Latent Dirichlet Allocation Topic Model Research Articles

Twitter bots, democratic deliberation and social accountability: the case of #OccupyWallStreet

PurposeThis study is motivated to provide a theoretically informed, data-driven assessment of the consequences associated with the participation of non-human bots in social accountability movements; specifically, the anti-inequality/anti-corporate #OccupyWallStreet conversation stream on Twitter.Design/methodology/approachA latent Dirichlet allocation (LDA) topic modeling approach as well as XGBoost machine learning algorithms are applied to a dataset of 9.2 million #OccupyWallStreet tweets in order to analyze not only how the speech patterns of bots differ from other participants but also how bot participation impacts the trajectory of the aggregate social accountability conversation stream. The authors consider two research questions: (1) do bots speak differently than non-bots and (2) does bot participation influence the conversation stream.FindingsThe results indicate that bots do speak differently than non-bots and that bots exert both weak form and strong form influence. Bots also steadily become more prevalent. At the same time, the results show that bots also learn from and adapt their speaking patterns to emphasize the topics that are important to non-bots and that non-bots continue to speak about their initial topics.Research limitations/implicationsThese findings help improve understanding of the consequences of bot participation within social media-based democratic dialogic processes. The analyses also raise important questions about the increasing importance of apparently nonhuman actors within different spheres of social life.Originality/valueThe current study is the first, to the authors’ knowledge, that uses a theoretically informed Big Data approach to simultaneously consider the micro details and aggregate consequences of bot participation within social media-based dialogic social accountability processes.

Identification of Hydrogen-Energy-Related Emerging Technologies Based on Text Mining

As a versatile energy carrier, hydrogen possesses tremendous potential to reduce greenhouse emissions and promote energy transition. Global interest in producing hydrogen from renewable energy sources and transporting, storing, and utilizing hydrogen is rising rapidly. However, the high costs of producing clean hydrogen and the uncertain application scenarios for hydrogen energy result in its relatively limited utilization worldwide. It is necessary to find new promising technological paths to drive the development of hydrogen energy. As part of technological innovation, emerging technologies have vital features such as prominent impact, novelty, relatively fast growth, etc. Identifying emerging hydrogen-energy-related technologies is important for discovering innovation opportunities during the energy transition. Existing research lacks analysis of the characteristics of emerging technologies. Thus, this paper proposes a method combining the latent Dirichlet allocation topic model and hydrogen-energy expert group decision-making. This is used to identify emerging hydrogen-related technology regarding two features of emerging technologies, novelty and prominent impact. After data processing, topic modeling, and analysis, the patent dataset was divided into twenty topics. Six emerging topics possess novelty and prominent impact among twenty topics. The results show that the current hotspots aim to promote the application of hydrogen energy by improving the performance of production catalysts, overcoming the wide power fluctuations and large-scale instability of renewable energy power generation, and developing advanced hydrogen safety technologies. This method efficiently identifies emerging technologies from patents and studies their development trends. It fills a gap in the research on emerging technologies in hydrogen-related energy. Research achievements could support the selection of technology pathways during the low-carbon energy transition.

“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.

Research on Mining Talent Demand for E-commerce Majors based on LDA Topic Model

[Purpose] Based on the text mining method, this study analyzes the job demand for domestic e-commerce industry positions in the Internet-oriented recruitment data, promotes the matching of e-commerce positions and talents, and promotes the good construction of the employment environment in the domestic e-commerce industry.[Method] Use the LDA(Latent dirichlet allocation) topic model for job competency requirements to calculate the similarity of the word segmentation results for professional talent requirements, determine the optimal number of topics, and output the visualization results of the LDA topic model.[Conclusion] In eastern China, there is a high demand for e-commerce jobs, and the majority of these positions only call for 1-3 years of experience. The basic requirement for the majority of jobs is a college degree. The Director of Operations and Director of Network Operations focus on e-commerce operations and management, the Network Promotion Specialist focuses on e-commerce advertising and product promotion, the Data Analyst and Market Analyst focus on data analysis and market research, and the Sales Representative focuses on sales. There is a correlation between the salary of the positions and education, experience and region; the higher the education, the more experience and the higher the level of regional development, the higher the salary level.

