Search Results (239)

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. Full article

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. Full article

Haze is a phenomenon caused by excessive PM2.5 (air-borne particulate matter having a diameter of fewer than 2.5 μm) and other pollutants and results from the interaction between specific climatic conditions and human activities. It significantly impacts human health, transportation, and the natural environment and has aroused widespread concern. However, the influence of haze on human mental health, being hidden and indirect, is often overlooked. When haze pollution occurs, people express their feelings and concerns about haze events on media such as Weibo. At present, few studies focus on haze public opinion, as well as the changing trends in people’s discussion of haze since its emergence, which is of great significance for haze response and resource management. Based on the perspective of topic analysis, this study explores the psychological impact of haze on people by exploring the feelings of netizens in haze public opinion and investigates the evolution of people’s concerns based on long-term public opinion data. In this study, seven typical provinces and cities in China with severe haze pollution were selected as the research area. Based on data on the “haze” theme from Weibo from 2013 to 2019, first, the microblog posts were preprocessed, and the keyword co-word network was constructed. Second, the Louvain algorithm was used to detect the topic community. Based on this, the cosine similarity was calculated to realize the temporal evolution analysis of topics. The results show that with the development and change in haze pollution, the content and intensity of the topics netizens pay attention to have changed, including five types: merger, split, survival, transformation, and rebirth/extinction. People’s attention to haze shows obvious spatial differences, and it is related to the degree of haze pollution, which is bipolar. Areas with severe haze tend to pay more attention to haze itself and its influence, while areas with light haze pay more attention to haze control. The research results can provide valuable insights for governments and relevant departments in guiding public opinion and resource allocation. Full article

In recent years, new media have exacerbated the complexity of online public opinion scenarios through fragmentation of information, diversification of public opinion, rapid diffusion of public opinion, and concealment of information sources, which have posed several serious challenges to the benign development of online public opinion ecosystems. Therefore, based on diversified public opinion scenarios, we study the interaction between information dissemination and the evolution of group opinions and the dissemination laws to solve the problem of imprecise grasping of the dissemination laws in complex public opinion scenarios. Facing the two-way interaction between online platforms and real society, we constructed a coupled online–offline viewpoint evolution dynamics model, which considers factors such as the user subject level and the network environment level, and combines viewpoint dynamics theory with information dissemination dynamics theory. Based on the real case of dual interaction between online and offline, we carry out the construction of a two-layer coupling network and numerical fitting comparison experiments to study the synergistic and penetration mechanism of public opinion in both online and offline multi-spaces. Based on parametric analysis experiments, the influence of different factors on communication indicators is mined, and the driving effect of the viewpoint environment of offline communication on online public opinion is studied, which reveals the objective role of multi-factors on the law of intralayer communication, cross-network communication, and viewpoint evolution, and provides strategic suggestions for the comprehensive management of public opinion in online–offline large-scale mass incidents. Full article

Salt cavern storage, characterized by its safety, stability, large scale, economic viability, and efficiency, stands out as a cost-effective and relatively secure method for large-scale petroleum reserves. This paper provides an overview of the current development status of salt cavern storage technologies both domestically and internationally, analyzes the advantageous conditions and numerous challenges faced by salt cavern Strategic Petroleum Reserve (SPR) storage in China, and forecasts the development trends of this technology. The conclusions indicate that China possesses all of the necessary conditions for the development of salt cavern storage. Moreover, utilizing the Analytical Hierarchy Process (AHP), a macro suitability hierarchical evaluation system is constructed for the site selection and construction of salt cavern storage facilities. This system quantifies various site selection indicators, integrating expert opinions and findings from relevant theoretical research to establish grading standards for the suitability indices of salt cavern storage construction. Applied to the site evaluation of salt cavern storage at the Jintan Salt Mine in Jiangsu, the results indicate its high suitability for storage construction, making it an ideal location for establishing such facilities. The evaluation results are consistent with expert opinions, demonstrating the rationality of this method. Full article

