Search

With the popularity of social media, online opinion analysis is becoming more and more widely and deeply used in management studies. Automatically recognizing the sentiment of user reviews is a crucial tool for opinion analysis research. However, previous studies mainly have focused on specific scenarios or algorithms that cannot be directly applied to real-world opinion analysis. To address this issue, we collect a new dataset of user reviews from multiple real-world scenarios such as e-retail, e-commerce, movie reviews, and social media. Due to the heterogeneity and complexity of this multi-scenario review data, we propose a self-distillation contrastive learning method. Specifically, we utilize two EMA (exponential moving average) models to generate soft labels as additional supervision. Additionally, we introduce the prototypical supervised contrastive learning module to reduce the variability of data in different scenarios by pulling in representations of the same class. Our method has proven to be extremely competitive, outperforming other advanced methods. Specifically, our method achieves an 87.44% F1 score, exceeding the performance of current advanced methods by 1.07%. Experimental results, including examples and visualization analysis, further demonstrate the superiority of our method. [ABSTRACT FROM AUTHOR]

An escalating amount of urban waste poses a significant threat to the sustainable growth of cities. Therefore, a waste-sorting policy is crucial for the advancement of humankind. The implementation of a waste-sorting policy relies heavily on public participation to ensure effective governance. This study examines public participation in urban waste-sorting by mining more than 580,000 microblog texts related to waste-sorting from 2012 to 2022, using data from Sina Weibo, China's leading social media platform. My findings indicate that (1) residents' attention to and support for mandatory waste-sorting policies varies by region; (2) widespread public interest stimulates publicity, education, and commercial entertainment related to waste-sorting policies and investment in thematically related sectors; (3) residents in regions with high education and income levels are more likely to generate waste and pay greater attention to waste-sorting policies; and (4) the promotion of waste-sorting policies affects knowledge dissemination. This study combines textual analysis and econometric techniques to offer a fresh perspective on the significance of public participation in promoting waste-sorting policies. It serves as an invaluable resource for governments to implement waste-sorting policies. [ABSTRACT FROM AUTHOR]

Featured Application: Public Opinion Analysis. The emergence of AI Art has ignited extensive debates on social media platforms. Various online communities have expressed their opinions on different facets of AI Art and participated in discussions with other users, leading to the generation of a substantial volume of data. Analyzing these data can provide useful insights into the public's opinions on AI Art, enable the investigation of the origins of conflicts in online debates, and contribute to the sustainable development of AI Art. This paper presents a deep learning-driven framework for analyzing the characteristics of public opinion on the Weibo topic of AI Art. To classify the sentiments users expressed in Weibo posts, the linguistic feature-enhanced pre-training model (LERT) was employed to improve text representation via the fusion of syntactic features, followed by a bidirectional Simple Recurrent Unit (SRU) embedded with a soft attention module (BiSRU++) for capturing the long-range dependencies in text features, thus improving the sentiment classification performance. Furthermore, a text clustering analysis was performed across sentiments to capture the nuanced opinions expressed by Weibo users, hence providing useful insights about different online communities. The results indicate that the proposed sentiment analysis model outperforms common baseline models in terms of classification metrics and time efficiency, and the clustering analysis has provided valuable insights for in-depth analyses of AI Art. [ABSTRACT FROM AUTHOR]

An innovative approach is introduced in this paper to address the challenges in emotional topic interpretation and accuracy in emotional situation assessment. Utilizing large data from social media to improve the accuracy of emotional analysis in online debates, with a specific emphasis on Korean themes. The proposed solution, the Online Topic Emotion Recognition Model (OTSRM), builds upon the foundational Online Latent Dirichlet Allocation (OLDA) model. The OTSRM integrates the concept of emotion intensity and introduces an inventive emotion iteration framework to tackle these issues. Key innovations of the OTSRM include establishing an affective evolution channel by augmenting affective heritability using a ß priori. Additionally, the model generates two critical distribution matrices: one for characteristic words and another for affective words, facilitating a deeper understanding of emotional context within topics. The relative entropy method is employed to discern emotional tones in textual content, calculating maximum emotion values for topic focus within adjacent time segments. Validation experiments using five diverse network event datasets and comparisons to mainstream models demonstrate the OTSRM's effectiveness with emotion recognition accuracy rates of 85.56% and 81.03%. The OTSRM represents significant progress in addressing challenges associated with emotional topic analysis and precise emotional dynamics assessment in Korean social media data. [ABSTRACT FROM AUTHOR]

Analysis of the spatiotemporal distribution of online public opinion topics can help understand the hotspots of public concern. The topic model is employed widely in public opinion topic clustering for social media data. In order to handle topic-clustering of low-quality geospatial social media data, such as microblog data, with short text and timeliness characteristics, this study proposed a Dirichlet multinomial mixture over time (DMMOT) model to cluster microblog topic for public opinion analysis. The DMMOT model assumes that a single document belongs to a single topic, in line with the characteristics of a short text, and it introduces the probability distribution of "topic-time" in the process of topic generation. The model parameter inference process was presented in detail by exploring the Gibbs sampling method. Results generated using the DMMOT model in case study show that the "topic-word" distribution is semantically aggregated within various topics, and "topic-time" distribution clustered within a time window under each topic. Furthermore, the characteristics of the trend of each topic over time are basically consistent with the corresponding trend of topic in reality in terms of content. These indicate that the DMMOT model improves topic clustering for short text to some extent. Furthermore, the DMMOT model performed well in both temporal and spatial analysis of public opinion topics based on microblog data. [ABSTRACT FROM AUTHOR]