Main Themes and Bibliometric Analysis of Conflict and Climate Change Studies

Climate change, thought to cause significant problems if necessary precautions are not taken, causes droughts and natural disasters to occur frequently and severely. The primary resources required for life, such as water, soil, and food, will decrease in such a situation. It is thought that experiencing tensions dependent on resource scarcity will trigger internal and external conflicts, especially in underdeveloped countries with weak central governments and low income levels. On the other hand, because wars cause the use of large amounts of fossil fuels and firearms, they destroy forests and natural resources and increase carbon dioxide emissions, which are considered the most crucial cause of the climate crisis. In other words, while climate changes trigger wars, unfortunately, wars also increase the climate crisis. Especially when war reaches an existential dimension for countries, the risk of non-compliance with these agreements increases even in states that reshape their energy policies with significant investments to prevent climate change. In this study, we examined the Web of Science (Wos) literature on the relationship between climate change, which is seen as a significant threat to our future, and wars through its main themes and bibliometric indicators. In this study, we examined the Web of Science (Wos) literature on the relationship between climate change, which is seen as a significant threat to our future, and wars through its main themes and bibliometric indicators. Looking at the time series, interest in conflict and climate change studies has increased, and most studies have been done mainly in the field of "environmental sciences and ecology". Latent Dirichlet Allocation (LDA) Topic Modeling was applied to the abstracts downloaded in this study to find the main topics of conflict and climate change studies. So, the main topics were food, politics, migration, carbon emissions, and animals.

The Relationship Between Political Leader’s Personalities and Regional Social Governance Modernization

The study aims to investigate the relationship between the personalities exhibited by party and government leaders and the modernization of regional social governance. It aspires to offer novel insights to empower the local governments of Chinese provinces, thereby assisting them in augmenting the modernization of social governance.Led by upper echelons theory, we proposed an analytical framework to explore the relationship. We firstly collected the texts of the activity reports of the leaders in 31 provinces of mainland China during the years 2018 to 2020. Their personalities were discerned through the application of Latent Dirichlet Allocation (LDA) topic modeling and principal component analysis. Integrating the dimensions of processes and outcomes, we then devised an evaluation system to assess the level of regional social governance modernization. The system underwent a comprehensive evaluation employing principal component analysis. Finally, we employed regression analysis and the Quadratic Assignment Procedure (QAP) regression analysis to quantitatively assess the effect of political leader’s personalities on the modernization level of regional social governance.According to our results, the personalities exhibited by political leaders could be classified into six dimensions, aligning with the framework proposed by Holland vocational interest theory. We revealed that the six types of personalities indeed exert influence on the modernization of regional social governance. However, compared to the effect of environmental factors such as economic conditions and the availability of skilled personnel, their explanatory power is relatively weaker. Among the identified personalities, the leaders displaying realistic and research-oriented personalities demonstrate a heightened capacity to yield substantial positive impacts on social governance modernization. Additionally, social personality also plays a discernible role in the context. Furthermore, the amalgamation of political leaders’ personalities illuminates a nuanced picture marked by moderate influence and intricate complexity.

Emotional Health and Climate-Change-Related Stressor Extraction from Social Media: A Case Study Using Hurricane Harvey

Climate change has led to a variety of disasters that have caused damage to infrastructure and the economy with societal impacts to human living. Understanding people’s emotions and stressors during disaster times will enable preparation strategies for mitigating further consequences. In this paper, we mine emotions and stressors encountered by people and shared on Twitter during Hurricane Harvey in 2017 as a showcase. In this work, we acquired a dataset of tweets from Twitter on Hurricane Harvey from 20 August 2017 to 30 August 2017. The dataset consists of around 400,000 tweets and is available on Kaggle. Next, a BERT-based model is employed to predict emotions associated with tweets posted by users. Then, natural language processing (NLP) techniques are utilized on negative-emotion tweets to explore the trends and prevalence of the topics discussed during the disaster event. Using Latent Dirichlet Allocation (LDA) topic modeling, we identified themes, enabling us to manually extract stressors termed as climate-change-related stressors. Results show that 20 climate-change-related stressors were extracted and that emotions peaked during the deadliest phase of the disaster. This indicates that tracking emotions may be a useful approach for studying environmentally determined well-being outcomes in light of understanding climate change impacts.

