46,213. The performance of the stock-value prediction can be improved by taking advantage of multi-source information and context-aware learning. The present research aims to achieve three objectives: 1. Applying cooperative fusion to combine the news headlines and price history of stocks collected from multiple sources to improve the quality of the input with correlated features. 2. Building a dictionary, FNSentiment, with a novel strategy. 3. Predicting stock values using FNSentiment and News Sentiment Prediction Model (NSPM) integration. In the experimentation, the proposed model outperformed the state-of-the-art models with an accuracy of 91.11%, RMSE of 10.35, MAPE of 0.02 and MAE of 2.74. [ABSTRACT FROM AUTHOR]

Accurate prediction of stock prices can reduce investment risks and increase returns. This paper combines the multi-source data affecting stock prices and applies sentiment analysis, swarm intelligence algorithm, and deep learning to build the MS-SSA-LSTM model. Firstly, we crawl the East Money forum posts information to establish the unique sentiment dictionary and calculate the sentiment index. Then, the Sparrow Search Algorithm (SSA) optimizes the Long and Short-Term Memory network (LSTM) hyperparameters. Finally, the sentiment index and fundamental trading data are integrated, and LSTM is used to forecast stock prices in the future. Experiments demonstrate that the MS-SSA-LSTM model outperforms the others and has high universal applicability. Compared with standard LSTM, the $R^{2}$ of MS-SSA-LSTM is improved by 10.74% on average. We found that: 1) Adding the sentiment index can enhance the model’s predictive performance. 2) The LSTM’s hyperparameters are optimized using SSA, which objectively explains the model parameter settings and improves the prediction effect. 3) The high volatility of China’s financial market is more suitable for short-term prediction.

Abstract Social media services and analytics platforms are rapidly growing. A large number of various events happen mostly every day, and the role of social media monitoring tools is also increasing. Social networks are widely used for managing and promoting brands and different services. Thus, most popular social analytics platforms aim for business purposes while monitoring various social, economic, and political problems remains underrepresented and not covered by thorough research. Moreover, most of them focus on resource-rich languages such as the English language, whereas texts and comments in other low-resource languages, such as the Russian and Kazakh languages in social media, are not represented well enough. So, this work is devoted to developing and applying the information system called the OMSystem for analyzing users’ opinions on news portals, blogs, and social networks in Kazakhstan. The system uses sentiment dictionaries of the Russian and Kazakh languages and machine learning algorithms to determine the sentiment of social media texts. The whole structure and functionalities of the system are also presented. The experimental part is devoted to building machine learning models for sentiment analysis on the Russian and Kazakh datasets. Then the performance of the models is evaluated with accuracy, precision, recall, and F1-score metrics. The models with the highest scores are selected for implementation in the OMSystem. Then the OMSystem’s social analytics module is used to thoroughly analyze the healthcare, political and social aspects of the most relevant topics connected with the vaccination against the coronavirus disease. The analysis allowed us to discover the public social mood in the cities of Almaty and Nur-Sultan and other large regional cities of Kazakhstan. The system’s study included two extensive periods: 10-01-2021 to 30-05-2021 and 01-07-2021 to 12-08-2021. In the obtained results, people’s moods and attitudes to the Government’s policies and actions were studied by such social network indicators as the level of topic discussion activity in society, the level of interest in the topic in society, and the mood level of society. These indicators calculated by the OMSystem allowed careful identification of alarming factors of the public (negative attitude to the government regulations, vaccination policies, trust in vaccination, etc.) and assessment of the social mood.

Sentiment classification can provide the decision support of social applications such as trend judgment, public opinion monitoring, etc. However, the accuracy of sentiment classification for Chinese Weibo is still not satisfactory due to the complexity of Chinese. In addition, affected by the different organisational structure levels, the sentiment tendency of fewer Weibo Comments may be judged to be the opposite. To solve the problem above, this paper presents a Chinese sentiment classification model based on extended sentiment dictionary and organisational structure of comments. First, the sentiment dictionary can be extended by using seven dictionaries, which include the base sentiment dictionary and six additional dictionaries. Then, the sets of rules are constructed, which include inter-sentence rules and organisational structure rules. Finally, comments on three hot topics are crawled and used to make the data sets for sentiment calculation. Accordingly, based on the result of sentiment calculation, sentiment classification is completed. The effectiveness of the proposed model is verified through comparison experiments, and the experimental results are also discussed. [ABSTRACT FROM AUTHOR]

