Online Opinion Research Articles

Exploring the Relationship Between Online Public Opinion, User Discourse, and Social Bot Production and Information Dissemination

The advent of the digital age and the subsequent rise of the Internet have greatly impacted the relationship between online opinion and user discourse in the early evolution of traditional media. However, it has introduced new challenges, namely the emergence of social bots that generate and disseminate information that aims to influence public opinion. Thus, the paper attempts to decipher whether online public opinion, user discourse, and the positions of social robots in the production and dissemination of information will reinforce or change each other. Through the adoption of questionnaire survey method, 414 Internet users who understand and have contacted the human-computer account on Douyin platform as the survey object, online questionnaire survey, it screens out 414 effective questionnaires for data analysis. Besides, the samples are analyzed for reliability, correlation, exploratory factor analysis (validity analysis), linear regression analysis (mediated effects analysis), and analysis of variance using the SPSS (Statistical Product Service Solutions) tool, and the data are obtained. At the same time, combined with text analysis in qualitative research, semiotic analysis is mainly used to analyze how sample data conveys the relationship between online public opinion, user discourse, and social robots. On this basis, the results indicate that all five hypotheses presented in the paper are verified, and two new relationships are explored.

Exploring the Opinion Shifting of Social Media Users Based on Stance Detection

ABSTRACTFine‐grained mining of stance change among social media users during crises contributes significantly to a comprehensive understanding of the development of public opinion online. This study collected detailed information on 227,281 Twitter users who continuously participated in the discussion about the COVID‐19 vaccine to analyze patterns of opinion shifting. Utilizing the COVID‐Twitter‐BERT pre‐trained model, we detect each user's stance on the COVID‐19 vaccine and construct a time‐series dataset reflecting their stance over time. A prediction model for users' opinion shifting is established based on the LightGBM model, and the SHAP explanation method is used to rank the importance of features to identify key features influencing the opinion shifting prediction. Our research findings indicate that nearly half of the users maintained a consistent stance on vaccines, with a relatively low proportion of shifts between pro‐vaccine and anti‐vaccine stances. The F1 value of the prediction model based on the LightGBM model is 0.92. These findings can assist in monitoring social media user opinions online.

Online Political Participation of Refugees in Germany: Analysis of a Survey in Bavaria

New media are an important resource for the political participation of marginalized groups. However, there is still a lack of knowledge about the factors that influence whether this opportunity is used. Influencing factors emerge from both the Civic Voluntarism Model and previous research on migrants’ political activity. Using data collected in 2019/2020 from 486 refugees living in Bavaria, we estimate linear probability models to investigate facilitating factors for the use of new media for political participation. The analysis shows that refugees in Germany who inform themselves about politics online tend to be predominantly male, higher educated, and politically involved. Language skills and the duration of stay also appear to be important. For the expression of one’s political opinion online, gender and language skills have an impact, but informing oneself about German politics, political interest, and offline political activity in Germany are the most relevant factors. This indicates that there is a close link between on- und offline activity. However, using the internet requires particular resources, so that people with lower language skills, for example, are particularly disadvantaged.

The Impact of Online Opinion on Justice: Two Cases in Comparative Law Perspective

In the early stages of the judicial process, trials were characterized by a pursuit of independence and justice, with judges adhering strictly to legal statutes and delivering judgments that aligned with legal logic. However, as today's digital landscape evolves, Internet users engage with the judiciary in distinct ways; they communicate online, actively voice their opinions, and gradually cultivate a representative form of public opinion on the web. As the impact of online public sentiment on judicial administration grows stronger, it increasingly exhibits a tendency to exert dominance. While the independence of the judiciary remains unquestionable, certain explosive instances of online public opinion also highlight pressing societal issues that warrant attention and cannot be overlooked. Using two well-known cases as an entry point, we will compare how networked public opinion influences justice differently in Japan and China. This analysis will delve into the underlying jurisprudence while seeking solutions tailored to China's national context. The goal is to foster positive interaction between these two realms—leveraging the constructive influence of online public opinion on judicial processes—and ultimately enhance China's judiciary system.

