Sentiment Evolution Research Articles

A Study on the Evolution of Public Sentiment and Emotional Communication Mechanisms in Women's Issues on microblog: Case Study of "Quan XiXi' s Dialogue with Chizuko Ueno"

The research utilizes Sina microblog as its platform, analyzing textual data associated with trending topics featuring "Peking University Dormitory and Ueno Chat", to explore patterns of sentiment evolution and emotional expression. Findings reveal that public sentiment follows a four-phase trajectory: inception, peak, fluctuation, and decline. Negative sentiments dominate among users discussing the topic. This analysis elucidates microblog's role in disseminating women's issues, identifies key characteristics and challenges of such discussions on the platform, delineates major disagreements and focal points in user discourse, and endeavors to uncover underlying societal symptoms. The insights contribute valuable data to studies on the forms and impacts of women's issue dissemination on microblog.

Correlations and Fractality in Sentence-Level Sentiment Analysis Based on VADER for Literary Texts

We perform a sentence-level sentiment analysis study of different literary texts in English language. Each text is converted into a series in which the data points are the sentiment value of each sentence obtained using the sentiment analysis tool (VADER). By applying the Detrended Fluctuation Analysis (DFA) and the Higuchi Fractal Dimension (HFD) methods to these sentiment series, we find that they are monofractal with long-term correlations, which can be explained by the fact that the writing process has memory by construction, with a sentiment evolution that is self-similar. Furthermore, we discretize these series by applying a classification approach which transforms the series into a one on which each data point has only three possible values, corresponding to positive, neutral or negative sentiments. We map these three-states series to a Markov chain and investigate the transitions of sentiment from one sentence to the next, obtaining a state transition matrix for each book that provides information on the probability of transitioning between sentiments from one sentence to the next. This approach shows that there are biases towards increasing the probability of switching to neutral or positive sentences. The two approaches supplement each other, since the long-term correlation approach allows a global assessment of the sentiment of the book, while the state transition matrix approach provides local information about the sentiment evolution along the text.

The Effects of Sentiment Evolution in Financial Texts: A Word Embedding Approach

ABSTRACT We examine the evolutionary effects of sentiment words in financial text and their implications for various business outcomes. We propose an algorithm called Word List Vector for Sentiment (WOLVES) that leverages both a human-defined sentiment word list and the word embedding approach to quantify text sentiment over time. We then apply WOLVES to investigate the evolutionary effects of the most popular financial word list, Loughran and McDonald (LM) dictionary, in annual reports, conference calls, and financial news. We find that LM negative words become less negative over time in annual reports compared to conference calls and financial news, while LM positive words remain qualitatively unchanged. This finding reconciles with existing evidence that negative words are more subject to managers’ strategic communication. We also provide practical implications of WOLVES by correlating the sentiment evolution of LM negative words in annual reports with market reaction, earnings performance, and accounting fraud.

Public Message Analysis Based on LDA-BERT-BiLSTM -- Taking the “Leadership Message Board” of People’s Daily Website as an Example

Abstract [Objective/Significance] This article explores the theme of elderly care and its emotional trend, providing a scientific basis for formulating and optimizing elderly care policies, thereby improving the quality of elderly care services and promoting the harmonious and stable development of society. [Method/Process] This study uses the message data related to pension issues in the “leadership message board” platform of People’s Daily Online as the research object, the LDA model to extract relevant topics, and the BERT-BiLSTM model to analyze the emotional trend changes of each subject. [Result/Conclusion] The research results show that the theme of pension covers 16 sub-subjects, such as “environmental noise problem of pension,” “pension community construction planning,” and “retirement pension policy treatment.” The classification accuracy of the BERT-BiLSTM model is 0.89, and the F1 value is 0.86, which shows its superiority in sentiment evolution analysis. The expression of negative emotions in pension theme messages is generally higher than that of neutral and positive feelings, and the elderly group’s emotional attitude shows significant differences under different themes of raising older people.