Mining is a high-risk industry where occupational accidents are common due to its complex nature. Therefore, providing a more holistic and dynamic risk assessment framework is essential to identify and minimize the potential risks and enhance safety measures. Unfortunately, traditional risk assessment methods have limitations and shortcomings, such as uncertainty, differences in experience backgrounds, and insufficiency to articulate the opinions of experts. In this paper, a novel risk assessment method precisely for such cases in the mining sector is proposed, applied, and compared with traditional methods. The objective of this study is to determine the risk scores of Turkish Coal Enterprises, based on non-fatal occupational accidents, which operates eight large-scale open-cast coal mine enterprises in Türkiye. The causes of the accidents were categorized into 25 sub-criteria under 6 main criteria. The risk scores for these criteria were computed using the Pythagorean fuzzy Analytical Hierarchy Process (PFAHP) method. The first shift (8–16 h) (0.6341) for the shift category is ranked highest out of the 25 sub-risk factors, followed by maintenance personnel (0.5633) for the occupation category; the open-cast mining area (0.5524) for the area category, the 45–57 age range (0.5279) for employee age category, and the mining machine (0.4247) for the reason category, respectively. The methodologies proposed in this study not only identify the most important risk factors in enterprises, but also provide a mechanism for risk-based rankings of enterprises by their calculated risk scores. The enterprises were risk-based ranked with the fuzzy Technique for Order Preference by Similarity to Ideal Solution (FTOPSIS) method and Paksoy approach based on interval type-2 fuzzy sets (IT2FSs). The findings indicate that the first three risk score rankings of enterprises are the same for both approaches. To examine the consistency of the applied methods, sensitivity analyses were performed. The results of the study also indicate that the proposed approaches are recommended for effective use in the mining sector due to their ease of application compared to other methods and their dynamic nature in the risk assessment process. Full article

This study aims to dynamically mine the demands of hotel consumers. A total of 378,270 online reviews in the cities of Beijing, Chengdu, and Guangzhou in China were crawled using Python. Natural language processing (e.g., opinion mining and the BERT model) and an improved Kano model (containing One-dimensional, Attractive, Indifferent, and Must-be) were utilised to analyse online hotel reviews. The results indicate that the hotel attributes that consumers care about (e.g., Clean, Breakfast, and Front Desk) are dynamically fluctuating, and the attention and satisfaction of corresponding attributes will also change. This study classified consumer demand into eight types across cities and found that it changes over time. In addition, we also found that hotel attributes, satisfaction and attention, and consumer demands vary among different cities. Existing studies of capturing consumer demand are usually time-consuming and static, and the results are subjective. This study compared and analysed the consumer demands of hotels in different cities via a dynamic perspective, and used hybrid methods to improve the granularity of the analysis, expanding the general applicability of the Kano model. Hotel managers can refer to the results of this article to allocate resources for improvement and create competitive hotel services. Full article

With the development of the Internet, the oversight of research integrity issues has extended beyond the scientific community to encompass the whole of society. If these issues are not addressed promptly, they can significantly impact the research credibility of both institutions and scholars. This article proposes a text convolutional neural network based on SMOTE to identify short texts of potential public opinion events related to suspected scientific integrity issues from common short texts. The SMOTE comprehensive sampling technique is employed to handle imbalanced datasets. To mitigate the impact of short text length on text representation quality, the Doc2vec embedding model is utilized to represent short text, yielding a one-dimensional dense vector. Additionally, the dimensions of the input layer and convolution kernel of TextCNN are adjusted. Subsequently, a short text event extraction model based on TF-IDF and TextRank is proposed to extract crucial information, for instance, names and research-related institutions, from events and facilitate the identification of potential public opinion events related to suspected scientific integrity issues. Results of experiments have demonstrated that utilizing SMOTE to balance the dataset is able to improve the classification results of TextCNN classifiers. Compared to traditional classifiers, TextCNN exhibits greater robustness in addressing the problems of imbalanced datasets. However, challenges such as low information content, non-standard writing, and polysemy in short texts may impact the accuracy of event extraction. The framework can be further optimized to address these issues in the future. Full article