Sankofa: Using Topic Models to Review the History of the Journal of Black Psychology

We use Latent Dirichlet Allocation (LDA) topic modeling to review the articles published in JBP between 1975 and 2020. Doing so allowed us to estimate where JBP has been, and where it might go. We interpret our work within the framework of “Sankofa,” which is an Akan symbol for the integration of the past and present toward the future. Overall, we identified five major research themes that have characterized JBP over the past four decades: Racial Attitudes (i.e., how individuals think of themselves and others in the context of race and ethnicity), Health and Well-being (i.e., health disparities and community well-being), Education (i.e., learning and higher education experiences), Sexuality and Gender (i.e., how individuals think about gender, sexuality, and body image), and Resistance and Resilience (i.e., how people experience and cope with discrimination). The present research has implications for future research directions, including increasing the representation of Black communities outside the U.S. in the JBP literature, highlighting more holistic experiences of Black people of marginalized genders and sexualities, and generating and strengthening Black-centered constructs.

ChatGPT and computational-based research: benefits, drawbacks, and machine learning applications

Generative artificial intelligence (GenAI) systems are disrupting how research is conducted across a wide range of disciplines. Many journals have decided not to allow these tools to be co-authors for the purposes of publication, but rather they must be acknowledged by authors as having been utilised in the writing process. Furthermore, due to the hallucinations that these models sometimes produce, authors are to review what is generated and recognise that they hold it to be true and accurate. To date, there has been varying research conducted on the accuracy of GenAI systems and their production of written text. However, new functions that allow GenAI systems to produce coding for constructing tools in computer programming languages highlights a new area that warrants investigation. Therefore, this article puts forth an account of using ChatGPT 3.5 to construct coding to be utilised for a Latent Dirichlet Allocation Topic Model (LDA-TM) for use in a Systematic Literature Review. This is hoped to address three elements of using ChatGPT 3.5 for coding: code review, error resolution, and scripting new code. The code will be aimed at designating an appropriate Hyper-parameter for the Random State for use in the LDA-TM. Within this context, this article will discuss the advantages and drawbacks of utilising this new tool and what it means for researchers who wish to augment their work with computer programming-based applications. To the authors knowledge, this is the first time this has been discussed within the context of the research being conducted.

Analyzing the Personality of Party and Government Leaders: A LDA Topic Model

Purpose/Significance: Personalities of party and government leaders play a pivotal role in shaping their preferences, attitudes, and conduct in the context of strategic decision-making. The analysis of personality carries substantial implications for the assessment and selection of leadership cadres. The study endeavors to introduce an innovative method for scrutinizing the personalities of party and government leaders, leveraging the technological topics generated through a Latent Dirichlet Allocation (LDA) model.Methods/Procedures: Anchored in the theory of personality behavior, the study posits that discernible topics can be extracted from news reports that document the political activities of party and government leaders. These discerned topics can be employed to make inferences about their personalities. Consequently, we systematically amassed news reports chronicling the political engagements of 62 party and government leaders spanning 31 provinces, municipalities, and autonomous regions in mainland China, covering their tenures in office up to 2021. Based on the LDA model, we conducted an analysis to uncover the dimensional structure of their personalities, incorporating techniques such as topic clustering and common factor extraction.Results/Conclusions: The study effectively identified six distinct personalities that correspond with Hollander's views on occupational personality. The development gave rise to a theory that specifically addresses the personalities exhibited by party and government leaders. Spatial analysis validated the presence of a spatial aggregation effect, underscoring the validity of our framework. Our study can provide implications for the training, evaluation, and designation of party and government leaders in the future.

Empowering Agriculture: Exploring User Sentiments and Suggestions for Plantix, a Smart Farming Application

Farming activities are transforming from traditional skill-based agriculture into knowledge-based and technology-driven digital agriculture. The use of intelligent information and communication technology introduces the idea of smart farming that enables farmers to collect weather data, monitor crop growth remotely and detect crop diseases easily. The introduction of Plantix, a pest and disease management tool in the form of a mobile application has allowed farmers to identify pests and diseases of the crop using their mobile devices. Hence, this study collected the reviews of Plantix to explore the response of the users on the Google Play Store towards the application through Latent Dirichlet Allocation (LDA) topic modeling. Results indicate four latent topics in the reviews: two positive evaluations (compliments, appreciation) and two suggestions (plant options, recommendations). We found the users suggested the application to additional plant options and additional features that might help the farmers with their difficulties. In addition, the application is expected to benefit the farmer more by having an early alert of diseases to farmers and providing various substitutes and a list of components for the remedial measures.