“Amusing ourselves to death”: Mechanisms in cyberbullying prompted by rumors and denigration amidst the COVID-19 pandemic in China

The use of rumors and denigration in cyberbullying have been studied in the contexts of public opinion and public policy, but questions remain. The study presented here examines the association of rumors and denigration with cyberbullying during the COVID-19 pandemic and provides a sentiment evolution and social network map of cyberbullying features at different stages of an episode. This study applied latent dirichlet allocation (LDA) topic modeling, sentiment analysis and semantic network analysis to analyze three Chinese cases where rumors and denigration triggered cyberbullying, with 7691 comments. The authors found that cyberbullying caused by rumors and denigration often started with the release of fake information, and core topics and sentiment values varied between stages of the cyberbullying episode. Collective moral disengagement theory suggests collective behavior may reduce moral self-control, generating online interactive behaviors that enhance the spread of rumors and denigration. Spiral of silence theory also offers perspectives on cyberbullying, which are considered in this study. While the cases in this study occurred within the context of COVID-19, cyberbullying via rumor and denigration may occur in many scenarios, so the current paper will interest multiple audiences. The findings of this study suggest that researchers and decision-makers could helpfully design programs to supervise public opinion, raise awareness of cyberbullying and avoid secondary harms.

Optimization Model Construction of Online Public Opinion Dissemination Based on Behavioral Data Mining

Abstract In this paper, we propose an optimization method based on behavioral data mining for the emergence of negative emotions in network public opinion in unexpected situations leading to problems that endanger social stability and use data mining to confirm the correspondence of the kNN algorithm. In the opinion propagation model, the radius of opinion radiation is assumed to use the network node density and distribution density as features of node exchange information. Then, the kNN algorithm is used to train the comment set for the analysis of user sentiment evolution of network opinion in the social network environment, and the web crawler technology is used to obtain the output interface data APIs of microblogs and WeChat, and the social media user comment data is used as the data for the empirical analysis of network opinion. snowNLP and kNN algorithms are used to analyze the sentiment score of network opinion and the sentiment score less than 0.5, i.e., the sentiment polarity. There were 15 days when the sentiment score tended to be negative and 65 days when the sentiment score was greater than 0.5, i.e., the sentiment polarity tended to be positive.

Analyzing the spatiotemporal coupling relationship between public opinion and the epidemic during COVID-19

PurposeThe outbreak of COVID-19 has become a major public health emergency worldwide. How to effectively guide public opinion and implement precise prevention and control is a hot topic in current research. Mining the spatiotemporal coupling between online public opinion and offline epidemics can provide decision support for the precise management and control of future emergencies.Design/methodology/approachThis study focuses on analyzing the spatiotemporal coupling relationship between public opinion and the epidemic. First, based on Weibo information and confirmed case information, a field framework is constructed using field theory. Second, SnowNLP is used for sentiment mining and LDA is utilized for topic extraction to analyze the topic evolution and the sentiment evolution of public opinion in each coupling stage. Finally, the spatial model is used to explore the coupling relationship between public opinion and the epidemic in space.FindingsThe findings show that there is a certain coupling between online public opinion sentiment and offline epidemics, with a significant coupling relationship in the time dimension, while there is no remarkable coupling relationship in space. In addition, the core topics of public concern are different at different coupling stages.Originality/valueThis study deeply explores the spatiotemporal coupling relationship between online public opinion and offline epidemics, adding a new research perspective to related research. The result can help the government and relevant departments understand the dynamic development of epidemic events and achieve precise control while mastering the dynamics of online public opinion.

Respond to Weibo Comments While Incorporating the Sentiment Evolution Trend Depicted by a Sankey Chart

Respond to Weibo Comments While Incorporating the Sentiment Evolution Trend Depicted by a Sankey Chart

The evolution of public sentiment toward government management of emergencies: Social media analytics

