Sentiment Analysis Research Articles

Beyond Sentiment Exploring the Dynamics of AIGC-Generated Sports Content and User Engagement on Xiaohongshu

This study explores the impact of AIGC-generated sports content on user sentiment and engagement on Xiaohongshu, a Chinese social media platform.Using MediaCrawler, we collected posts and comments related to sports topics generated by AI. Sentiment analysis was performed using SnowNLP to classify comments as positive or negative, with 57.1% showing positive sentiment and 42.9% negative. Despite the prevalence of positive sentiment, no significant difference in engagement (measured by likes) was observed between positive and negative comments.Temporal analysis revealed that user engagement is event-driven, with spikes in positive sentiment during major sports events. Additionally, word cloud analysis highlighted promotional and spam-like themes, suggesting challenges in content moderation. The interaction patterns showed a skewed distribution, with a small number of highly active users dominating discussions.The findings suggest that timing, relevance, and event alignment are more critical than sentiment polarity in driving engagement.The study provides insights for content creators and platforms on optimizing AIGC strategies through trend alignment and effective user collaboration.

E-learning adoption: a comparative analysis of public sentiments during COVID-19

ABSTRACT The COVID-19 pandemic accelerated e-learning adoption, presenting both opportunities and challenges for educational development, particularly in the context of Information Technology for Development (ITD). This study profiles public sentiments on e-learning to identify key factors influencing IT-enabled education. A text analysis of Tweets from the United States and India posted from March 2020 to January 2022 was conducted using a computer-aided text analysis and natural language processing alongside a content analysis using a machine learning technique. Findings show positive sentiments towards e-learning from both countries, with trust, anticipation, and joy as predominant emotion categories. Themes of strongest importance are students, schools, and education as central to e-learning discussions. The study also uncovers challenges such as the need for internet infrastructure and teacher training in digital pedagogy. These findings contribute to the broader understanding of how information technologies can address educational challenges and promote development in diverse global contexts.

API comparison based on the non-functional information mined from Stack Overflow

When comparing similar APIs, developers tend to distinguish them from the aspects of functional details. At the same time, some important non-functional factors (such as performance, usability, and security) may be ignored or noticed after using the API in the project. This may result in unnecessary errors or extra costs. API-related questions are common on Stack Overflow, and they can give a well-rounded picture of the APIs. This provides us with a rich resource for API comparison. However, although many methods are offered for mining Questions and Answers (Q&As) automatically, they often suffer from two main problems: 1) they only focus on the functional information of APIs; 2) they analyze each text in isolation but ignore the correlations among them. In this paper, we propose an approach based on the pre-training model BERT to mine the non-functional information of APIs from Stack Overflow: we first tease out the correlations among questions, answers as well as corresponding reviews, so that one Q&A can be analyzed as a whole; then, an information extraction model is constructed by fine-tuning BERT with three subtasks—entity identification, aspect classification, and sentiment analysis separately, and we use it to mine the texts in Q&As step by step; finally, we summarize and visualize the results in a user-friendly way, so that developers can understand the information intuitively at the beginning of API selection. We evaluate our approach on 4,456 Q&As collected from Stack Overflow. The results show our approach can identify the correlations among reviews with 90.1% precision, and such information can improve the performance of the data mining process. In addition, the survey on maturers and novices indicates the understandability and helpfulness of our method. Moreover, compared with language models, our method can provide more intuitive and brief information for API comparison in non-functional aspects.

Sentiment Analysis for the Identification of Negative Situations in Soccer Matches Using Social Networks and Artificial Intelligence Techniques

Sentiment Analysis for the Identification of Negative Situations in Soccer Matches Using Social Networks and Artificial Intelligence Techniques

Online Reviews Meet Visual Attention: A Study on Consumer Patterns in Advertising, Analyzing Customer Satisfaction, Visual Engagement, and Purchase Intention

This study aims to bridge the gap between traditional consumer behavior analysis and modern techniques by integrating big data analysis, eye-tracking technology, and survey methods. The researchers considered that understanding consumer behavior is crucial for creating effective advertisements in the digital age. Initially, a big data analysis was performed to identify significant clusters of consumer sentiment from online reviews generated during a recent seasonal promotional campaign. The key factors were identified and grouped into the “Product”, “Model”, “Promo”, and “Effect” categories. Using these clusters as a foundation, an eye-tracking analysis measured visual attention metrics such as the fixation duration and count to understand how the participants engaged with the different advertisement content. Subsequently, a survey assessed the same participants’ purchase intentions and preferences related to the identified clusters. The results showed that the sentiment clusters related to products, promotions, and effects positively impacted the customer satisfaction. The eye-tracking data revealed that advertisements featuring products and models garnered the most visual attention, while the survey results indicated that promotional content significantly influenced the purchase intentions. This multi-step approach delivers an in-depth understanding of the factors that affect customer satisfaction and decision-making, providing valuable information for optimizing marketing strategies in the Korean skincare market. The findings emphasize the importance of integrating consumer sentiment analysis with visual engagement metrics to develop more effective and compelling marketing campaigns.

