Search Results (333)

This study examines how Environmental, Social, and Governance (ESG) reporting is communicated and perceived on YouTube. A dataset of 553 relevant videos and 5060 user comments was extracted on 2 April 2025 ranging between 2014 and 2025, and sentiment, topic, and stance analyses were applied to both transcripts and comments. The majority of video content strongly endorsed ESG reporting, emphasizing themes such as transparency, regulatory compliance, and financial performance. In contrast, viewer comments revealed diverse stances, including skepticism about methodological inconsistencies, accusations of greenwashing, and concerns over politicization. Notably, statistical analysis showed minimal correlation between video sentiment and audience sentiment, suggesting that user perceptions are shaped by factors beyond the tone of the videos themselves. These findings underscore the need for more rigorous ESG frameworks, enhanced standardization, and proactive stakeholder engagement strategies. The study highlights the value of online platforms for capturing stakeholder feedback in real time, offering practical insights for organizations and policymakers seeking to strengthen ESG disclosure and communication. Full article

This paper explores emotional analysis in Hebrew texts, focusing on improving machine learning techniques for depression detection by integrating psychological feature lexicons. Hebrew’s complex morphology makes emotional analysis challenging, and this study seeks to address that by combining traditional machine learning methods with sentiment lexicons. The dataset consists of over 350,000 posts from 25,000 users on the health-focused social network “Camoni” from 2010 to 2021. Various machine learning models—SVM, Random Forest, Logistic Regression, and Multi-Layer Perceptron—were used, alongside ensemble techniques like Bagging, Boosting, and Stacking. TF-IDF was applied for feature selection, with word and character n-grams, and pre-processing steps like punctuation removal, stop word elimination, and lemmatization were performed to handle Hebrew’s linguistic complexity. The models were enriched with sentiment lexicons curated by professional psychologists. The study demonstrates that integrating sentiment lexicons significantly improves classification accuracy. Specific lexicons—such as those for negative and positive emojis, hostile words, anxiety words, and no-trust words—were particularly effective in enhancing model performance. Our best model classified depression with an accuracy of 84.1%. These findings offer insights into depression detection, suggesting that practitioners in mental health and social work can improve their machine learning models for detecting depression in online discourse by incorporating emotion-based lexicons. The societal impact of this work lies in its potential to improve the detection of depression in online Hebrew discourse, offering more accurate and efficient methods for mental health interventions in online communities. Full article

In the sentiment analysis of online comments, all comments are generally considered as a whole, with little attention paid to the inevitable emotional fluctuations in comments caused by changes in product value. In this study, we analyzed the online comments related to apple sales on Chinese e-commerce platforms, and combined topic models, sentiment analysis, and transfer learning to investigate the impact of product value on emotional fluctuations in online comments. We found that as product value changes, the sentiment of online comments undergoes significant fluctuations. Among the prominent negative sentiments, the proportion of topics influenced by product value significantly increases as product value decreases. This study reveals the correlation between changes in product value and sentiment fluctuations in online comments, and demonstrates the necessity of classifying online comments based on product value as an indicator. This study offers a novel perspective for enhancing sentiment analysis by incorporating product value dynamics. Full article

Sentiment analysis is a sub-field within Natural Language Processing (NLP), concentrating on the extraction and interpretation of user sentiments or opinions from textual data. Despite significant advancements in the analysis of online content, a continuing challenge persists in the handling of sentiment datasets that are high-dimensional and frequently include substantial amounts of irrelevant or redundant features. Existing methods to address this issue typically rely on dimensionality reduction techniques; however, their effectiveness in removing irrelevant features and managing noisy or redundant data has been inconsistent. This research seeks to overcome these challenges by introducing an innovative methodology that integrates ensemble feature selection techniques based on information gain with feature hashing. Our proposed approach aims to enhance the conventional feature selection process by synergistically combining these two strategies to more effectively tackle the issues of irrelevant features, noisy classes, and redundant data. The novel integration of information gain with feature hashing facilitates a more precise and strategic feature selection process, resulting in improved efficiency and effectiveness in sentiment analysis tasks. Through comprehensive experimentation and evaluation, we demonstrate that our proposed method significantly outperforms baseline approaches and existing techniques across a wide range of scenarios. The results indicate that our method offers substantial advancements in managing high-dimensional sentiment data, thereby contributing to more accurate and reliable sentiment analysis outcomes. Full article