At present, social media have become the main media of network public opinion (PO) dissemination. By analyzing the trend of emotional development in public emergencies, we can explore the evolution law of PO and identify potential risks, which provide decision support for the guidance and control of government management. First, based on the concept of critical points in the complex system, this study established a public sentiment (PS) evolution model under public emergencies and proposed an algorithm to identify the critical points in PS based on microblog data analysis. In addition, the BC-BIRCH algorithm was used to construct a topic clustering model for public emergencies, which improved the effect of topic discovery by merging multiple topic clusters. The evolution of public emergencies was analyzed by calculating the emotional heat value of different topic events. Finally, experimental results showed that the emotion of netizens' fluctuates greatly in the initial stage of PO under different themes. The method used in this paper achieved good results in topic clustering, critical point prediction, and PO evolution analysis of public emergencies. The main contribution of this paper is to analyze the evolution of the internal mechanism of PS and to identify and predict key nodes such as the outbreak and extinction of netizens' sentiment based on data-driven methods so as to provide the basis and support to the government and related media as the main body of prevention and control to respond in advance and guide in time.

The predicting public sentiment evolution on public emergencies under deep learning and internet of things

The predicting public sentiment evolution on public emergencies under deep learning and internet of things

Revealing Public Opinion towards the COVID-19 Vaccine with Weibo Data in China: BertFDA-Based Model.

The COVID-19 pandemic has created unprecedented burdens on people’s health and subjective well-being. While countries around the world have established models to track and predict the affective states of COVID-19, identifying the topics of public discussion and sentiment evolution of the vaccine, particularly the differences in topics of concern between vaccine-support and vaccine-hesitant groups, remains scarce. Using social media data from the two years following the outbreak of COVID-19 (23 January 2020 to 23 January 2022), coupled with state-of-the-art natural language processing (NLP) techniques, we developed a public opinion analysis framework (BertFDA). First, using dynamic topic clustering on Weibo through the latent Dirichlet allocation (LDA) model, a total of 118 topics were generated in 24 months using 2,211,806 microblog posts. Second, by building an improved Bert pre-training model for sentiment classification, we provide evidence that public negative sentiment continued to decline in the early stages of COVID-19 vaccination. Third, by modeling and analyzing the microblog posts from the vaccine-support group and the vaccine-hesitant group, we discover that the vaccine-support group was more concerned about vaccine effectiveness and the reporting of news, reflecting greater group cohesion, whereas the vaccine-hesitant group was particularly concerned about the spread of coronavirus variants and vaccine side effects. Finally, we deployed different machine learning models to predict public opinion. Moreover, functional data analysis (FDA) is developed to build the functional sentiment curve, which can effectively capture the dynamic changes with the explicit function. This study can aid governments in developing effective interventions and education campaigns to boost vaccination rates.

Issues and Challenges of Aspect-based Sentiment Analysis: A Comprehensive Survey

The domain of Aspect-based Sentiment Analysis, in which aspects are extracted, their sentiments are analysed and sentiments are evolved over time, is getting much attention with increasing feedback of public and customers on social media. The immense advancements in this field urged the researchers to devise new techniques and approaches, each sermonizing a different research analysis/question, that cope with upcoming issues and complex scenarios of Aspect-based Sentiment Analysis. Therefore, this survey emphasized on the issues and challenges that are related to extraction of different aspects and their relevant sentiments, relational mapping between aspects, interactions, dependencies, and contextual-semantic relationships between different data objects for improved sentiment accuracy, and prediction of sentiment evolution dynamicity. A rigorous overview of the recent progress is summarized based on whether they contributed towards highlighting and mitigating the issue of Aspect Extraction, Aspect Sentiment Analysis or Sentiment Evolution. The reported performance for each scrutinized study of Aspect Extraction and Aspect Sentiment Analysis is also given, showing the quantitative evaluation of the proposed approach. Future research directions are proposed and discussed, by critically analysing the presented recent solutions, that will be helpful for researchers and beneficial for improving sentiment classification at aspect-level.

Sentiment Evolution Analysis and Association Rule Mining for COVID-19 Tweets

This article presents a data mining study carried out on social media users in the context of COVID-19 and offers four main contributions. The first one consists in the construction of a COVID-19 dataset composed of tweets posted by users during the first stages of the virus propagation. The second contribution offers a sample of the interactions between users on topics related to the pandemic. The third contribution is a sentiment analysis, which explores the evolution of emotions throughout time, while the fourth one is an association rule mining task. The indicators determined by statistics and the results obtained from sentiment analysis and association rule mining are eloquent. For instance, signs of an upcoming worldwide economic crisis were clearly detected at an early stage in this study. Overall results are promising and can be exploited in the prediction of the aftermath of COVID-19 and similar crisis in the future.