Multimodal Sarcasm Detection: A Comprehensive Review

Sarcasm, a form of verbal irony, involves using remarks that intentionally convey the opposite of their literal meaning. It serves to criticize or humorously undermine a situation. Verbal and non-verbal cues—such as changes in tone, incongruence across modalities, and word emphasis—often convey sarcasm. As technology advances, more people express their opinions online, necessitating the development of efficient models for detecting speech nature. Machine Learning algorithms, Linguistic Models, Ensemble Learning, and Multi-modal approaches play crucial roles in this endeavor. While most research has focused on unimodal approaches using textual data, the field now embraces multimodal sarcasm detection. This approach integrates diverse data types, including images, text, and audio, to enhance accuracy and automate sarcasm classification. In our review paper, we delve into the captivating world of multimodal sarcasm detection, tracing its evolution from early unimodal methods to the current state of multimodal techniques. We aim to provide a comprehensive overview, shedding light on challenges, methodologies, and prospects. Keywords: Sarcasm Detection, Multimodal Approaches, Machine Learning Algorithms, Linguistic Models, Ensemble Learning

Online opinion leadership styles and purchase intention in livestreaming e-commerce

ABSTRACT As online opinion leaders and persuaders, livestreamers enable the widespread success of livestreaming e-commerce by substantially impacting viewers’ online purchase intention. Yet, extant studies have overlooked online opinion leadership styles exhibited by livestreamers and how these influence viewers’ online purchase intention. We explore this issue by developing a comprehensive framework of livestreamers’ online opinion leadership styles, comprising authentic, ethical, servant, and participative dimensions, based on both livestreaming and opinion leadership literature. Then, drawing on regulatory focus theory, the partial least square-structural equal modeling analysis of survey data collected from 321 Chinese viewers revealed that livestreamers with authentic and ethical online opinion leadership styles promote viewers’ prevention focus. Next, livestreamers with the servant and participative styles promote viewers’ promotion focus. Finally, viewers’ prevention and promotion focus propel their online purchase intention. Our findings contribute to the development of a comprehensive framework of online opinion leadership styles in computer-mediated livestreaming e-commerce.

How low-credibility gossip information impact the users opinions in social network

Low-credibility gossip information in social networks is a trigger for online opinion distortion. Since fragmented information always appears along with low content credibility and gossip, this paper put forward an online opinion distortion model based on DW algorithm, and information credibility, gossip intensity and opinion leaders were integrated in order to find out the mainly factors which induce opinion distortion. Then, four groups of experiment by using MATLAB were conducted, and the results show that the credibility of information is a key factor affects the speed of opinion, and also very important for the direction of the opinion dynamic of the whole network. Online opinions can easily impact by the gossip information, and extreme gossip information causes serious division of opinion group, and the whole network opinions cannot be converged even in a quite long-time iteration. Super opinion leaders have the ability to balance the influence of gossip, even in an online environment full of gossip information. Based on these, a case study including 315 thousand records of posts and comments from Weibo is conducted for confirming the mainly findings in the simulation analysis, and strategies like high credibility information, low gossip probability, and behalf opinion leader are put forwarded finally for reduce opinion distortion.

Assessing the Alignment Between Online Word-Of-Mouth and Schools’ Actual Academic Performance: A Deep Neural Network Analysis

ABSTRACT Many parents use social media to gather word-of-mouth regarding schools’ performance, subsequently influencing their school choice decisions. Yet, it’s unclear how well online opinions reflect schools’ actual academic performance. To address this gap, this study uses machine learning to examine whether the online evaluations of students’ learning can match schools’ test scores and their improvements. Findings indicate that while online evaluations don’t perfectly align with test scores, the association between online word-of-mouth and test scores remains stronger than that of test score gains. Consequently, online word-of-mouth tends to recommend schools with higher test scores over higher value-added scores.

A Text-Inception-Based Natural Language Processing Model for Sentiment Analysis of Drug Experiences

The study of sentiment in Natural Language Processing (NLP) is among the most successful research areas because of the availability of millions of user opinions online since the turn of the century. The economic, political, and medical fields are just some of the many that have benefited from studies of sentiment research. While numerous studies have examined more mainstream topics like consumer electronics, movies, and restaurants, relatively few have examined health and medical concerns. Considerable insight into where to direct efforts to improve public health might be gained by a study of how people feel about healthcare as a whole and of individual drug experiences in particular. When it comes to medicine, automatic analysis of online user evaluations paves the way for sifting through massive amounts of user feedback to find information regarding medications' efficacy and side effects that might be used to enhance pharmacovigilance programs. Simple rules-based methods have given way to more complex machine learning approaches like deep learning, which is developing as a technology for many natural language processing jobs. The opensource datasets have been analyzed with models that use word embeddings and term frequency-inverse document frequency (TF-IDF). A feature-enhanced text-inception model for sentiment classification was presented to work in tandem with this approach. The model first employed a cutting-edge text-inception module to glean useful shallow features from the text. K-MaxPooling was subsequently employed to reduce the dimensionality of its shallow and deep includes as well as enhance the generalization of characteristics, and a deep feature extraction module was formed using the bidirectional gated recurrent unit (Bi-GRU) and the capsule neural network to comprehend the text's semantic data. By combining traditional methods with cutting-edge artificial intelligence techniques, this hybrid approach can revolutionize public health initiatives, decision-making, and pharmacovigilance in the healthcare industry. This model achieved an exceptional accuracy rate of 99%, underscoring its effectiveness in sentiment classification and demonstrating its potential to significantly contribute to advancing healthcare and medical research.