In recent years, the aspect-based sentiment analysis model uses graph convolution neural（GCN） network to learn the grammatical structure information of sentences, but ignores the known sentiment word information and the known topic environment to which the comments belong. These gradually can not meet the needs of sentiment analysis of Chinese social networks. To solve the above problems, this paper proposes a double-channel of char and word model（2 D-SGCN） based on soft fusion of dictionary and deep learning. Firstly, it constructed a microblog domain sentiment dictionary based on the expansion of the basic sentiment dictionary, then obtained sentiment words. Secondly, used the pre-training model to obtain the initial feature vector of the chars and word, and integrated the aspect word and topic information in the char dimension. Then used the Bi-LSTM and GCN with emotional information(SGCN) models to learn global and local information respectively. And obtained the final features of aspect words through the attention mechanism. Then obtained better expression of text through multi-dimensional fusion. Finally, combined the topic and aspect information for correction and classification. On the Restaurant dataset of SemEval-2014, F1 is 73.67%. On the NLPCC2012 dataset, F1 is 91.5%. The effectiveness of the model is proved. [ABSTRACT FROM AUTHOR]

The most commonly used methods in text sentiment analysis are rule-based sentiment dictionary and machine learning, with the later referring to the use of vectors to represent text followed by the use of machine learning to classify the vectors. Both methods have their limitations, including inflexibility of rules, non-prominence of sentiment words. In this paper, we design a weight distributing method combining the two methods for text sentiment analysis, by which the sentence vectors obtained can both highlight words with sentiment meanings while retaining their text information. Empirical results show that based on this new method, the accuracy rate of text sentiment analysis can reach as high as 82.1%, which means 13.9% higher than rule-based sentiment dictionary method, and 7.7% higher than TF-IDF weighting method.

With the speedy development of e-commerce, a growing number of customers tend to share their subjective perceptions of the product or service on the Internet. This phenomenon makes the commercial value of online reviews increasingly prominent. In this context, how to gain insights into consumers’ perceptions and attitudes from massive comments has become a hot-button topic. Addressing this requirement, this paper developed a fusion sentiment analysis method combining textual analysis techniques with machine learning algorithms, aiming to mine online product experience. The method mainly consists of three steps. Firstly, inspired by the sensitivity of sentiment dictionary to emotional information, we utilize the dictionary to extract sentiment features. Afterward, the SVM algorithm is adopted to identify sentiment polarities of reviews. Based on this, sentiment topics are extracted from reviews through the LDA model. Furthermore, to avoid the omission of emotional information, the dictionary is extended based on semantic similarity. Meanwhile, in this research, the fact that words in reviews have unequal sentiment contribution, which has been neglected in existing studies, is taken into account. Specifically, we introduce the weighting method to measure the sentiment contribution. Finally, the investigation of consumers’ reading experiences of online books on Amazon has verified the feasibility and validity of the method. The results demonstrate that the method accurately determines reviews’ emotional tendencies and captures elements affecting reading experiences from reviews. Overall, the research provides an effective way to mine online product experience and track customers’ demands, thereby strongly supporting future product improvement and marketing strategy optimization.

The study proposes the text tone detection system based on sentiment dictionaries and fuzzy rules. Computer analysis of texts from different sources has been performed in emotional categories: anger, anticipation, disgust, fear, joy, sadness, surprise and trust. A synonym dictionary has been used to expand the vocabulary. To increase the accuracy and validity of sentiment analysis, the authors of the study have used coefficients that take into account different emotional loads of words of various parts of speech and the action of intensifying or softening adverbs. A quantitative value of the text tone has been obtained as a result of an aggregation of normalized data on all emotional categories by the fuzzy inference methods. It has been found that emotional words have a greater impact on the text tone value in the case of analysis of short messages. The proposed approach makes it possible to contribute to all emotional categories in the final text evaluation.