This paper explores responses to online coverage of an avian tracking project. Researchers attached novel trackers to a small group of wild magpies (Gymnorhina tibicen). These were subsequently removed by conspecifics, an example of ‘rescue behavior’ that was recounted in several media outlets. Online comments on three articles, from across the political spectrum (the Conversation, UK Guardian, and UK Daily Mail), were selected for thematic analysis. The resulting 680 comments were analyzed qualitatively and quantitatively to uncover predominant themes and the overall balance of positive and negative sentiments expressed about this tagging project or wildlife tagging generally. Topics occurring most frequently were themed into three interrelated areas: (1) sharing personal feelings and experiences, (2) comparing the merits of different species, and (3) sharing knowledge and opinion. Twenty-one percent (21%) of respondents expressed an opinion on the ethics of wildlife tagging. In the Daily Mail and Guardian, this opinion was more likely to be negative towards the use of tags. Opinion was more balanced for readers of the Conversation’s article. Willingness to comment on online news is low, and readers of this story were not asked directly for their opinion. Nevertheless, the data here illustrate some public perceptions of wildlife tagging, and there was a clear negative reaction from many responders. Widening the means through which people can engage with animal science has the potential to advance discussions around research ethics and animal welfare. Reactions to this story expose important questions for scientists seeking to engage with, and convince, the public of the merits of their work. Full article

With the rapid development of the Internet, the speed and scope of sudden public events disseminating in cyberspace have grown significantly. Current methods of quantifying public opinion heat often neglect emotion-driven factors and user interaction behaviors, making it difficult to accurately capture fluctuations during dissemination. To address these issues, first, this study addressed the complexity of interaction behaviors by introducing an approach that employs the information gain ratio as a weighting indicator to measure the “interaction heat” contributed by different interaction attributes during event evolution. Second, this study built on SnowNLP and expanded textual features to conduct in-depth sentiment mining of large-scale opinion texts, defining the variance of netizens’ emotional tendencies as an indicator of emotional fluctuations, thereby capturing “emotional heat”. We then integrated interactive behavior and emotional conflict assessment to achieve comprehensive heat index to quantification and dynamic evolution analysis of online public opinion heat. Subsequently, we used Hodrick–Prescott filter to separate long-term trends and short-term fluctuations, extract six key quantitative features (number of peaks, time of first peak, maximum amplitude, decay time, peak emotional conflict, and overall duration), and applied K-means clustering algorithm (K-means) to classify events into three propagation patterns, which are extreme burst, normal burst, and long-tail. Finally, this study conducted ablation experiments on critical external intervention nodes to quantify the distinct contribution of each intervention to the propagation trend by observing changes in the model’s goodness-of-fit ($R^2$) after removing different interventions. Through an empirical analysis of six representative public opinion events from 2024, this study verified the effectiveness of the proposed framework and uncovered critical characteristics of opinion dissemination, including explosiveness versus persistence, multi-round dissemination with recurring emotional fluctuations, and the interplay of multiple driving factors. Full article