Changes in online public opinions associated with various three-child supportive policies in China: Observational study using social media data over time.

According to the Seventh National Census, China's fertility rate is less than 1.5, marking a significant national issue with potential risks. To counter this low birth rate, the Chinese government has relaxed family planning policies and introduced supportive measures. Changes in birth policy have attracted considerable attention from the people of China. This article aims to study the public's response to the three-child support policy using Weibo as a window. The goal is to provide a more balanced evaluation of current perspectives, enabling policymakers to formulate better fertility information, particularly when anticipating a poor public response to controversial policies. This research uses a crawler to gather data from Sina Weibo. Through opinion mining of Weibo posts on the three-child policy, Weibo users' online opinions on the three-child policy are analyzed from two perspectives: their attention content and sentiment tendency. Using an interrupted time series, it examines changes in online views on the policy, matching policy documents to the time nodes of Weibo posts. The public has shown great interest in and provided short-term positive feedback on policies related to improving maternity insurance, birth rewards, and housing subsidies. In contrast, there has been a continuous negative response to policies such as extending maternity leave, which has particularly sparked concerns among women regarding future employment and marital rights protection. On social media, the public's attention to the three-child birth policy has focused mainly on the protection of women's rights, especially legal rights after childbirth, and issues related to physical and mental health. Child-rearing support and economic pressure are also hot topics, involving the daily expenses of multichild families, childcare services, and housing pressure. However, this study also revealed that infertile or single women express a strong desire to have children, but due to limitations in the personal medical insurance system, this desire has not been fully satisfied. Our study demonstrates the feasibility of a rapid and flexible method for evaluating the public response to various three-child supportive policies in China using near real-time social media data. This information can help policy makers anticipate public responses to future pandemic three-child policies and ensure that adequate resources are dedicated to addressing increases in negative sentiment and levels of disagreement in the face of scientifically informed but controversial, restrictions.

A fuzzy-based emotion detection method to classify the attractiveness of urban green spaces

In European studies, the most used definition of Urban Green Spaces (UGS) is based on the European Urban Atlas, which includes public green areas primarily used for recreation and green areas adjacent to urban areas that are managed or utilized for recreational purposes. UGS play a vital role in creating sustainable and resilient cities, as they provide essential social benefits for the well-being and health of urban residents. Both planners and scientists acknowledge the importance of involving, actively or passively, citizens in defining criteria for designing and managing inclusive and functional UGS. According to a post-normal science approach, the integration of hard data from scientific sources with soft data gathered from citizens’ engagement holds the potential to shape an innovative support system for public policies addressing significant, urgent, and uncertain challenges pertaining to UGS. Nowadays, the abundance of data generated through online reviews, opinions, and comments allows for collecting valuable information about people’s opinions and sentiments towards UGS. This study proposes a methodological framework that utilizes emotion detection techniques to identify and analyze citizens’ emotions concerning UGS through social reviews. To balance computational costs and classification accuracy, the framework introduces a fuzzy emotion-based classification method called FREDoC (Fuzzy Relevance Emotions Document Classification). This method incorporates a lightweight natural language pro-cessing (NLP) approach to detect and annotate terms associated with specific emotional categories within the text. The framework adopts the psycho-evolutionary classification approach based on R. Plutchik’s observations of general emotional responses. This model is implemented within a Geographical Information System (GIS) for the purpose of categorizing UGS, specifically green parks, according both to WHO report key indicators and to the detected relevant emotions. The outcome is a novel classification model of UGS that can assist decision-makers in identifying the attractiveness of UGS as catalysts for urban transformation processes.