Social media services and analytics platforms are rapidly growing. A large number of various events happen mostly every day, and the role of social media monitoring tools is also increasing. Social networks are widely used for managing and promoting brands and different services. Thus, most popular social analytics platforms aim for business purposes while monitoring various social, economic, and political problems remains underrepresented and not covered by thorough research. Moreover, most of them focus on resource-rich languages such as the English language, whereas texts and comments in other low-resource languages, such as the Russian and Kazakh languages in social media, are not represented well enough. So, this work is devoted to developing and applying the information system called the OMSystem for analyzing users' opinions on news portals, blogs, and social networks in Kazakhstan. The system uses sentiment dictionaries of the Russian and Kazakh languages and machine learning algorithms to determine the sentiment of social media texts. The whole structure and functionalities of the system are also presented. The experimental part is devoted to building machine learning models for sentiment analysis on the Russian and Kazakh datasets. Then the performance of the models is evaluated with accuracy, precision, recall, and F1-score metrics. The models with the highest scores are selected for implementation in the OMSystem. Then the OMSystem's social analytics module is used to thoroughly analyze the healthcare, political and social aspects of the most relevant topics connected with the vaccination against the coronavirus disease. The analysis allowed us to discover the public social mood in the cities of Almaty and Nur-Sultan and other large regional cities of Kazakhstan. The system's study included two extensive periods: 10-01-2021 to 30-05-2021 and 01-07-2021 to 12-08-2021. In the obtained results, people's moods and attitudes to the Government's policies and actions were studied by such social network indicators as the level of topic discussion activity in society, the level of interest in the topic in society, and the mood level of society. These indicators calculated by the OMSystem allowed careful identification of alarming factors of the public (negative attitude to the government regulations, vaccination policies, trust in vaccination, etc.) and assessment of the social mood. [ABSTRACT FROM AUTHOR]

Objective: This study aimed to explore Chinese people's attitudes to the official application of TCM in coronavirus disease 2019 (COVID-19) treatment. Methods: We collected data referring to TCM on Weibo from 0:00 on January 24, 2020, to 23:59:59 on March 31, 2020 (Beijing time). In addition, this study used DLUT-Emotion ontology to analyze the sentiment orientation and emotions of selected data and then conducted a text analysis. Results: According to DLUT-Emotion ontology, we examined 3 sentiment orientations of 215,565 valid Weibo posts. Among them, 25,025 posts were judged as positive emotions, accounting for approximately 12%; 22,362 were regarded as negative emotions, accounting for approximately 10%; and 168,178 were judged as neutral emotions, accounting for approximately 78%. Results indicate that the words judged as "Good" have the highest frequency, and words marked as "Happy" have increased over time. The word frequency of "Fear" and "Sadness" showed a significant downward trend. Conclusion: Weibo users have a relatively positive attitude to the TCM in the COVID-19 treatment in general. Results of text analysis show that data with negative emotions is essentially an expression of public opinions to supporting TCM or not. Texts of "Fear" and "Sadness" do not reflect users' negative attitudes to TCM. [ABSTRACT FROM AUTHOR]

The paper describes application of the semantic rule-based sentiment analysis approach, which was earlier developed and tested on English texts, to the Russian language. In order to take into account specificity of Russian it was adapted, particularly representation of the rules as patterns over a list of words was replaced with algorithms over the syntax tree of a sentence. The experiments on a quarter of a corpus of sentences extracted from hotel reviews allowed to perform the error analysis and refinement of the approach. The final results on the whole corpus allowed to achieve the results close to the state-of-the-art methods based on neural networks. The advantages of the approach, including simple interpretability of its results and absence of the need of learning, make it perspective for further research in sentiment analysis.

The Shanghai epidemic (COVID-19) is another large-scale epidemic in China's central cities in the post-epidemic era from the end of March 2022. It is of great significance to study the public's attitude towards the Shanghai epidemic to support healthy psychology and a positive attitude. This study used crawler technology to obtain the Weibo data related to the epidemic situation in Shanghai that was published by users. The crawled microblogs were preprocessed, and the BosonNLP sentiment dictionary for attitude classification was selected. The Chinese vocabulary ontology for 21 emotion classifications was also used. The results showed that the general attitude of the public in Shanghai was positive. This fluctuated greatly in the initial stage and gradually increased in the later stage. Through text mining, it is clear that goods and materials, nucleic acid virus testing, and other aspects of the epidemic in Shanghai are concerning for the public. The public attitude in areas that are close to the epidemic center is relatively more negative. The study can provide references for policymakers to fight COVID-19 by improving public attitude and solving urgent matters. [ABSTRACT FROM AUTHOR]