With the rapid advancement of information technology and the increasing maturity of online shopping platforms, cross-border shopping has experienced rapid growth. Online consumer reviews, as an essential part of the online shopping process, have become a vital way for merchants to obtain user feedback and gain insights into market demands. The research employs Python tools (Jupyter Notebook 7.0.8) to analyze the 14,078 pieces of review text data from the top four best-selling products in a certain product category on a certain cross-border e-commerce platform. By applying social network analysis, constructing LDA (Latent Dirichlet Allocation) topic models, and establishing LSTM (Long Short-Term Memory) sentiment classification models, the topics and sentiment distribution of the review set are obtained, and the evolution trends of topics and sentiments are analyzed according to different periods. The research finds that in the overall review set, consumers’ focus is concentrated on five aspects: functional features, quality and cost-effectiveness, usage effectiveness, post-purchase support, and design and assembly. In terms of changes in review sentiments, the negative proportion of the topics of functional features and usage effects is still relatively high. Given the above, this study integrates the 4P and 4C theories to propose strategies for enhancing the marketing capabilities of cross-border e-commerce in the context of digital cross-border operations, providing theoretical and practical marketing insights for cross-border e-commerce enterprises. Full article

Ting, Tai, Lou, and Ge are types of ancient buildings that represent traditional Chinese architecture and culture. They are primarily constructed using mortise and tenon joints, complemented by brick and stone foundations, showcasing traditional architectural craftsmanship. However, research aimed at conserving, inheriting, and rejuvenating these buildings is limited, despite their status as Provincial Cultural Relic Protection Units of China. Therefore, the aim of this study was to reveal the spatial distribution of Ting, Tai, Lou, and Ge buildings across China, as well as the factors driving differences in their spatial distribution. Tourist experiences and building popularity were also explored. The spatial analysis method (e.g., Standard deviation ellipse and Geographic detector), Word cloud generation, and sentiment analysis, which uses Natural Language Processing techniques to identify subjective emotions in text, were applied to investigated the research issues. The key findings of this study are as follows. The ratio of Ting, Tai, Lou, and Ge buildings in Southeast China to that in Northwest China divided by the “Heihe–Tengchong” Line, an important demographic boundary in China with the ratio of permanent residents in the two areas remaining stable at 94:6, was 94.6:5.4. Geographic detector analysis revealed that six of the seven natural and socioeconomic factors (topography, waterways, roads, railways, population, and carbon dioxide emissions) had a significant influence on the spatial heterogeneity of these cultural heritage buildings in China, with socioeconomic factors, particularly population, having a greater influence on building spatial distributions. All seven factors (including the normalized difference vegetation index, an indicator used to assess vegetation health and coverage) were significant in Southeast China, whereas all factors were non-significant in Northwest China, which may be explained by the small number of buildings in the latter region. The average rating scores and heat scores for Ting, Tai, Lou, and Ge buildings were 4.35 (out of 5) and 3 (out of 10), respectively, reflecting an imbalance between service quality and popularity. According to the percentages of positive and negative reviews, Lou buildings have much better tourism services than other buildings, indicating a need to improve services to attract more tourists to Ting, Tai, and Ge buildings. Four main types of words were used with high frequency in the tourism reviews collected form Ctrip, a popular online travel platform in China: (1) historical stories; (2) tourism; (3) culture; and (4) cities/provinces. Ting and Tai buildings showed similar word clouds, as did Lou and Ge buildings, with only the former including historical stories. Conversely, landmark was a high-frequency word only in the reviews of Lou and Ge buildings. Specific suggestions were proposed based on the above findings to promote tourism and revive ancient Chinese architecture. Full article

This research focuses on developing a sentiment-based system to analyze public opinion on electromagnetic radiation in online networks. Issues related to EMR, such as the NIMBY effect and negative public sentiment, can lead to health crises, social conflicts, and challenges in decision-making. This study addresses limitations in existing research, including inaccurate data collection and a lack of systematic analysis. By incorporating Jieba Chinese word segmentation technology, this study introduces an innovative data collection method based on topic similarity, significantly improving data accuracy. Additionally, this research establishes a comprehensive public opinion analysis framework that integrates user follower counts, geographical distribution, and interaction data. This framework facilitates the identification of sources of negative sentiment and the development of effective response strategies. As a case study, the dissemination patterns of EMR-related public opinion on Weibo are analyzed, focusing on group sentiment and social interaction. The proposed system achieves a 65.85% improvement in data collection accuracy, demonstrating its effectiveness. Furthermore, this study provides actionable recommendations for relevant departments and governments to monitor, analyze, and respond to EMR-related public opinion. By enhancing decision-making and protecting public interests, this study highlights the role of technology in improving social governance and substantial development. Full article