Existing methods for monitoring internet public opinion rely primarily on regular crawling of textual information on web pages but cannot quickly and accurately acquire and identify textual information in images and videos and discriminate sentiment. The problems make this a challenging research point for multimodal information detection in an internet public opinion scenario. In this paper, we look at how to dynamically monitor the internet opinion information (mostly images and videos) that different websites post. Based on the most recent advancements in text recognition, this paper proposes a new method of visual multimodal text recognition and sentiment analysis (MTR-SAM) for internet public opinion analysis scenarios. In the detection module, a LK-PAN network with large sensory fields is proposed to enhance the CML distillation strategy, and an RSE-FPN with a residual attention mechanism is used to improve feature map representation. Second, it proposes that the original CTC decoder be replaced with a GTC method to solve earlier problems with text detection at arbitrary rotation angles. Additionally, the performance of scene text detection for arbitrary rotation angles is improved using a sinusoidal loss function for rotation recognition. Finally, the improved sentiment analysis model is used to predict the sentiment polarity of the text recognition results. The experimental results show that the new method proposed in this paper improves recognition speed by 31.77%, recognition accuracy by 10.78% on the video dataset, and the F1 score of the multimodal sentiment analysis model by 4.42% on the self-built internet public opinion dataset (lab dataset). The method proposed provides significant technical support for internet public opinion analysis in multimodal domains. [ABSTRACT FROM AUTHOR]

Public opinion is the abbreviation of public ideas, which is the sum of the beliefs, attitudes, opinions and emotions expressed by the masses about various phenomena in the society. Network public opinion is not only the mapping of public opinion in the network, but also the direct response of social public opinion. Weibo public opinion has gradually become an important medium for people to obtain public opinion in time. The outbreak of Weibo public opinion is very likely to cause social repercussions, which will even affect people's trust in the government and even social stability. The scale of the Internet is expanding, the number of users is increasing, and the applications provided by the Internet are becoming more and more popular. In this context, Weibo public opinion analysis has become an important research topic. Facing the rapid growth of micro blog information, how to obtain the hot topics of micro blog public opinion timely, comprehensively and accurately is the primary problem to be solved in the process of micro blog public opinion analysis. Based on the infectious disease model, this paper proposes an analysis model of Weibo public opinion communication. The speech analysis model is proposed to extract the information for the processing, and the representation of the data is applied to improve the algorithm efficiency. The experimental results compared with the state-of-the-art have proven the satisfactory performance. [ABSTRACT FROM AUTHOR]

In the era of mobile Internet, college students increasingly tend to express their opinions and views through online social media; furthermore, social media influence the value judgments of college students. Therefore, it is vital to understand and analyze university online public opinion over time. In this paper, we propose a data-driven architecture for analysis of university online public opinion. Weibo, WeChat, Douyin, Zhihu and Toutiao apps are selected as sources for collection of public opinion data. Crawler technology is utilized to automatically obtain user data about target topics to form a database. To avoid the drawbacks of traditional methods, such as sentiment lexicon and machine learning, which rely on a priori knowledge and complex handcrafted features, the Word2Vec tool is used to perform word embedding, the LSTM-CFR model is proposed to realize Chinese word segmentation and a convolutional neural network (CNN) is built to automatically extract implicit features in word vectors, ultimately establishing the nonlinear relationships between implicit features and the sentiment tendency of university public opinion. The experimental results show that the proposed model is more accurate than SVM, RF, NBC and GMM methods, providing valuable information with respect to public opinion management. [ABSTRACT FROM AUTHOR]

Existing methods for monitoring internet public opinion rely primarily on regular crawling of textual information on web pages but cannot quickly and accurately acquire and identify textual information in images and videos and discriminate sentiment. The problems make this a challenging research point for multimodal information detection in an internet public opinion scenario. In this paper, we look at how to dynamically monitor the internet opinion information (mostly images and videos) that different websites post. Based on the most recent advancements in text recognition, this paper proposes a new method of visual multimodal text recognition and sentiment analysis (MTR-SAM) for internet public opinion analysis scenarios. In the detection module, a LK-PAN network with large sensory fields is proposed to enhance the CML distillation strategy, and an RSE-FPN with a residual attention mechanism is used to improve feature map representation. Second, it proposes that the original CTC decoder be replaced with a GTC method to solve earlier problems with text detection at arbitrary rotation angles. Additionally, the performance of scene text detection for arbitrary rotation angles is improved using a sinusoidal loss function for rotation recognition. Finally, the improved sentiment analysis model is used to predict the sentiment polarity of the text recognition results. The experimental results show that the new method proposed in this paper improves recognition speed by 31.77%, recognition accuracy by 10.78% on the video dataset, and the F1 score of the multimodal sentiment analysis model by 4.42% on the self-built internet public opinion dataset (lab dataset). The method proposed provides significant technical support for internet public opinion analysis in multimodal domains.