Traditional machine learning and deep learning models ignore the strength of emotional feature words when processing sentiment classification tasks. As a result, the emotional semantic relationship is poor, and the accuracy of sentiment classification is low. To this end, an improved BiLSTM-CNN+Attention sentiment classification algorithm with a sentiment dictionary was proposed. Firstly, a feature extraction algorithm fused with sentiment dictionaries was used to optimize the weight of feature words. Secondly, a convolutional neural network (CNN) model was designed to extract local features, and a bidirectional long and short-term memory(BiLSTM) model was used to extract contextual semantic features and long-distance dependencies. Then, the attention mechanism was designed to add weights to sentiment features. Finally, a Softmax classifier was used to predict the sentiment category. The experimental results show that the proposed sentiment classification algorithm can achieve the best precision, recall, and F value. Compared with TextCNN, BiLSTM, long and short-term memory (LSTM), CNN, and random forest models, the F value of the proposed method is increased by 2.35%, 3.63%, 4.36%, 2.72%, and 6.35%, respectively. In short, the proposed method can fully integrate the weights of emotional feature words, utilize contextual semantic features, and improve the performance of sentiment classification. Therefore, the proposed method has specific educational value and application prospects. [ABSTRACT FROM AUTHOR]

Abstract Background Anorexia nervosa is a clinical disorder syndrome of the wide spectrum without a fully recognized etiology. The necessary issue in the clinical diagnostic process is to detect the causes of this disease (e.g., my body image, food, family, peers), which the therapist gradually comes to by verifying assumptions using proper methods and tools for diagnostic process. When a person is diagnosed with anorexia, a clinician (a doctor, a therapist or a psychologist) proposes a therapeutic diagnosis and considers the kind of treatment that should be applied. This process is also continued during therapeutic diagnosis. In both cases, it is recommended to apply computer-aided tools designed for testing and confirming the assumptions made by a psychologist. The paper aims to present the computer-aided therapeutic diagnosis method for anorexia. The proposed method consists of 4 stages: free statements of a patient about his/her body image, the general sentiment analysis of statement based on Recurrent Neural Network, assessment of the intensity of five basic emotions: happiness, anger, sadness, fear and disgust (using the Nencki Affective Word List and conversion of words to their basic form), and the assessment of particular areas of difficulties—the sentiment analysis based on the dictionary approach was applied. Results The sentiment analysis of a document achieved 72% and 51% of effectiveness, respectively, for RNN and dictionary-based methods. The intensity of sadness (emotion) occurring within the dictionary method is differentiated between control and research group at the level of 10%. Conclusion The quick access to the sentiment analysis of a statement on the image of patient’s body, emotions experienced by the patient and particular areas of difficulties of people prone to the anorexia nervosa disorders, may help to establish the diagnosis in a very short time and start an immediate therapy. The proposed automatic method helps to avoid patient’s aversions towards the therapy, which may include avoiding patient–therapist communication, talking about less essential topics, coming late for the sessions. These circumstances can guarantee promising prognosis for recovering.

Considering the scarcity of Uyghur sentiment resources, in this paper proposed a new combined unsupervised sentiment classification method for Uyghur text without any labeled corpora. In the first part, a Uyghur sentiment dictionary, UYSentiDict, was adopted to classify the sentences. For the sentiment vocabulary matching, both the matching of the original word and the stem were considered, and the influence of sentence patterns, negation words, and degree adverbs were further considered as well. Based on different thresholds, the sentences with higher sentiment values were selected from the lexicon-based classification results as a pseudo-labeled dataset. In the second part, different sentiment characteristics were learned from the pseudo-labeled dataset by the machine learning classifier, and the remaining categorical data were further classified. It can be concluded that the method proposed in this paper has good classification efficiency in Uyghur sentiment corpora in four different fields, and some results were performed better than the classification results of machine learning classifier. Moreover, this method is not restricted by the field of data and does not need to be marked in advance with good training corpus, and can solve the resource shortage problem in the field of Uyghur sentiment classification effectively. [ABSTRACT FROM AUTHOR]