A Comparison of Latent Semantic Analysis and Latent Dirichlet Allocation in Educational Measurement

Topic models are mathematical and statistical models used to analyze textual data. The objective of topic models is to gain information about the latent semantic space of a set of related textual data. The semantic space of a set of textual data contains the relationship between documents and words and how they are used. Topic models are becoming more common in educational measurement research as a method for analyzing students’ responses to constructed-response items. Two popular topic models are latent semantic analysis (LSA) and latent Dirichlet allocation (LDA). LSA uses linear algebra techniques, whereas LDA uses an assumed statistical model and generative process. In educational measurement, LSA is often used in algorithmic scoring of essays due to its high reliability and agreement with human raters. LDA is often used as a supplemental analysis to gain additional information about students, such as their thinking and reasoning. This article reviews and compares the LSA and LDA topic models. This article also introduces a methodology for comparing the semantic spaces obtained by the two models and uses a simulation study to investigate their similarities.

Uncovering the quality factors driving the success of mobile payment apps

This study comprehensively analyzed the key quality factors of mobile payment applications that shape consumer perceptions and their influence on market performance. Leveraging text analytics techniques, including Latent Dirichlet Allocation (LDA) topic modeling and sentence-level sentiment analysis, we analyzed a vast dataset of 230,940 reviews of nine mobile payment apps. Our investigation revealed four significant quality factors discussed in online consumer reviews: payment convenience, security, customer service, and app design. Crucially, this study demonstrated the substantial impact of positive and negative evaluations of these factors on the market performance of mobile payment apps, with numerical ratings acting as mediators. This study breaks new ground by empirically validating the link between post-usage evaluations and the app success. Additionally, it also empirically validated the link between post-usage evaluations and app success, elucidating the role of quality factors. The insights can empower app developers and marketers to enhance user experience and attain market dominance.

Exploring Technology- and Sensor-Driven Trends in Education: A Natural-Language-Processing-Enhanced Bibliometrics Study

Over the last decade, there has been a large amount of research on technology-enhanced learning (TEL), including the exploration of sensor-based technologies. This research area has seen significant contributions from various conferences, including the European Conference on Technology-Enhanced Learning (EC-TEL). In this research, we present a comprehensive analysis that aims to identify and understand the evolving topics in the TEL area and their implications in defining the future of education. To achieve this, we use a novel methodology that combines a text-analytics-driven topic analysis and a social network analysis following an open science approach. We collected a comprehensive corpus of 477 papers from the last decade of the EC-TEL conference (including full and short papers), parsed them automatically, and used the extracted text to find the main topics and collaborative networks across papers. Our analysis focused on the following three main objectives: (1) Discovering the main topics of the conference based on paper keywords and topic modeling using the full text of the manuscripts. (2) Discovering the evolution of said topics over the last ten years of the conference. (3) Discovering how papers and authors from the conference have interacted over the years from a network perspective. Specifically, we used Python and PdfToText library to parse and extract the text and author keywords from the corpus. Moreover, we employed Gensim library Latent Dirichlet Allocation (LDA) topic modeling to discover the primary topics from the last decade. Finally, Gephi and Networkx libraries were used to create co-authorship and citation networks. Our findings provide valuable insights into the latest trends and developments in educational technology, underlining the critical role of sensor-driven technologies in leading innovation and shaping the future of this area.