Exploring the Influence Factors of Purchase Intention of College Students by Short Video Opinion Leaders in Field of the Beauty

Over the past decade, the rapid development of new media and e-commerce have triggered the emergence of online opinion leaders. Simultaneously, consumers’ purchase intention has been swayed by some opinions expressed by online opinion leaders. Therefore, this paper aims to delve into the factors influencing the consumption of college students by opinion leaders in field of the beauty. It aims to explore the influence degree of short video opinion leaders on the purchase intention of college student consumers in three dimensions, including short video production, opinion leaders’ characteristics and short video content. Employing a questionnaire for data collection and SPSS 29.0 for analysis, the study uses methods such as reliability analysis, exploratory factor analysis, and regression analysis to validate the model and research hypotheses. The results of the study show that in the dimension of opinion leaders’ short video production, the attractiveness of the title and editing format of the short videos have a significant positive impact on the purchase intention of college students. Regarding opinion leaders’ characteristics, their popularity, professionalism, and interactivity exert a substantial positive influence on college students’ purchase intentions, whereas timeliness shows no significant impact. In terms of opinion leaders short video content, comparing products with multiple brands, promoting affordable substitutes, and vivid and interesting promotion discourse of opinion leaders all have a significant positive impact on the purchase intention. Finally, this paper provides suggestions for short video opinion leaders in field of the beauty.

Silencing Online Incivility: Examining the Effects of Impoliteness and Intolerance in Online Political Discussions

ABSTRACT Drawing on silencing and online incivility literature, this study examined how people evaluate and respond to impolite and intolerant online opinions in different discussion contexts. Based on a between-subject online survey experiment in the U.S. (N = 959), we found that people perceived impoliteness and intolerance as uncivil, leading to intentions to silence others. The results also revealed that intolerance resulted in higher perceived incivility and silencing intentions compared to impoliteness. Furthermore, the direct effects of impoliteness and intolerance on perceived incivility and their indirect effects on silencing intentions through perceived incivility were stronger in agreeing discussions than in disagreeing ones. However, social endorsement cues did not moderate the mechanisms.

Are Your Comments Positive? A Self-Distillation Contrastive Learning Method for Analyzing Online Public Opinion

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.

Navigating the complexities of online opinion formation: An insight into consumer cognitive heuristics

Few studies have considered changes in consumer perceptions when faced with multiple levels of review ratings. Drawing on availability heuristic theory, we aim to explore the synergistic effects of different levels of review ratings on consumers' cognitive processes. Using a longitudinal dataset of reviews from 4637 restaurants on Yelp, we conducted an empirical study using individual and time-dual fixed-effects models. Our findings indicate that easy-to-retrieve (review) rating is better than aggregate ratings in predicting consumer purchase decisions. The inconsistency between easy-to-retrieve and aggregate ratings influences consumers' cognitive heuristic when interpreting online reviews. Additionally, inconsistencies and proportional changes in expert and amateur reviews influence consumer perceptions of different levels of information. Furthermore, we conducted two online experiments to validate the distinguishing impact of aggregate versus easy-to-retrieve ratings on consumers. These findings provide insightful implications for understanding consumers’ cognitive heuristics in online consumption contexts.

Ethics guidelines for palliative care of terminally ill patients in Islamic Republic of Iran.

There have been many challenges with clinical interventions and policy decisions to enhance the quality of life and care for patients facing life-threatening illnesses, thus highlighting the need for ethical considerations and guidelines for palliative care of terminally ill patients. To document the development of guidelines for addressing ethical concerns in the palliative care of terminally ill patients in Islamic Republic of Iran. The guidelines were developed in 4 phases: a scoping review of existing palliative care guidelines on PubMed, Scopus, Web of Science, Google Scholar, and 2 Persian databases; focus group discussions to improve the drafts guidelines; online opinion poll of 32 experts, including ethicists, religious scholars, psychologists, palliative care specialists, and sociologists; and a national workshop to produce the final guidelines for government approval. We published the "National palliative care ethical guidelines and regulations for terminally ill patients" in Islamic Republic of Iran after endorsement and approval by the High Council of Medical Ethics. The guidelines provides recommendations on 5 main aspects of palliative care: structure, composition and qualification of interdisciplinary teams; the roles and responsibilities of ethics advisors; general ethical principles governing palliative care practice; specific guidelines for psychological, spiritual and religious support; and protocols for ethical decision-making in end-of-life care. Considering the challenges associated with palliative care, it is necessary to provide ethical guidelines specific to the needs of terminally ill patients. These guidelines will serve as a steppingstone towards integrating palliative care into the national healthcare services in Islamic Republic of Iran.