Exploring Sentiment Analysis for the Indonesian Presidential Election Through Online Reviews Using Multi-Label Classification with a Deep Learning Algorithm

Presidential elections are an important political event that often trigger intense debate. With more than 139 million users, YouTube serves as a significant platform for understanding public opinion through sentiment analysis. This study aimed to implement deep learning techniques for a multi-label sentiment analysis of comments on YouTube videos related to the 2024 Indonesian presidential election. Offering a fresh perspective compared to previous research that primarily employed traditional classification methods, this study classifies comments into eight emotional labels: anger, anticipation, disgust, joy, fear, sadness, surprise, and trust. By focusing on the emotional spectrum, this study provides a more nuanced understanding of public sentiment towards presidential candidates. The CRISP-DM method is applied, encompassing stages of business understanding, data understanding, data preparation, modeling, evaluation, and deployment, ensuring a systematic and comprehensive approach. This study employs a dataset comprising 32,000 comments, obtained via YouTube Data API, from the KPU and Najwa Shihab channels. The analysis is specifically centered on comments related to presidential candidate debates. Three deep learning models—Convolutional Neural Network (CNN), Bidirectional Long Short-Term Memory (Bi-LSTM), and a hybrid model combining CNN and Bi-LSTM—are assessed using confusion matrix, Area Under the Curve (AUC), and Hamming loss metrics. The evaluation results demonstrate that the Bi-LSTM model achieved the highest accuracy with an AUC value of 0.91 and a Hamming loss of 0.08, indicating an excellent ability to classify sentiment with high precision and a low error rate. This innovative approach to multi-label sentiment analysis in the context of the 2024 Indonesian presidential election expands the insights into public sentiment towards candidates, offering valuable implications for political campaign strategies. Additionally, this research contributes to the fields of natural language processing and data mining by addressing the challenges associated with multi-label sentiment analysis.

A New Approach to Assess Sustainable Corporate Reputation with Citizen Comments Using Machine Learning and Natural Language Processing

This study investigates the assessment of sustainable corporate reputation through citizen comments and how it can be measured by sentiment analysis methods based on machine learning and text mining. The research analyses citizen feedback on municipalities in the field of public services and examines their impact on the social reputation of the services provided by municipalities. Support vector machines, one of the machine learning methods, was used for sentiment analysis. In the study, Google Maps comments of the citizens receiving services from the municipality were used. The results of the sentiment analysis reveal that sustainable corporate reputation is directly related to citizen satisfaction and feedback. In this context, municipalities should continuously receive feedback and make strategic improvements based on citizens’ comments to ensure sustainable service quality. Municipalities are especially appreciated by citizens for their fast, effective, and high-quality services. However, some negative comments focus on issues such as the slowness of services, cleaning problems, and staff attitudes, indicating that certain improvements are needed. This feedback emphasises the need for continuous improvement in service quality.

User Sentiment Analysis of the Shared Charging Service for China’s G318 Route

Shared charging services have gained popularity for their contribution to green travel. Accurately identifying the core factors that influence user experience (UX) not only enhances service quality and optimizes user satisfaction, but also promotes the dissemination of green travel concepts. However, the influencing factors and their mechanisms vary significantly across regions, particularly along the Chengdu–Lhasa (G318) route, which features large elevation changes, diverse climatic conditions, rugged terrain, and frequent geological disasters, making the influencing factors particularly complex. This study analyzes comment texts from 38 shared charging stations along the G318 route in the e-Charging APP, totaling 15,214 comments. A comprehensive approach is employed, including high-frequency word analysis, term frequency–inverse document frequency (TF-IDF) comparison, co-occurrence semantic network and co-word matrix feature correlation analysis, Latent Dirichlet Allocation (LDA) topic modeling, and sentiment analysis. This multifaceted analysis explores core themes, user viewpoints, and sentiments in the comments, focusing on users’ perspectives on service quality, usage experience, and environmental impact of the charging stations. The findings indicate that charging speed, service attitude, environment, operational status of hardware and software, and pricing are key factors influencing user sentiment. Users have a high demand for the perfection of supporting facilities of shared charging stations, directly affecting user satisfaction and indirectly influencing the brand image and market competitiveness of enterprises.

Elevating equity: advancing diversity and inclusivity through trialing bias reduction tools in the general internal medicine program resident application process.