Danmaku video provides a platform for users to communicate online while watching videos. Danmaku is a live commenting function where the comments related to the video being screened are created by users and prominently shown in real-time on the video screen. These live comments contain complex and rich sentiments, reflecting users' instant opinions and feelings on video programs. In some sense, danmaku provides emotional timing information about video data, and it also offers an innovative mean to analyze video data. However, existing sentiment classification methods are not suitable for danmaku data analysis. To solve this problem, this paper constructs a danmaku sentiment dictionary and presents a new method using sentiment dictionary and Naïve Bayes for the sentiment analysis of danmaku reviews. The method is greatly helpful in supervising the overall emotional orientation of a danmaku video and predicting its popularity. Through the processes of extracting emotional information from a danmaku video, classifying sentiment and visualizing data, the time distribution of the seven sentiment dimensions can be obtained. In addition, a weight calculation can be conducted for classifying the sentiment polarity of danmaku reviews. Experimental results show that the proposed method has a significant effect on sentiment score and polarity detection.

To solve the problem of Chinese microblog sentiment classification, a sentiment classification method combining PMI and Hownet based on microblog data is proposed. Through the research on the short and novel features of microblog data, a method of dictionary merging is proposed. The existing dictionaries are merged according lo Hownet word similarity, and PMI is used to perform sentiment classification of online words. The network sentiment words are added to construct sentiment dictionary that adapts to the features of microblog text, and sentiment classification models are trained based on the new dictionary combined with supervised learning methods. The experimental results show that using this method for sentiment analysis can effectively identify the impact of new internet words on sentiment analysis, with an accuracy rale of 78. 3 % . In the sentiment analysis of microblog containing new words on the lnternet, the accuracy rale is higher than that of only using dictionaries or supervised learning. [ABSTRACT FROM AUTHOR]

Words are one of the most essential elements of expressing sentiments in context although they are not the only ones. Also, syntactic relationships between words, morphology, punctuation, and linguistic phenomena are influential. Merely considering the concept of words as isolated phenomena causes a lot of mistakes in sentiment analysis systems. So far, a large amount of research has been conducted on generating sentiment dictionaries containing only sentiment words. A number of these dictionaries have addressed the role of combinations of sentiment words, negators, and intensifiers, while almost none of them considered the heterogeneous effect of the occurrence of multiple linguistic phenomena in sentiment compounds. Regarding the weaknesses of the existing sentiment dictionaries, in addressing the heterogeneous effect of the occurrence of multiple intensifiers, this research presents a sentiment dictionary based on the analysis of sentiment compounds including sentiment words, negators, and intensifiers by considering the multiple intensifiers relative to the sentiment word and assigning a location-based coefficient to the intensifier, which increases the covered sentiment phrase in the dictionary, and enhanced efficiency of proposed dictionary-based sentiment analysis methods up to 7% compared to the latest methods. [ABSTRACT FROM AUTHOR]

This paper describes a novel approach to measure individual investor sentiment using text-based analysis of millions of posts extracted from Chinese financial online forums. We describe how we built a database of more than 200 million stock posts from online financial forums, created GubaLex, a sentiment dictionary consisting of 48,878 words to allow sentiment analysis, and how we developed GubaSenti, an individual investor sentiment index for the stock market in China. This allowed (1) the first systemic measurement of individual investor sentiment in China; (2) an approach to text-based analysis that reflects investor sentiment about millions of posts about stocks listed in Guba; (3) a way to flexibly measure investor sentiment of a single stock, a sector or an industry and the whole market; and (4) made this possible for daily, weekly, monthly, quarterly, and yearly time periods. We also examine the relationship of the sentiment proxy and stock returns and compare it with two typical BW metrics in China. Empirical results show that GubaSenti correlates better with market performance than BW metrics in China and can be used to predict market changes in the short term. [ABSTRACT FROM AUTHOR]

The convenience of social media in communication and information dissemination has made it an ideal place for spreading rumor events, which raises a higher requirement for automatic debunking of rumor events. Meanwhile, the traditional rumor classification approaches relying on manual labeled features have to face a daunting number of manual efforts. In general, when facing a dubious claim, people can authenticate and verify the realness of an event with the contents of continuous posts, such as source credibility, public sentiments, propagation structures, and so on. In this paper, we pay more attention to the emotional expressions of posts host, especially the fine-grained sentiments, which are effective for rumor events detection. Thus, this paper presents a novel two-layer GRU model for rumor events detection based on a Sentiment Dictionary (SD) and a dynamic time series (DTS) algorithm, named as SD-DTS-GRU. The model learns continuous representations of microblog events in a better manner by making use of the SD to identify fine-grained human emotional expressions of each event and retaining the time distribution of social events by the DTS algorithm. The experimental results on Sina Weibo datasets show that our model achieves a high accuracy of 95.2% and demonstrate that our proposed SD-DTS-GRU model outperforms latest explorations on rumor events detection.