In the current fraught relationship between nature and human society, land conservation and utilization have spawned intensive conflicts that require mediation. The present study explores this issue of coordination between nature and society in a fragile watershed located in northeastern Taiwan: the Lanyang River Watershed. Land zoning in this area has been historically classified and legally implemented, and additional development is constrained by an application review process. Currently, additional land utilization is still in demand in sensitive areas of this watershed, such as for mining and tilling. Due to the geographically, geologically, and climatically fragile characteristics of the watershed, the hillside residents have benefited from the conservation of nature with comprehensive ecosystem services but are at the forefront of the loss of life and property caused by forest ecosystem degradation. They are one of the key local resource users and main stakeholders. Applying the contingent valuation method to survey the hillside residents, the present study assessed the economic value they receive from the comprehensive ecosystem services offered by the natural forest ecosystems. Their opinions are explored using a survey on their awareness of ecosystem damage, their opinions on damage compensation, and on the feasible compensation channels for damage. As the study results ascertained the high value of the comprehensive ecosystem services continuously delivered by the conserved forest ecosystem, the study affirmed that conservation in the area classified and zoned as sensitive is an economic beneficial policy. With a high regard for ecosystem services and awareness of the impact of degradation and of the general agreement for the feasibility of channels of damage compensation, the continuity of conservation for these comprehensive ecosystem services is the preferred strategy for the local hillside residents. To emphasize this further, the opinions of the local community at the intersection of nature and society, where there is a delineated land zoning framework, strongly favor conservation over intensive resource exploitation and agricultural expansion, making further development an unfavorable strategy. Full article

The existing deep learning-based detection of fake information focuses on the transient detection of news itself. Compared to user category profile mining and detection, transient detection is prone to higher misjudgment rates due to the limitations of insufficient temporal information, posing new challenges to social public opinion monitoring tasks such as fake user detection. This paper proposes a multimodal aggregation portrait model (MAPM) based on multi-model joint representation for social media platforms. It constructs a deep learning-based multimodal fake user detection framework by analyzing user behavior datasets within a time retrospective window. It integrates a pre-trained Domain Large Model to represent user behavior data across multiple modalities, thereby constructing a high-generalization implicit behavior feature spectrum for users. In response to the tendency of existing fake user behavior mining to neglect time-series features, this study introduces an improved network called Sequence Interval Detection Net (SIDN) based on Sequence to Sequence (seq2seq) to characterize time interval sequence behaviors, achieving strong expressive capabilities for detecting fake behaviors within the time window. Ultimately, the amalgamation of latent behavioral features and explicit characteristics serves as the input for spectral clustering in detecting fraudulent users. The experimental results on Weibo real dataset demonstrate that the proposed model outperforms the detection utilizing explicit user features, with an improvement of 27.0% in detection accuracy. Full article

Investigating public attitudes on social media is crucial for opinion mining systems. Stance detection aims to predict the attitude towards a specific target expressed in a text. However, effective neural stance detectors require substantial training data, which are challenging to curate due to the dynamic nature of social media. Moreover, deep neural networks (DNNs) lack explainability, rendering them unsuitable for scenarios requiring explanations. We propose a distantly supervised explainable stance detection framework (DS-ESD), comprising an instruction-based chain-of-thought (CoT) method, a generative network, and a transformer-based stance predictor. The CoT method employs prompt templates to extract stance detection explanations from a very large language model (VLLM). The generative network learns the input-explanation mapping, and a transformer-based stance classifier is trained with VLLM-annotated stance labels, implementing distant supervision. We propose a label rectification strategy to mitigate the impact of erroneous labels. Experiments on three benchmark datasets showed that our model outperformed the compared methods, validating its efficacy in stance detection tasks. This research contributes to the advancement of explainable stance detection frameworks, leveraging distant supervision and label rectification strategies to enhance performance and interpretability. Full article