Decades of medical data show worse patient outcomes among racial and gender minorities due to implicit, explicit, and structural biases. Increasing representation of marginalized groups among care providers is imperative to help address this. Limited literature exists on bias awareness strategies for interviewers during the selection of applicants to General Internal Medicine (GIM) programs in Canada. This study examines the trial of bias reduction tools to increase interviewers' awareness of implicit biases. The Model of Improvement framework guided the trail of an instructional video, the adapted implicit association test (IAT), and a paper awareness tool (PAT) to increase interviewers' awareness of implicit biases during the University of Alberta's GIM applicant selection. An anonymous online survey was disseminated to physician interviewers. Descriptive statistics (percentages) and a modified sentiment analysis was completed. 10 of 14 interviewers completed the survey. Respondents reported an increased awareness of using bias reduction tools (IAT, 25%; video, 71%; PAT, 67%) to inform them on their implicit biases. The future use of IAT, video, and PAT was supported by 50%, 71%, and 67% of interviewers, respectively. Interviewers prefer the instructional video and PAT over the IAT. Textual responses suggest existing concerns for biases inherent to the interview process yet 70% (7/10) of respondents believe that interviews should have a weighting of 50% towards final ranking of candidates. As many institutions continue to rely on interviews to evaluate candidates, our findings indicate the need for a national study to develop a framework to mitigate inherent biases during interviewing of candidates.

Decoding nationalistic biases in the Grand Ethiopian Renaissance Dam research

ABSTRACT The Nile Basin, supporting 40% of Africa's population, faces a critical challenge in aligning developmental goals with water security needs. The Grand Ethiopian Renaissance Dam (GERD) illustrates this dilemma: it promises substantial energy benefits for Ethiopia but raises downstream water scarcity concerns, particularly in Egypt. This study examines GERD-related research to understand how academic perspectives may influence regional tensions or foster collaboration. Through systematic analysis of 79 articles published between 2011 and 2023, we utilized quantitative sentiment analysis to explore potential biases linked to researcher nationality, methodology, and co-authorship diversity. Findings reveal a statistically significant nationalistic bias, with Egyptian and Ethiopian researchers showing negative and positive sentiments, respectively, suggesting research can inadvertently shape polarized public and political stances on GERD. Importantly, studies with diverse co-authorship displayed reduced bias, underscoring the value of multi-national collaboration in mitigating partiality. Contrary to expectations, qualitative methods did not necessarily correlate with extreme positions, while quantitative methods appeared vulnerable to unintended bias. These insights highlight the need for critically assessing academic objectivity in transboundary resource issues, advocating for interdisciplinary and collaborative research to build mutual trust, which could potentially inform and improve regional diplomatic efforts.

Aspect-based sentiment analysis via dual residual networks with sentiment knowledge

Aspect-based sentiment analysis via dual residual networks with sentiment knowledge

Mobile app review analysis for crowdsourcing of software requirements: a mapping study of automated and semi-automated tools

Mobile app reviews are valuable for gaining user feedback on features, usability, and areas for improvement. Analyzing these reviews manually is difficult due to volume and structure, leading to the need for automated techniques. This mapping study categorizes existing approaches for automated and semi-automated tools by analyzing 180 primary studies. Techniques include topic modeling, collocation finding, association rule-based, aspect-based sentiment analysis, frequency-based, word vector-based, and hybrid approaches. The study compares various tools for analyzing mobile app reviews based on performance, scalability, and user-friendliness. Tools like KEFE, MERIT, DIVER, SAFER, SIRA, T-FEX, RE-BERT, and AOBTM outperformed baseline tools like IDEA and SAFE in identifying emerging issues and extracting relevant information. The study also discusses limitations such as manual intervention, linguistic complexities, scalability issues, and interpretability challenges in incorporating user feedback. Overall, this mapping study outlines the current state of feature extraction from app reviews, suggesting future research and innovation opportunities for extracting software requirements from mobile app reviews, thereby improving mobile app development.

A Comprehensive Review of Sentiment Analysis: From Rule-Based Methods to Deep Learning and Future Directions

A Comprehensive Review of Sentiment Analysis: From Rule-Based Methods to Deep Learning and Future Directions

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.