Clustering and Topic Modeling of Verdicts of Narcotics Cases Using Machine Learning

Narcotics are a grave crime that can lead to addiction, loss of consciousness, and even death. Furthermore, narcotics can damage society’s environment. Narcotics criminal cases have been reported widely in Indonesia. The variety of narcotics cases makes it extremely difficult for judges to make decisions. Therefore, it is necessary to study and analyze the judge’s decisions from the data on the narcotics cases. In this study, we propose using a machine learning approach based on K-means clustering method for clustering and analyzing the verdicts on narcotics cases to see the trend of the verdicts on narcotics cases. In addition, we also use latent Dirichlet allocation (LDA) topic modeling to study the trend of these narcotics cases. Based on the results of the study using K=3 for clustering, there were three categories of verdicts: decisions with light sentences (less than three years), decisions with moderate sentences (three to six years), and decisions with severe sentences (more than ten years). Furthermore, using topic modeling based on the LDA method, the top three topics of narcotics cases based on the verdicts were determined, namely: the first topic refers to verdicts where narcotics perpetrators are found guilty; the second topic refers to verdicts with evidence of marijuana-type narcotics; and the third topic refers to verdicts with evidence of methamphetamine-type narcotics.

Geospatial vaccine misinformation risk on social media: Online insights from an English/Spanish natural language processing (NLP) analysis of vaccine-related tweets

BackgroundMisinformation is known to affect norms, attitudes, and intentions to engage with healthy behaviors. Evidence strongly supports that Spanish speakers may be particularly affected by misinformation and its outcomes, yet current insights into the scope and scale of misinformation is primarily ethnocentric, with greater emphasis on English-language design. ObjectiveThis study applies Natural Language Processing (NLP) to analyze a corpus of English/Spanish tweets about vaccines, broadly defined, for misinformation indicators. MethodsWe analyzed NEnglish = 247,140 and NSpanish = 104,445 tweets using Latent Dirichlet Allocation (LDA) topic models with Coherence score calculation (model fit) with a Mallet adjustment (topic optimization). We used informal coding to name computer-identified topics and compare misinformation scope and scale between languages. ResultsThe LDA analysis yielded a 12-topic solution for English and a 14-topic solution for Spanish. Both corpora contained overlapping misinformation, including uncertainty of research guiding policy recommendations or standing in support of antivax movements. However, the Spanish data were positioned in a global context, where misinformation was directed at government equity and disparate vaccine distribution. ConclusionOur findings support that misinformation is a global issue. However, misinformation may vary depending on culture and language. As such, tailored strategies to combat misinformation in digital planes are strongly encouraged.

Changing or unchanging Chinese attitudes toward ride-hailing? A social media analytics perspective from 2018 to 2021

Despite the global popularity of ride-hailing services, frequent events in recent years have caused the public to query and even refuse to adopt ride-hailing. The public’s attitudes are the decisive factor affecting ride-hailing development. Previous studies identified the public’s attitude toward ride-hailing at a one-time point through questionnaire design without monitoring changes in the public’s attitude. This study aims to analyze the evolution and reasons for the public’s attitudes toward ride-hailing in terms of trend lines and significant events. We collected 114,361 comments across social media platforms (Sina Weibo and Tik Tok) on Chinese ride-hailing events from May 2018 to September 2021. Through sentiment analysis to investigate the evolution of the public’s attitudes toward ride-hailing, we identified four significant events that led to significant changes in public attitudes. We then employed Latent Dirichlet Allocation (LDA) topic model and text network analysis to examine the comments in these significant events to understand the exact reasons for the change in attitudes. The results indicate that the public’s attitude variations are closely linked with social events. Meanwhile, among all topics, Platform and Safety are constant public concerns. Other topics (e.g., Publicity, Government, and Pity) of public concern are related to significant events. The gap between perceived and actual security toward ride-hailing services seems to exist. We also found gender discrimination against females in ride-hailing events. The findings provide valuable insights into the future development of ride-hailing.

Perspektif Opini Pelanggan pada Aplikasi MyPertamina menggunakan Metode Latent Dirichlet Allocation (LDA)

Fluctuations in world oil prices are one of the major factors affecting the country's economic growth, including Indonesia. The government issued a fuel subsidy program, but the program was used by the wrong target and caused the government budget to swell. The solution is to provide programs to the right targets, the government created the MyPertamina application. MyPertamina's application reviews need to be further analyzed and researched to find out the customer's perspective on the application and help the government improve its work program. This study proposes the LDA (Latent Dirichlet Allocation) topic modeling method to analyze user reviews of the MyPertamina application. The methodology used in this research is starting with a literature study, data collection, data preprocessing, sentiment analysis, and topic modeling using LDA. The results of the analysis show that there are several negative reviews with most reviews being positive. This indicates that the MyPertamina application is a good program and right on target in distributing subsidized fuel. Based on the results of the analysis, the are some suggestions about improving application performance in the registration process and adding payment options through e-wallets other than LinkAja or m-banking. The conclusion of the perspective user, the MyPertamina application is effective in controlling subsidized fuel purchases and several user suggestions need to improve regarding registration and payment.