During the coronavirus disease 2019 (COVID-19) pandemic, non-face-to-face e-commerce has become a significant consumer channel for customers to buy fresh food. However, little is known about customer opinion changes in fresh food e-commerce (FFEC) products and services during COVID-19. This study investigated the changes in expectations and preferences of FFEC customers on products and services before and during the pandemic from online reviews through a text mining approach. We divided the pandemic into two phases, acute and recovery, and found that eight attributes affect customers’ opinions. Some logistic service-related attributes gained customer attention during the acute phase, but product-related attributes gained more attention in the recovery phase. Customers showed a great level of forgiveness on many attributes during the acute phase, but customers’ dissatisfaction was expressed during the recovery phase. Finally, the results of the comparative importance–performance analysis provide improvement strategies for FFEC and help optimize their resource allocation of FFEC and enhance sustainable operation capacity in the case of a crisis. Full article

In the field of education, investigating the relationships between different majors in universities is an important topic in current educational research. The application of social networks from informatics provides new opportunities and potentials for the field of education. Due to the complexity of social interactions, the social network connections surrounding individuals exert a significant influence on their daily decision-making processes. This paper aims to introduce the social network and influence analysis theories from informatics into the field of education, regarding major as a variable, and comparing and analyzing the influence relationships between majors. An empirical study was conducted, involving the collection of questionnaire data on graduates’ evaluations of various aspects of their university experiences across different majors. The evolution of this model follows the DeGroot opinion dynamics with the inclusion of stubborn nodes. By defining leader majors and general majors based on the data and modeling the questionnaire data as the outcome of a discrete random process, an influence matrix is ultimately generated through the opinion dynamic model. Through this modeling approach, we revealed the underlying influence relationships between different disciplines (majors). These findings provide schools with insights to adjust the directions of discipline cultivation, and offer new perspectives and methods for the study of majors in higher education. Full article

The efficiency of natural language processing has improved dramatically with the advent of machine learning models, particularly neural network-based solutions. However, some tasks are still challenging, especially when considering specific domains. This paper presents a model that can extract insights from customer reviews using machine learning methods integrated into a pipeline. For topic modeling, our composite model uses transformer-based neural networks designed for natural language processing, vector-embedding-based keyword extraction, and clustering. The elements of our model have been integrated and tailored to better meet the requirements of efficient information extraction and topic modeling of the extracted information for opinion mining. Our approach was validated and compared with other state-of-the-art methods using publicly available benchmark datasets. The results show that our system performs better than existing topic modeling and keyword extraction methods in this task. Full article

Investigating public attitudes towards social media is crucial for opinion mining systems to gain valuable insights. Stance detection, which aims to discern the attitude expressed in an opinionated text towards a specific target, is a fundamental task in opinion mining. Conventional approaches mainly focus on sentence-level classification techniques. Recent research has shown that the integration of background knowledge can significantly improve stance detection performance. Despite the significant improvement achieved by knowledge-enhanced methods, applying these techniques in real-world scenarios remains challenging for several reasons. Firstly, existing methods often require the use of complex attention mechanisms to filter out noise and extract relevant background knowledge, which involves significant annotation efforts. Secondly, knowledge fusion mechanisms typically rely on fine-tuning, which can introduce a gap between the pre-training phase of pre-trained language models (PLMs) and the downstream stance detection tasks, leading to the poor prediction accuracy of the PLMs. To address these limitations, we propose a novel prompt-based stance detection method that leverages the knowledge acquired using the chain-of-thought method, which we refer to as PSDCOT. The proposed approach consists of two stages. The first stage is knowledge extraction, where instruction questions are constructed to elicit background knowledge from a VLPLM. The second stage is the multi-prompt learning network (M-PLN) for knowledge fusion, which learns model performance based on the background knowledge and the prompt learning framework. We evaluated the performance of PSDCOT on publicly available benchmark datasets to assess its effectiveness in improving stance detection performance. The results demonstrate that the proposed method achieves state-of-the-art results in in-domain, cross-target, and zero-shot learning settings. Full article