Policy Gaps and Diverging Perceptions of Effectiveness: An Assessment of Sustainable Permanent Grassland Management in Switzerland

This article focuses on the effectiveness of the Swiss policy mix promoting sustainable permanent grassland (PG) management in the country. We used the Cascade Framework and stakeholder’s sentiment analysis to qualitatively assess propagation pathways for generating policy effectiveness in terms of PGs’ deliverance of ecosystem services (ESs), to ultimately enable sustainable PG management. We employed a mixed-method approach combining a review of governmental documents, formal policies and policy evaluations with semi-structured interviews with Swiss stakeholders. Through this analysis, we identified 16 policy instruments influencing PG management, including 3 regulatory instruments, 11 incentive instruments, and 2 informational instruments. Results showed that these instruments primarily aim to promote sustainable PG management by employing measures targeting the very structure and composition of the landscape. As such, we found gaps in the types of instruments employed, particularly in terms of demand-side policies, which can explain the poor policy outcomes in relation to a number of environmental quality objectives. In parallel, we found that most of the interviewed stakeholders considered Swiss grassland policy as generally effective, mainly because it was perceived as democratic. While this study focuses on Switzerland, its novel conceptual and methodological approach of using the cascade-framework for policy analysis can be applied to other biogeographical regions and socio-economic contexts. Our findings can improve the calibration of future policy instruments to enable land managers and grassland landscape users to restore or maintain PGs in good ecological condition, by targeting mechanisms that can ensure achieving environmental quality objectives while remaining democratically legitimate.

Data augmentation framework with enhanced graph convolutional network for cross-domain aspect-based sentiment analysis

Data augmentation framework with enhanced graph convolutional network for cross-domain aspect-based sentiment analysis

Polarity-aware deep attention network for aspect-based sentiment analysis

Polarity-aware deep attention network for aspect-based sentiment analysis

Screening for Depression Using Natural Language Processing: Literature Review.

Depression is a prevalent global mental health disorder with substantial individual and societal impact. Natural language processing (NLP), a branch of artificial intelligence, offers the potential for improving depression screening by extracting meaningful information from textual data, but there are challenges and ethical considerations. This literature review aims to explore existing NLP methods for detecting depression, discuss successes and limitations, address ethical concerns, and highlight potential biases. A literature search was conducted using Semantic Scholar, PubMed, and Google Scholar to identify studies on depression screening using NLP. Keywords included "depression screening," "depression detection," and "natural language processing." Studies were included if they discussed the application of NLP techniques for depression screening or detection. Studies were screened and selected for relevance, with data extracted and synthesized to identify common themes and gaps in the literature. NLP techniques, including sentiment analysis, linguistic markers, and deep learning models, offer practical tools for depression screening. Supervised and unsupervised machine learning models and large language models like transformers have demonstrated high accuracy in a variety of application domains. However, ethical concerns related to privacy, bias, interpretability, and lack of regulations to protect individuals arise. Furthermore, cultural and multilingual perspectives highlight the need for culturally sensitive models. NLP presents opportunities to enhance depression detection, but considerable challenges persist. Ethical concerns must be addressed, governance guidance is needed to mitigate risks, and cross-cultural perspectives must be integrated. Future directions include improving interpretability, personalization, and increased collaboration with domain experts, such as data scientists and machine learning engineers. NLP's potential to enhance mental health care remains promising, depending on overcoming obstacles and continuing innovation.

Sustainable sentiment analysis on E-commerce platforms using a weighted parallel hybrid deep learning approach for smart cities applications

Sentiment analysis (SA) of several user evaluations on e-commerce platforms can be used to increase customer happiness. This method automatically extracts and identifies subjective data from product evaluations using natural language processing (NLP) and machine learning (ML) methods. These statistics may eventually reveal information on the favourable, neutral, or negative attitudes of the consumer base. Due to its capacity to grasp the complex links between words and phrases in reviews as well as the emotions they imply, deep learning (DL) is very useful for SA tasks. A unique approach termed Weighted Parallel Hybrid Deep Learning-based Sentiment Analysis on E-Commerce Product Reviews (WPHDL-SAEPR) is introduced by the proposed system. Accurately distinguishing between distinct sentiments found in online store reviews is the aim of the WPHDL-SAEPR technique. Additional data pre-processing processes are implemented within the WPHDL-SAEPR architecture to guarantee compatibility. Words are embedded into the paper using the word2vec model, while sentiment is classified using the WPHDL model. The Restricted Boltzmann Machine (RBM) and Singular Value Decomposition (SVD) models are combined in this model. The results of the WPHDL-SAEPR approach’s simulation were assessed using a consumer review database, with the results being emphasized at each stage.

Sentiment analysis in infodemic management: leveraging the eppm Risk communication model

Infodemics are the rapid spread of false or misleading information related to public health emergencies, often through digital platforms. They can cause confusion, fear, and even harm to public health. This study investigates the application of sentiment analysis for infodemic management during disease outbreaks. Leveraging the Extended Parallel Process Model (EPPM) of risk communication, the research aims to categorize rumors based on their perceived threat level (high, medium, or low). Machine learning is employed to analyze infodemic text data collected from two Nigerian states (Oyo and Bauchi) to assess threat appraisal according to the EPPM model. The findings can inform targeted interventions for effective infodemic management before, during, and after outbreak of diseases.