Improving sentiment analysis accuracy with emoji embedding

Due to the diversity and variability of Chinese syntax and semantics, accurately identifying and distinguishing individual emotions from online texts is challenging. To overcome this limitation, we incorporate a new source of individual sentiment, emojis, which contain thousands of graphic symbols and are increasingly being used for expressing emotion in online conversations. We examined popular sentiment analysis algorithms, including rule-based and classification algorithms, to evaluate the impact of supplementing emojis as additional features to improve the algorithm performance. Emojis were also translated into corresponding sentiment words when constructing features for comparison with those directly generated from emoji label words. In addition, considering different functions of emojis in texts, we classified all posts in the dataset by their emoji usage and examined the changes in algorithm performance. We found that emojis are effective as expanding features for improving the accuracy of sentiment analysis algorithms, and the algorithm performance can be further increased by taking different emoji usages into consideration. In this study, we developed an improved emoji-embedding model based on Bi-LSTM (namely, CEmo-LSTM), which achieves the highest accuracy (around 0.95) when analyzing online Chinese texts. We applied the CEmo-LSTM algorithm to a large dataset collected from Weibo from December 1, 2019 to March 20, 2020 to understand the sentiment evolution of online users during the COVID-19 pandemic. We found that the pandemic remarkably impacted individual sentiments and caused more passive emotions (e.g., horror and sadness). Our novel emoji-embedding algorithm creatively combined emojis as well as emoji usage with the sentiment analysis model and can handle emotion mining tasks more effectively and efficiently.

Analysis of public opinion evolution of COVID-19 based on LDA-ARMA hybrid model

The aim of this study was to explore a method for developing an emotional evolution classification model for large-scale online public opinion of events such as Coronavirus Disease 2019 (COVID-19), in order to guide government departments to adopt differentiated forms of emergency management and to correctly guide online public opinion for severely afflicted areas such as Wuhan and those afflicted elsewhere in China. We propose the LDA-ARMA deep neural network for dynamic presentation and fine-grained categorization of a public opinion events. This was applied to a huge quantity of online public opinion texts in a complicated setting and integrated the proposed sentiment measurement algorithm. To begin, the Latent Dirichlet Allocation (LDA) was employed to extract information about the topic of comments. The autoregressive moving average model (ARMA) was then utilized to perform multidimensional sentiment analysis and evolution prediction on large-scale textual data related to COVID-19 published by netizens from Wuhan and other countries on Sina Weibo. The results show that Wuhan netizens paid more attention to the development of the situation, treatment measures, and policies related to COVID-19 than other issues, and were under greater emotional pressure, whereas netizens in the rest of the country paid more attention to the overall COVID-19 prevention and control, and were more positive and optimistic with the assistance of the government and NGOs. The average error in predicting public opinion sentiment was less than 5.64%, demonstrating that this approach may be effectively applied to the analysis of large-scale online public sentiment evolution.

Sentiment evolution with interaction levels in blended learning environments: Using learning analytics and epistemic network analysis

Sentiment evolution is a key component of interactions in blended learning. Although interactions have attracted considerable attention in online learning contexts, there is scant research on examining sentiment evolution over different interactions in blended learning environments. Thus, in this study, sentiment evolution at different interaction levels was investigated from the longitudinal data of five learning stages of 38 postgraduate students in a blended learning course. Specifically, text mining techniques were employed to mine the sentiments in different interactions, and then epistemic network analysis (ENA) was used to uncover sentiment changes in the five learning stages of blended learning. The findings suggested that negative sentiments were moderately associated with several other sentiments such as joking, confused, and neutral sentiments in blended learning contexts. Particularly in relation to deep interactions, student sentiments might change from negative to insightful ones. In contrast, the sentiment network built from social-emotion interactions shows stronger connections in joking-positive and joking-negative sentiments than the other two interaction levels. Most notably, the changes of co-occurrence sentiment reveal the three periods in a blended learning process, namely initial, collision and sublimation, and stable periods. The results in this study revealed that students’ sentiments evolved from positive to confused/negative to insightful.