Summary: Aspect‐category sentiment classification of microblog comments aims to identify the sentiment polarity of different opinion aspects in microblog comments, which is meaningful for the analysis of public opinion. At present, most of aspect‐category sentiment classification methods need much annotation data, and regard comments as independent samples, without using of the relationship between comments. This article proposes an aspect‐category sentiment classification method based on tensor graph convolutional networks. First, the combination of a comment and its aspect category is regarded as a hybrid node, and the original representation of a hybrid node is encoded by the Bert model. Second, sentiment graph and semantic graph are constructed according to the semantic similarity and sentimental relevance between hybrid nodes, and they are stacked into a tensor. Then two convolution operations, including intra‐graph convolution and inter‐graph convolution, are performed for each layer of graph tensor. In this way, hybrid nodes can learn and merge the heterogeneous information of different graphs. Finally, under the supervision of few labeled comments, the sentiment classification can be completed based on the features of the hybrid nodes. Experimental results on two microblog datasets show that the proposed model can significantly improve the performance of sentiment classification compared with other baseline models. [ABSTRACT FROM AUTHOR]

Correlation analysis of law-related news is a task to of dividing news into law-related or law-unrelated news, which is the basis of public opinion analysis. Public opinion news consists of the title and the body. The title describes the theme of the news, and the body describes the content of the news. They are equally important and interdependent in the analysis of lawrelated news. Therefore, we make full use of the dependence between the title and the body and propose a learning method that combines the bidirectional attention flow of the title and the body. This method encodes the title and the body respectively by using a bidirectional gated recurrent unit (BiGRU) to obtain the word-level feature matrix of the title and the word-level feature matrix of the body. Then it further extracts the law relevant key features from the body feature matrix, to obtain the word-level feature representation of the body. Finally, we combine the word-level feature representation of the title and the body to build bidirectional attention flow. In this way, the information of the two is fully integrated and interacted to improve the accuracy of the legal correlation analysis of news. To verify the validity of the method in this paper, we conducted experiments on the analysis of law-related news. The results show that our method has achieved good results. Compared with the baseline method, the F1 values of our method is increased by 2.2%, which strongly proves that the interaction between title and body has a good supporting effect on news text classification. [ABSTRACT FROM AUTHOR]

Abstract In recent years, researches on sentiment of individual investors are becoming popular, especially using big data technology. Most researches mainly focus on the relationship between the individual sentiment and the market fluctuations. In this work, we aim to testify the time-sensitivity of stock prices against the general sentiment of individual investors and to assess the influence of the evaluation of consulting institutions on stock prices. Firstly, we develop a distributed web spider to fetch the opinions data from social networks like Sina Guba, Eastmoney Guba and Sina Finance, and financial data from the RESSET database. Then through natural language processing, we build a sentiment index and institution evaluation index. Finally, we use correlation analysis, regression analysis and time series analysis to achieve our targets. The results show that: 1) the fluctuation of stock prices is more sensitively to the intraday sentiment of individuals; 2) there is no significant correlation between general sentiment of individual investors and the evaluation of consulting institutions, though the two factors both surely influence the change of stock prices; 3) the change of stock prices can be expressed by the public opinion well. [ABSTRACT FROM AUTHOR]

With the worldwide proliferation of social networks, the social networks have played an important role in the social activities .Peoples are inclined to obtain the corresponding public opinion to make decision such as shopping, education, investment and so on. Analysis of data generated by social networks has become an important field of research, however in the field of public opinion analysis of social networks the quantitative measure indexes are still lacking. In this paper, the calculation method of pessimistic investor sentiments indicator is proposed, and the index has a certain theoretical and practical value. [ABSTRACT FROM AUTHOR]

Online public opinion reflects social conditions and public attitudes regarding special social events. Therefore, analyzing the temporal and spatial distributions of online public opinion topics can contribute to understanding issues of public concern, grasping and guiding the developing trend of public opinion. However, how to evaluate the validity of classification of online public opinion remains a challenging task in the topic mining field. By combining a Bidirectional Encoder Representations from Transformers (BERT) pre-training model with the Latent Dirichlet Allocation (LDA) topic model, we propose an evaluation method to determine the optimal classification number of topics from the perspective of semantic similarity. The effectiveness of the proposed method was verified based on the standard Chinese corpus THUCNews. Taking Coronavirus Disease 2019 (COVID-19)-related geotagged posts on Weibo in Wuhan city as an example, we used the proposed method to generate five categories of public opinion topics. Combining spatial and temporal information with the classification results, we analyze the spatial and temporal distribution patterns of the five optimal public opinion topics, which are found to be consistent with the epidemic development, demonstrating the feasibility of our method when applied to practical cases. [ABSTRACT FROM AUTHOR]