Investigating Influential COVID-19 Perspectives: A Multifaceted Analysis of Twitter Discourse

Lecture notes in computer science, Год журнала: 2025, Номер unknown, С. 3 - 22

Опубликована: Янв. 1, 2025

Язык: Английский

---

Fusing Deep Learning and Fuzzy Logic for Social Media Influence Assessment

Journal of Cases on Information Technology, Год журнала: 2025, Номер 27(1), С. 1 - 19

Опубликована: Апрель 12, 2025

Focusing on the field of social media influence prediction, this study aims to evaluate efficacy a model that incorporates Long Short-Term Memory Networks (LSTMs) with fuzzy logic. Through experimental comparisons, we found LSTM combined logic performs well in predicting interaction metrics, especially when dealing complex and uncertain data. The design covers datasets from two typical platforms, multiple models are used for comparison, including traditional ARIMA, rule-based models, deep learning such as GRU RNN. results show fusion not only improves prediction accuracy but also demonstrates stable performance improvement under different event categories. In addition, analyzed association between user behavior influence, proposed multi-dimensional approach comprehensively assess tailored enhancement strategies users.

Язык: Английский

---

Comparing Models for Sentiment Analysis of Tweets in Response to Public Health Announcements During the Pandemic

Communications in computer and information science, Год журнала: 2025, Номер unknown, С. 153 - 166

Опубликована: Янв. 1, 2025

Язык: Английский

---

BERT-Based Deep Learning Models for Analyzing Sentiments of COVID-19-Related Social Media Tweets

Advances in computational intelligence and robotics book series, Год журнала: 2025, Номер unknown, С. 21 - 36

Опубликована: Фев. 28, 2025

Social media data has become an important tool for understanding public attitudes. All over the world, COVID-19 pandemic impacted people's lives in various ways. People worldwide utilize social to express their thoughts and feelings about pandemic. Because of diversity Twitter posts, researchers analyze sentiment examine public's numerous sentiments concerning COVID-19. In meantime, people have shared immunization protection efficacy on sites such as Twitter. Studies demonstrated that it may strengthen ideas impact general opinion. This study focuses analyzing connected using bidirectional encoder representations from transformers (BERT) with random forest (RF), convolutional neural networks (CNN), recurrent CNN (RCNN) classifiers.

Язык: Английский

---

Machine learning-based optimisation algorithms for sentiment analysis: an analysis of the state-of-the-art and upcoming challenges

Journal of Experimental & Theoretical Artificial Intelligence, Год журнала: 2025, Номер unknown, С. 1 - 32

Опубликована: Май 29, 2025

Язык: Английский

---

Sentiment Analysis Method of Epidemic-related Microblog Based on Hesitation Theory

ACM Transactions on Asian and Low-Resource Language Information Processing, Год журнала: 2024, Номер 23(4), С. 1 - 25

Опубликована: Фев. 15, 2024

The COVID-19 pandemic in 2020 brought an unprecedented global crisis. After two years of control efforts, life gradually returned to the pre-pandemic state, but localized outbreaks continued occur. Toward end 2022, resurged China, leading another disruption people’s lives and work. Many pieces information on social media reflected views emotions toward second outbreak, which showed distinct differences compared first outbreak 2020. To explore emotional attitudes at different stages underlying reasons, this study collected microblog data from November 2022 January 2023 June 2020, encompassing Chinese reactions pandemic. Based hesitancy Fuzzy Intuition theory, we proposed a hypothesis: can be integrated into machine learning models select suitable corpora for training, not only improves accuracy also enhances model efficiency. hypothesis, designed hesitancy-integrated model. experimental results demonstrated model’s positive performance self-constructed database. By applying analyze pandemic, obtained their sentiments months. We found that most negative appeared beginning followed by fluctuations influenced events, ultimately showing overall trend. Combining word cloud techniques Latent Dirichlet Allocation (LDA) effectively helped reasons behind changes attitude.

Язык: Английский

---

Modeling approaches for early warning and monitoring of pandemic situations as well as decision support

Frontiers in Public Health, Год журнала: 2022, Номер 10

Опубликована: Ноя. 14, 2022

The COVID-19 pandemic has highlighted the lack of preparedness many healthcare systems against situations. In response, population-level computational modeling approaches have been proposed for predicting outbreaks, spatiotemporally forecasting disease spread, and assessing as well effectiveness (non-) pharmaceutical interventions. However, in several countries, these efforts only limited impact on governmental decision-making so far. light this situation, review aims to provide a critical existing discuss potential future developments.

Язык: Английский

---

Sentiment Analysis Using VADER and Logistic Regression Techniques

Опубликована: Фев. 9, 2023

Язык: Английский

---

Social media and COVID‐19 vaccination hesitancy during pregnancy: a mixed methods analysis

BJOG An International Journal of Obstetrics & Gynaecology, Год журнала: 2023, Номер 130(7), С. 750 - 758

Опубликована: Апрель 20, 2023

Abstract Objective To evaluate the reasons for COVID‐19 vaccine hesitancy during pregnancy. Design We used regular expressions to identify publicly available social media posts from pregnant people expressing at least one reason their decision not accept vaccine. Setting Two platforms – WhatToExpect and Twitter. Sample A total of 945 in (1017 posts) 345 Twitter (435 tweets). Methods annotators manually coded according Scientific Advisory Group Emergencies (SAGE) working group's 3Cs model ( confidence, complacency convenience barriers ). Within each we created subthemes that emerged data. Main Outcome Measures Subthemes were derived people's posting own words. Results Safety concerns most common largely linked perceived speed which was lack data about its safety This led a preference wait until after baby born or take other precautions instead. Complacency surrounded belief they are young healthy already had COVID‐19. Misinformation false efficacy allegations, even conspiracy theories, fed into creating confidence barriers. Convenience (such as availability) uncommon. Conclusion The information this study can be highlight questions, fears hesitations have Highlighting these help public health campaigns improve communication between healthcare professionals patients.

Язык: Английский

---

News Classification and Categorization with Smart Function Sentiment Analysis

International Journal of Intelligent Systems, Год журнала: 2023, Номер 2023, С. 1 - 24

Опубликована: Ноя. 13, 2023

Search engines are tools used to find information on the Internet. Since web has a plethora of websites, engine queries majority active sites and builds database organized according keywords utilized in search. Because this, when user types few descriptive words home page search engine, function lists websites corresponding these keywords. However, there some problems with this approach. For instance, if wants about word Jaguar, most results animals cars. This is polysemic problem that forces always provide popular but not relevant results. article presents study using sentiment technology help news classification categorization improve accuracy. We have introduced smart embedded into tackle issues record determine their sentimentality. Therefore, topic involves several aspects natural language processing (NLP) analysis for classification. A crawler was collect British Broadcasting Corporation (BBC) across Internet, carried out preprocessing text by NLP, applied methods polarity processed data. The sentimentality represents negative, positive, or neutral polarities assigned algorithms. research BBC site different explore news. toolkit (NLTK) BM25 indexed preprocessed patterns database. experimental depict proposed surpassing normal an accuracy rate 85%. Moreover, show negative Sentistrength algorithm. Furthermore, Valence Aware Dictionary sEntiment Reasoner (VADER) best-performing model obtained 85% data collected function.

Язык: Английский

---