Due to the rapid proliferation of social media and online reviews, the accurate identification and classification of controversial texts has emerged as a significant challenge in the field of natural language processing. However, traditional text-classification methodologies frequently encounter critical limitations, such as feature sensitivity and inadequate generalization capabilities. This results in a notably suboptimal performance when confronted with diverse controversial content. To address these substantial limitations, this paper proposes a novel controversial text-detection framework based on stacked ensemble learning to enhance the accuracy and robustness of text classification. Firstly, considering the multidimensional complexity of textual features, we integrate comprehensive feature engineering, i.e., encompassing word frequency, statistical metrics, sentiment analysis, and comment tree structure features, as well as advanced feature selection methodologies, particularly lassonet, i.e., a neural network with feature sparsity, to effectively address dimensionality challenges while enhancing model interpretability and computational efficiency. Secondly, we design a two-tier stacked ensemble architecture, which not only combines the strengths of multiple machine learning algorithms, e.g., gradient-boosted decision tree (GBDT), random forest (RF), and extreme gradient boosting (XGBoost), with deep learning models, e.g., gated recurrent unit (GRU) and long short-term memory (LSTM), but also implements the support vector machine (SVM) for efficient meta-learning. Furthermore, we systematically compare three hyperparameter optimization algorithms, including the sparrow search algorithm (SSA), particle swarm optimization (PSO), and Bayesian optimization (BO). The experimental results demonstrate that the SSA exhibits a superior performance in exploring high-dimensional parameter spaces. Extensive experimentation across diverse topics and domains also confirms that our proposed methodology significantly outperforms the state-of-the-art approaches. Full article

Sentiment analysis (SA) analyzes online data to uncover insights for better decision-making. Conventional text SA techniques are effective and easy to understand but encounter difficulties when handling sparse data. Deep Neural Networks (DNNs) excel in handling data sparsity but face challenges with high-dimensional, noisy data. Incorporating rich domain semantic and sentiment knowledge is crucial for advancing sentiment analysis. To address these challenges, we propose an innovative hybrid sentiment analysis approach that combines established DNN models like RoBERTA and BiGRU with an attention mechanism, alongside traditional feature engineering and dimensionality reduction through PCA. This leverages the strengths of both techniques: DNNs handle complex semantics and dynamic features, while conventional methods shine in interpretability and efficient sentiment extraction. This complementary combination fosters a robust and accurate sentiment analysis model. Our model is evaluated on four widely used real-world benchmark text sentiment analysis datasets: MR, CR, IMDB, and SemEval 2013. The proposed hybrid model achieved impressive results on these datasets. These findings highlight the effectiveness of this approach for text sentiment analysis tasks, demonstrating its ability to improve sentiment analysis performance compared to previously proposed methods. Full article

Detecting hate speech in social media is challenging due to its rarity, high-dimensional complexity, and implicit expression via sarcasm or spelling variations, rendering linear models ineffective. In this study, the SVM (Support Vector Machine) algorithm is used to map text features from low-dimensional to high-dimensional space using kernel function techniques to meet complex nonlinear classification challenges. By maximizing the category interval to locate the optimal hyperplane and combining nuclear techniques to implicitly adjust the data distribution, the classification accuracy of hate speech detection is significantly improved. Data collection leverages social media APIs (Application Programming Interface) and customized crawlers with OAuth2.0 authentication and keyword filtering, ensuring relevance. Regular expressions validate data integrity, followed by preprocessing steps such as denoising, stop-word removal, and spelling correction. Word embeddings are generated using Word2Vec’s Skip-gram model, combined with TF-IDF (Term Frequency–Inverse Document Frequency) weighting to capture contextual semantics. A multi-level feature extraction framework integrates sentiment analysis via lexicon-based methods and BERT for advanced sentiment recognition. Experimental evaluations on two datasets demonstrate the SVM model’s effectiveness, achieving accuracies of 90.42% and 92.84%, recall rates of 88.06% and 90.79%, and average inference times of 3.71 ms and 2.96 ms. These results highlight the model’s ability to detect implicit hate speech accurately and efficiently, supporting real-time monitoring. This research contributes to creating a safer online environment by advancing hate speech detection methodologies. Full article