Детермінанти споживчої поведінки в умовах пандемії COVID-19

The article is aimed at identifying typical determinants of consumer behaviour amidst the COVID-19 pandemic, and identifying current consumer trends and priorities in purchasing goods. An attempt is made to identify the main changes in the behaviour of modern consumers and the extent of changes in their preferences for buying goods. Consumer behaviour is defined as a complex socio-economic and, generally, interdisciplinary phenomenon accumulating a whole range of determinants. The authors have identified key factors determining consumer behaviour in the COVID-19 pandemic. It is confirmed that the current pandemic and the associated economic recession affect consumers’ sensitivity to the economic factor, stratifying them into four groups: vulnerable, conservative, optimistic and forced ascetics. The appearance of digital consumer, a new model of the buyer, is substantiated. A trend to significantly increase the volume of the consumer basket in 2020, and reduce the frequency of purchases with a focus on meeting primary human needs is revealed. New trends in consumer behaviour are identified: the focus on home cooking and eating at home, healthy lifestyle, protecting health, and feeling safe and secure. Particular attention is paid to reviewing product categories preferred by the modern consumer. Deterioration of the consumers’ psychological stability and increase in the level of tension and conflict in the course of service in outlets is proved. A summary of the features of the consumer sentiment evolution is made by the stages of the COVID-19 pandemic global development. The opportunities opened by the pandemic for the modern consumer and the process of consumption, in general are substantiated.

A Literature Review of Sentiment Evolution

Sentiment analysis has existed as a field of research since the early 20th century. While sentiment analysis is a powerful tool for discovering the inherent emotions, it leaves much to be desired. Most of it stems from the fact that traditional sentiment analysis ignores the dynamics involved. Sentiment evolution, which takes into account the dynamic nature of opinions, is an avenue that shows much promise. In this paper, we present the growing field of sentiment evolution tracking. We describe the various disciplines it has been applied in. It is followed by a bibliometric review of existing literature that analyses the publishing and citation trends on the topic.

Parallel evolution and response decision method for public sentiment based on system dynamics

Governments face difficulties in policy making in many areas such as health, food safety, and large-scale projects where public perceptions can be misplaced. For example, the adoption of the MMR vaccine has been opposed due to the publicity indicating an erroneous link between the vaccine and autism. This research proposes the “Parallel Evolution and Response Decision Framework for Public Sentiments” as a real-time decision-making method to simulate and control the public sentiment evolution mechanisms. This framework is based on the theories of Parallel Control and Management (PCM) and System Dynamics (SD) and includes four iterative steps: namely, SD modelling, simulating, optimizing, and controlling. A concrete case of an anti-nuclear mass incident that sparked public sentiment in China is introduced as a study sample to test the effectiveness of the proposed method. In addition, the results indicate the effects by adjusting the key control variables of response strategies. These variables include response time, response capacity, and transparency of the government regarding public sentiment. Furthermore, the advantages and disadvantages of the proposed method will be analyzed to determine how it can be used by policy makers in predicting public opinion and offering effective response strategies.

Exploiting Long-Term Dependency for Topic Sentiment Analysis

Most existing unsupervised approaches to detect topic sentiment in social texts consider only the text sequences in corpus and put aside social dynamics, as leads to algorithm’s disability to discover true sentiment of social users. To address the issue, a probabilistic graphical model LDTSM (Long-term Dependence Topic-Sentiment Mixture) is proposed, which introduces dependency distance and uses the dynamics of social media to achieve the perfect combination of inheriting historical topic sentiment and fitting topic sentiment distribution underlying in current social texts. Extensive experiments on real-world SinaWeibo datasets show that LDTSM significantly outperforms JST, TUS-LDA and dNJST in terms of sentiment classification accuracy, with better inference convergence, and topic and sentiment evolution analysis results demonstrate that our approach is promising.