Event Graph Neural Network for Opinion Target Classification of Microblog Comments

Opinion target classification of microblog comments is one of the most important tasks for public opinion analysis about an event. Due to the high cost of manual labeling, opinion target classification is generally considered as a weak-supervised task. This article attempts to address the opinion target classification of microblog comments through an event graph convolution network (EventGCN) in a weak-supervised manner. Specifically, we take microblog contents and comments as document nodes, and construct an event graph with three typical relationships of event microblogs, including the co-occurrence relationship of event keywords extracted from microblogs, the reply relationship of comments, and the document similarity. Finally, under the supervision of a small number of labels, both word features and comment features can be represented well to complete the classification. The experimental results on two event microblog datasets show that EventGCN can significantly improve the classification performance compared with other baseline models.

The “Blue Check” Communication on the Pandemia Vaccine Campaign

This chapter has the exploratory goal of understanding the attitudes and perceptions of 'verified' Twitter (VA) accounts about the COVID-19 vaccine campaign. Identifying their sentiment and opinion about it could therefore be crucial to the success of vaccination. A content analysis of tweets from the period December 24, 2020 to March 23, 2021 about the vaccine campaign in Italy was conducted to understand the semantic strategies used by VAs based on their orientation toward the vaccine, whether pro, anti, or neutral, and their possible motivations. Topic modeling allowed the authors to detect five prevalent themes and their associated words. A sentiment analysis and opinion analysis were performed on a smaller sample of tweets. The results suggest that 'authoritative' opinion about the vaccine has been very fragmented and not entirely positive, as expected. This could prove to be a critical issue in getting the vaccine positively accepted by the public.

Study on Product Opinion Analysis for Customer Satisfaction on E-Commerce Websites

The E-commerce websites have been emerged in a high range of marketing benefits for the users to publish or share the experience of the received product by posting review that contain useful comments, opinions and feedback on the product. These days, a large number of clients acquire freedoms to look at comparative items in online sites and pick their top choices in computerized retailers, like Amazon.com and Taobao.com. Client audits in online media and electronic trade Websites contain important electronic word data of items. Sentiment Analysis is broadly applied as voice of clients for applications that target showcasing and client care. Sentiment extractors in their most essential structure classify messages as either having a good or negative or once in a while neutral supposition. A typical application of sentiment investigation is the programmed assurance of whether an online review contains a positive or negative review. Subsequently, in this paper, with the use of the strategies on sentiment analysis, obstinate sentences alluding to a particular element are first recognized from item online audits. We have proposed deep learning strategy as a classification model for discovering the condition of review. The outcomes showed suggested site for the client dependent on the early audits, past reviews and answer given to inquiry audit for the client. Additionally, it is seen that the proposed strategy can ready to answer every one of the reviews with a superior closeness like a human reaction to the client.

Analisis Pro Kontra Vaksin Covid 19 Menggunakan Sentiment Analysis Sumber Media Sosial Twitter

The development of information technology today has experienced very rapid growth. One of the developments in information technology, namely social media such as Twitter, Facebook, and Youtube, are some of the most popular communication media in today's society. Twitter is often used to express emotions about something, either praising or criticizing in the form of emotion. Human emotions can be categorized into five basic emotions, namely love, joy, sadness, anger, and fear. Twitter users' emotional tweets can be known as opinion or sentiment analysis (opinion analysis or sentiment analysis). Sentiment analysis is also carried out to see opinions or tendencies towards a problem or policy, whether they tend to have negative or positive opinions. The COVID-19 vaccine has become one of the discussions with a fairly high intensity on social media. Vaccine-related tweets have increased as government policies evolve. The responses of netizens also varied, ranging from clinical trials of vaccines, free vaccines, vaccine effectiveness, halal vaccines, to the implementation of vaccinations. This research produces a system that can analyze tweet sentiment related to the covid 19 vaccine in Indonesia where the tweet is obtained using the Twitter API. This system uses the Multinominal Naive Bayes method for the classification process.

A Clustering Method of Case-Involved News by Combining Topic Network and Multi-Head Attention Mechanism

Finding the news of same case from the large numbers of case-involved news is an important basis for public opinion analysis. Existing text clustering methods usually based on topic models which only use topic and case infomation as the global features of documents, so distinguishing between different cases with similar types remains a challenge. The contents of documents contain rich local features. Taking into account the internal features of news, the information of cases and the contributions provided by different topics, we propose a clustering method of case-involved news, which combines topic network and multi-head attention mechanism. Using case information and topic information to construct a topic network, then extracting the global features by graph convolution network, thus realizing the combination of case information and topic information. At the same time, the local features are extracted by multi-head attention mechanism. Finally, the fusion of global features and local features is realized by variational auto-encoder, and the learned latent representations are used for clustering. The experiments show that the proposed method significantly outperforms the state-of-the-art unsupervised clustering methods.

Political Opinion Analysis in Social Networks: Case of Twitter and Facebook

The 21st century has been characterized by an increased attention to social networks. Nowadays, going 24 hours without getting in touch with them in some way has become difficult. Facebook and Twitter, these social platforms are now part of everyday life. Thus, these social networks have become important sources to be aware of frequently discussed topics or public opinions on a current issue. A lot of people write messages about current events, give their opinion on any topic and discuss social issues more and more. The emergence and enormous popularity of these social networks have led to the emergence of several types of analysis to take advantage of them. One of them is the analysis of opinions in texts. It aims at automatically classifying opinions in order to position them on a sentiment scale, thus allowing to characterize a set of opinions without having to rely on a human to read them. Currently, opinion analysis offers us a lot of information related to public opinion, either in the commercial world or in the political world. Many studies have shown that machine learning techniques, such as the support vector machine (SVM) and the naive Bayes classifier (NB), perform well in this type of classification. In our study, we first propose an approach for tracking and analyzing political opinions in social networks. Then, we propose a trained and evaluated machine learning model for political opinion classification. And finally, the study aims at setting up a web interface to collect and analyze in real time political opinions from social networks

Peculiarities of Ukrainians’ Approval of Decentralization Reform

Every countrywide reform can always have specific opponents and fans as the changes make people leave their comfort zone. As an example, we have chosen a Ukrainian decentralization reform. Although this local self-government reform can be considered the most successful in our country, the attitude of Ukrainians to the changes has not always been unambiguous. Using taxonomic analysis, the paper calculates the integrated indicator of public approval of decentralization reform in Ukraine based on sociological research for 2015–2020. We have described the features of conducting surveys in different periods and identified the reasons for the emergence of such an attitude to the reform. We have also calculated the weights of the impact of each primary indicator on the integrated indicator, which helped us identify the weaknesses and strengths of the reform in public opinion Furthermore, the analysis allowed us to reveal and substantiate a set of problems in implementing decentralization reform in Ukraine, and the causes and solutions were worked out for each problem. Finally, we have made a generalized algorithm for the application of the experience of public opinion analysis in planning and carrying out reforms.