Quo Vadis Hadith Studies in Islamic Boarding Schools in Al-Jabiri's Perspective

This study aims to analyze the paradigm shift and the direction of the hadith study objectives at Ma'had Aly HasyimAs-sari Jombang used the perspective of Muhammad Abid Al-Jabiriy's Arabic reasoning. This study used a descriptive curative approach. Technical Data Analysis Using Miles and Huberman Theory with three steps: data collection, data reduction, third data presentation, verification, and data conclusions. Primary and secondary data were used in this study. Secondary data were obtained from secondary sources, such as tabloids, magazines, bulletins, and online opinions, while primary data were obtained from primary sources, such as interviews and observations. This study found that first, the Islamic Boarding School, especially Ma'had Aly Hasyim Asaraiy, in essence has long used irfani and bayani reasoning in the form of hadith studies as a counter to the extreme burhani reasoning of Western civilization as a counterweight. However, lately, Islamic boarding school education with its Ma'had Aly begin to be carried away by the strandarization of such education. Second, Ma'had Aly education has a purpose as a response to global changes in the world of education which requires formality as an authority for recognizing the knowledge of its graduates, but has a big consequence that one day the boarding school will lose its irfanical reasoning characteristics by sinking into extreme burhani reasoning in the national education system implemented by the government.

Automatic Algerian Sarcasm Detection from Texts and Images

In recent years, the number of Algerian Internet users has significantly increased, providing a valuable opportunity for collecting and utilizing opinions and sentiments expressed online. They now post not just texts but also images. However, to benefit from this wealth of information, it is crucial to address the challenge of sarcasm detection, which poses a limitation in sentiment analysis. Sarcasm often involves the use of non-literal and ambiguous language, making its detection complex. To enhance the quality and relevance of sentiment analysis, it is essential to develop effective methods for sarcasm detection. By overcoming this limitation, we can fully harness the expressed online opinions and benefit from their valuable insights for a better understanding of trends and sentiments among the Algerian public. In this work, our aim is to develop a comprehensive system that addresses sarcasm detection in Algerian dialect, encompassing both text and image analysis. We propose a hybrid approach that combines linguistic characteristics and machine learning techniques for text analysis. Additionally, for image analysis, we utilized the deep learning model VGG-19 for image classification, and employed the EasyOCR technique for Arabic text extraction. By integrating these approaches, we strive to create a robust system capable of detecting sarcasm in both textual and visual content in the Algerian dialect. Our system achieved an accuracy of 92.79% for the textual models and 89.28% for the visual model.

Кластерный анализ лингвистических профилей скрытых сообществ

The aim of the study is to present clusters of profiles of hidden communities based on linguistic parameters. The article analyzes the structure and relationships between the attributes of clusters of community profiles. The scientific novelty of the study lies in the fact that the combination of methods of hierarchical cluster analysis of hidden network communities and analysis of variance will reveal the uniformity/heterogeneity of the author's texts created at the grammatical and lexical levels. Using the Ward method, three clusters of linguistic profiles were identified, each of which was given a formal Silhouette Score. A meaningful assessment of the profiles is presented in the form of appropriate linguistic comments. As a result of the study, it was found that online publications are characterized by variation at the level of syntax, but not at the level of morphology. The proposed community clustering approach can be used to identify potentially dangerous online subcultures and opinion leaders in the online space. As a result of the implementation of this approach, linguistic profiles of communities are complemented by digital sociodemographic information.

The Influence of Social Media Influencers on Consumer Decision-Making: A Comprehensive SEM Analysis

In recent times, social media influencers and their marketing campaigns have gained significant popularity and attention. The aim of this study is to identify the extent to which social media influencers impact consumer decision-making and buying behaviors. The paper examines influencer marketing as a form of electronic word-of-mouth (eWOM) and how it affects the consumer purchase journey. Framework is developed using existing literature on topics like consumer decision-making, eWOM, opinion leadership, source credibility, and digital interaction. The methodology utilizes a deductive research approach with a cross-sectional quantitative survey. The target population comprises consumers in Karachi who regularly use social media. The study uses Structural equation modeling (SEM) analysis to identify the relationship between social media word mouth, quality of information, Digital interaction, Digital Attractiveness, and Digital interaction on consumer decision-making with the mediation effect of opinion leaders. Convenience sampling is employed to collect data from over 150 respondents. The results provide empirical evidence that opinion leadership and source credibility significantly influence consumer decision-making when it comes to influencer marketing. This implies that the personality and perceived trustworthiness of the influencer matter more than their attractiveness or expertise. However, digital expertise is not found to have a positive effect. Overall, the findings highlight the need for brands to partner with credible influencers who can leverage their leadership to steer audience opinions and purchases. Future research can build on this by investigating negative eWOM, commercialism, and manipulating tactics used by influencers. The paper contributes to the growing research on social media marketing and how online opinion leaders shape consumer behaviors.