Sensors in postharvest technologies: Evidence from patent portfolio analysis

The objective of the present study was to provide insight into trends of sensors in postharvest of fresh produce. Patent portfolio of 881 patents obtained through a multistep refinement of the PatSnap patent database was analyzed. Intensive patenting activities started in 2014 with most patents originating from Asia, with China as the leading patenting authority. Latent Dirichlet Allocation topic modelling differentiated existence of three distinct topics, out of which two are related to the application of sensors in (A) produce sorting and packaging along with related processes, and (B) produce storage, respectively. The third topic is related to the development and application of a diversity of sensors for analysis of the fresh produce and storage environment, as well as solutions for the application of sensors in monitoring, data collection and development of prediction models. The analysis of patent portfolio and trends highlights the ongoing and rapid advancement of sensing technologies in fresh produce postharvest, which has a substantial impact on the landscape of postharvest processes. Our findings indicate that these developments are poised to transform existing practices, particularly in quality and safety monitoring. Additionally, they are expected to provide comprehensive datasets that can support the broader integration of artificial intelligence into postharvest processes, ultimately leading to more coherent and efficient supply chains.

Temporal and Emotional Variations in People's Perceptions of Mass Epidemic Infectious Disease After the COVID-19 Pandemic Using Influenza A as an Example: Topic Modeling and Sentiment Analysis Based on Weibo Data.

The COVID-19 pandemic has had profound impacts on society, including public health, the economy, daily life, and social interactions. Social distancing measures, travel restrictions, and the influx of pandemic-related information on social media have all led to a significant shift in how individuals perceive and respond to health crises. In this context, there is a growing awareness of the role that social media platforms such as Weibo, among the largest and most influential social media sites in China, play in shaping public sentiment and influencing people's behavior during public health emergencies. This study aims to gain a comprehensive understanding of the sociospatial impact of mass epidemic infectious disease by analyzing the spatiotemporal variations and emotional orientations of the public after the COVID-19 pandemic. We use the outbreak of influenza A after the COVID-19 pandemic as a case study. Through temporal and spatial analyses, we aim to uncover specific variations in the attention and emotional orientations of people living in different provinces in China regarding influenza A. We sought to understand the societal impact of large-scale infectious diseases and the public's stance after the COVID-19 pandemic to improve public health policies and communication strategies. We selected Weibo as the data source and collected all influenza A-related Weibo posts from November 1, 2022, to March 31, 2023. These data included user names, geographic locations, posting times, content, repost counts, comments, likes, user types, and more. Subsequently, we used latent Dirichlet allocation topic modeling to analyze the public's focus as well as the bidirectional long short-term memory model to conduct emotional analysis. We further classified the focus areas and emotional orientations of different regions. The research findings indicate that, compared with China's western provinces, the eastern provinces exhibited a higher volume of Weibo posts, demonstrating a greater interest in influenza A. Moreover, inland provinces displayed elevated levels of concern compared with coastal regions. In addition, female users of Weibo exhibited a higher level of engagement than male users, with regular users comprising the majority of user types. The public's focus was categorized into 23 main themes, with the overall emotional sentiment predominantly leaning toward negativity (making up 7562 out of 9111 [83%] sentiments). The results of this study underscore the profound societal impact of the COVID-19 pandemic. People tend to be pessimistic toward new large-scale infectious diseases, and disparities exist in the levels of concern and emotional sentiments across different regions. This reflects diverse societal responses to health crises. By gaining an in-depth understanding of the public's attitudes and focal points regarding these infectious diseases, governments and decision makers can better formulate policies and action plans to cater to the specific needs of different regions and enhance public health awareness.