Sentiment analysis of Chinese micro-blog based on sentiment dictionary has become a challenging research subject in the field of artificial intelligence. However, due to insufficient sentiment words, Chinese micro-blog sentiment analysis is difficult to process high accuracy. Aimed at this issue, we propose a method for constructing multiple sentiment dictionaries, which mainly constructs original sentiment dictionary, emoji dictionary, and other related dictionaries. Among them, we have innovatively constructed a Chinese micro-blog new word sentiment dictionary. Multiple sentiment dictionaries increase the coverage of sentiment words. At the same time, we further analyze semantic rule sets between Chinese micro-blog texts and take the inter-sentence analysis rules and sentence pattern analysis rules into the sentiment analysis of Chinese micro-blog, which further improves the accuracy of Chinese micro-blog sentiment analysis. Finally, based on the method of multiple sentiment dictionaries and semantic rule sets, we propose an algorithm for Chinese micro-blog sentiment calculation from complex sentences to clauses and then from clauses to words, and finally combined with the emoji. This algorithm can accurately classify Chinese micro-blog into positive Chinese micro-blog, negative Chinese micro-blog, and neutral Chinese micro-blog. The experimental results show that this method has greatly improved the sentiment analysis of Chinese micro-blog.

The method of text sentiment analysis based on sentiment dictionary often has the problems that the sentiment dictionary doesn't contain enough sentiment words or omits some field sentiment words. In addition, due to the existence of some polysemic sentiment words with positivity, negativity, and neutrality, the words' polarity cannot be accurately expressed, so the accuracy of text sentiment analysis is reduced to some extent. In this paper, an extended sentiment dictionary is constructed. The extended sentiment dictionary contains the basic sentiment words, the field sentiment words, and the polysemic sentiment words, which improves the accuracy of sentiment analysis. The naive Bayesian classifier is used to determine the field of the text in which the polysemic sentiment word is. Thus, the sentiment value of the polysemic sentiment word in the field is obtained. By utilizing the extended sentiment dictionary and the designed sentiment score rules, the sentiment of the text is achieved. The experimental results prove that the proposed sentiment analysis method based on extended sentiment dictionary has certain feasibility and accuracy. The research is meaningful for the sentiment recognition of the comment texts.

In this era of Internet and big data, there is billions of news generated every day, and the traditional manual methods are insufficient for public opinion orientation analysis. Especially for Chinese, which has more complicated syntax and semantic structure, and there is no space between words as separator. This greatly increases the difficulty of analyzing opinion orientation. In this paper, a novel approach is proposed aiming at solving the problem of public opinion orientation analysis based on Chinese news. The approach combines word2vec, sentiment dictionaries and syntax rules, where the word2vec can map words into different vectors with finite dimensions. Through it we can calculate the cosine similarity between the words and sentiment dictionaries to get the orientation value of target words, which is helpful for calculating the orientation value of key sentences and full text. Specifically, the process consists of three steps. First, word2vec is used to train word embedding, and every word in corpus is mapped into a given vector space. Then, key sentences are extracted from news content. Finally, pre-defined syntax rules with word vector similarity are used to analyze document orientation based on key sentences. Several experiments are conducted on both closed and open datasets, and the results validate the effectiveness of the proposed approach.

Most of existing methods do not consider the influence of expression and tone on barrage sentiment analysis. This decreases the effect and accuracy of barrage sentiment analysis. Therefore, we propose a barrage sentiment analysis scheme based on expression and tone. First, we propose a new sentiment dictionary based on expression and tone to increase the effect of barrage sentiment analysis. Second, we propose a new calculation method of sentiment value based on expression and tone for barrage sentiment analysis to increase the accuracy. Meanwhile, we change a single threshold to a threshold range, to expand the scope of neutral barrages. Finally, the experimental results show that our scheme is more effective and practical than the existing methods in the scenario of barrage sentiment analysis.