This study investigates how review inconsistency influences perceived helpfulness in online restaurant reviews both in ratings and specific aspects of service attributes. Drawing on 106,464 Yelp reviews spanning 666 restaurants, we employed aspect-based sentiment analysis and Tobit regression to capture not only rating inconsistencies but also differences in sentiment toward décor, taste, service, and price. Results indicate that rating inconsistency negatively affects review helpfulness, suggesting that highly divergent ratings reduce credibility. However, aspect inconsistency shows mixed effects. Discrepancies in décor and taste positively influence perceived helpfulness by offering novel information, whereas service-related inconsistencies diminish review helpfulness, due to heightened consumer sensitivity to possible service failures. Reviewer expertise further strengthens the negative influence of inconsistency as readers expect experienced reviewers to provide objective feedback. These findings extend current research by shifting the analytical lens from individual reviews to sets of reviews, thereby capturing the relational dynamics that shape consumers’ perceptions of review credibility. The results also highlight the importance of analyzing review content by specific aspects to uncover nuanced effects. Practically, platforms can benefit from grouping reviews by attributes and alerting users to noteworthy inconsistencies, facilitating more informed consumer decision-making. Full article

In the digital era, user-generated online reviews serve as a valuable resource for understanding visitor experiences in cultural institutions. This study analyses sentiments and thematic trends in TripAdvisor reviews of mountain museums, using Latent Dirichlet Allocation topic modelling and sentiment analysis. A dataset of 2157 reviews from ten museums was classified into local and non-local perspectives, revealing significant differences in visitor expectations. Findings indicate that local visitors prioritize historical authenticity and educational value, whereas non-local visitors emphasize aesthetic appeal, interactivity, and cultural immersion. Sentiment analysis highlights generally positive perceptions, with business travellers and groups of friends reporting the highest satisfaction levels. Comparative analysis across visitor types reveals distinct engagement patterns, with families valuing child-friendly exhibits, couples seeking cultural enrichment, and solo travellers focusing on intellectual depth. These insights inform strategic recommendations for museum management, including multilingual content, interactive elements, and guided tours dedicated to specific visitor profiles. Despite limitations related to lack of real-time feedback, this research demonstrates the potential of sentiment analysis in enhancing museum experiences. Future studies should integrate multimodal analysis and real-time tracking to further refine visitor experience evaluation. Full article

Hotels are one of the fastest-growing sectors in the tourism industry, and sentiment analysis plays a vital role in improving business performance and supporting sustainable practices. This paper proposes a novel framework combining topic mining and aspect-based sentiment analysis to examine 29,334 hotel reviews in Henan province in China, with the aim of informing strategies for sustainable hotel development. Our results reveal six key attributes of customer concern, particularly emphasizing family experiences, which reflect Henan’s appeal as a family tourism destination. Additionally, we uncover sentiment quadruples, including categories, aspect terms, opinion terms, and polarities, thus enabling a dual-dimensional evaluation of factors influencing customer satisfaction. The results reveal that service mainly influences overall category-level satisfaction, while bed, front desk, and breakfast primarily drive aspect-level satisfaction. This study provides valuable insights into customer feedback, offering empirical support for optimizing services and guiding the sustainable strategic development of regional hotels. Full article