An improved information gain feature selection method based on sentiment dictionary was proposed.Firstly,aiming at the existing problems of information gain feature selection,such as paying attention to the frequency of feature word and ignoring the balance of corpus,an improved method was proposed.Secondly,considering the influence of sentiment words in text classification,a feature selection method IGSC (information gain combining sentiment classification) based on sentiment dictionary was proposed for text classification.By matching the text emotion words and combining the weight of emotion words,the feature dimension reduction was realized and the problem of text data sparseness affecting classification performance was solved.Finally,according to the proposed feature selection method of travel review data set for experimental verification and analysis,the experimental results show that the improved text sentiment classification feature selection method has been improved in terms of classification accuracy,recall and F value,and classification has better stability.

Online social media has become an ideal place in spreading rumor events with its convenience in communication and information dissemination, which raises the difficulty in debunking rumor events automatically. To deal with such a challenge, traditional classification approaches relying on manually labeled features have to face a daunting number of human efforts. With the consideration of the realness of a rumor event, it will be verified and authenticated with multi-type individual information, especially with individuals' emotional expressions to events and their own credibility. This paper presents a novel two-layer GRU model for rumor events detection based on multi-type individual information (MII) and a dynamic time-series (DTS) algorithm, named as MII–DTS-GRU. Specifically, MII refers to adopt the sentiment dictionary to identify fine-grained human emotional expressions to events and fuse with the individual credibility. Besides, the DTS algorithm retains the time distribution of social events. Experimental results on Sina Weibo datasets show that our model achieves a high accuracy of 96.3% and demonstrate that our proposed MII–DTS-GRU model outperforms the state-of-the-art models on rumor events detection. [ABSTRACT FROM AUTHOR]

Online Social Networks (OSNs) is an ideal place for spreading rumor events as it is convenient in information production and dissemination. Automatically debunking these rumor events is important to pursue and restore the truth. However, it is a challenging task to employ traditional classification approaches for rumor events detection since they rely on hand-crafted features that require daunting manual efforts. Besides, we observe that the various posts of each rumor event will debate its realness over time. Different individuals also have different emotional reactions to events, which will affect others' identification. Thus, this paper firstly employs an automatic construction method to develop a Sentiment Dictionary (SD) to capture the fine-grained human emotional reactions to different events. Secondly, a Two-steps Dynamic Time Series (TsDTS) algorithm, involving the sentimental information in the division process, is elaborated to retain the time-span distribution information of microblog events in a natural manner. At last, a novel two-layer Cascaded Gated Recurrent Unit (CGRU) model based on the SD and the TsDTS algorithm is proposed for rumor events detection, named as SD-TsDTS-CGRU. Experimental results on real datasets from OSNs demonstrate that our proposed SD-TsDTS-CGRU model outperforms the latest rumor events detection algorithms. [ABSTRACT FROM AUTHOR]

Background: Anorexia nervosa is a clinical disorder syndrome of the wide spectrum without a fully recognized etiology. The necessary issue in the clinical diagnostic process is to detect the causes of this disease (e.g., my body image, food, family, peers), which the therapist gradually comes to by verifying assumptions using proper methods and tools for diagnostic process. When a person is diagnosed with anorexia, a clinician (a doctor, a therapist or a psychologist) proposes a therapeutic diagnosis and considers the kind of treatment that should be applied. This process is also continued during therapeutic diagnosis. In both cases, it is recommended to apply computer-aided tools designed for testing and confirming the assumptions made by a psychologist. The paper aims to present the computer-aided therapeutic diagnosis method for anorexia. The proposed method consists of 4 stages: free statements of a patient about his/her body image, the general sentiment analysis of statement based on Recurrent Neural Network, assessment of the intensity of five basic emotions: happiness, anger, sadness, fear and disgust (using the Nencki Affective Word List and conversion of words to their basic form), and the assessment of particular areas of difficulties-the sentiment analysis based on the dictionary approach was applied.Results: The sentiment analysis of a document achieved 72% and 51% of effectiveness, respectively, for RNN and dictionary-based methods. The intensity of sadness (emotion) occurring within the dictionary method is differentiated between control and research group at the level of 10%.Conclusion: The quick access to the sentiment analysis of a statement on the image of patient's body, emotions experienced by the patient and particular areas of difficulties of people prone to the anorexia nervosa disorders, may help to establish the diagnosis in a very short time and start an immediate therapy. The proposed automatic method helps to avoid patient's aversions towards the therapy, which may include avoiding patient-therapist communication, talking about less essential topics, coming late for the sessions. These circumstances can guarantee promising prognosis for recovering. [ABSTRACT FROM AUTHOR]

With the growing pace of internet usage, there is a vast variety of diverse individual opinions and thoughts avail-able online. Consumer reviews can act as a feedback and as well as a pool of ideas for which they can be of immense importance to any business. With the growth and popularity of opinion-rich resources such as online review sites and personal blogs, people now can and do, actively use information technology to seek out and un-derstand the opinions of others to decide whether to buy a product or not. Social media websites such as Facebook, Twitter, and e-commerce websites such as eBay, Amazon, etc. are being widely used to communicate viewpoints effectively. Assigning a positive or a negative sentiment to these reviews can help companies understand their users and also help users to make better decisions. Sentiment analysis being a challenging task can be tackled using supervised machine learning techniques or through unsupervised lexicon based approaches if labelled data is unavailable. In this study, we show that in absence of labelled product reviews of a particular website, labelled product reviews from a different website can be effectively used to train the supervised techniques to achieve a comparable performance to the unsupervised lexicon based approaches. This approach also benefits by covering all of the product reviews which the lexicon based approaches fail to do so. We deduce this by comparing five su-pervised approached and three lexicon based approaches on iPhone 5s reviews gathered from Amazon, Facebook, and Reevoo blog. Furthermore, we also found that unigram features combined with bigram features give the best results, and the effect of varying the training data size on the performance of ML classifiers in some cases was significant whereas in other cases it did not have any effect. Our results also suggest that reviews from Amazon are easiest to classify, followed by reviews from Reevo, and Facebook reviews are the hardest to classify. [ABSTRACT FROM AUTHOR]

Abstract Background Diagnosing and treating anorexia nervosa is an important challenge for modern psychiatry. Taking into account a connection between the mental state of a person and the characteristics of their language, this paper presents developed and tested method for analyzing the written statements of patients with anorexia nervosa and healthy individuals, including the identification of keywords. Methods Due to the short nature of the texts, which is related to the difficulty of expressing oneself about one’s body when suffering from anorexia, the bag of words approach was used for documents’ information representation. The document is represented as a vector, where its various elements indicate the number of individual words. Then, a rule-based model was created, where as a collection of rules, dictionary files were used corresponding to three groups of positive, negative and neutral sounds for each subcategory. Next in the analyzed texts were searched and counted keywords. Based on the keywords found, each of the documents was categorized into one of the groups in every subcategory. Results It is possible to indicate a set of characteristics sentiment for every person. Additionally, the results of specific patient could be analyzed in six specific subcategories: self-esteem, acceptance of the assessment of the environment, emotions, autoimmune, functioning of the body and body image. Conclusions The described analysis indicates the existence of a relationship between the mental state of the author’s textual health and the vocabulary he or she uses. It is possible to indicate a set of characteristic sentiment terms specific to a given group of people. Their presence is related to the author’s mental state and their body image. It could help focus on specific topics during therapy.

Sentiment lexicon is a list of vocabularies that consists of positive and negative words. In opinion mining, sentiment lexicon is one of the important source in text polarity classification task in sentiment analysis model. Studies in Malay sentiment analysis is increasing since the volume of sentiment data is growing on social media. Therefore, requirement in Malay sentiment lexicon is high. However, Malay sentiment lexicon development is a difficult task due to the scarcity of Malay language resource. Thus, various approaches and techniques are used to generate sentiment lexicon. The objective of this paper is to develop Malay sentiment lexicon generation algorithm based on WordNet. In this study, the method is to map the WordNet Bahasa with English WordNet to get the offset value of a seed set of sentiment words. The seed set is used to generate the synonym and antonym semantic relation in English WordNet. The highest result achives 86.58% agreement with human annotators and 91.31% F1-measure in word polarity classification. The result shows the effectiveness of the proposed algorithm to generate Malay sentiment lexicon based on WordNet.