Social Network Environment Research Articles

Research on User Reviews Analysis Based on Sentiment Analysis from the Perspective of Social Networks

Based on theories such as user resource relationship theory, attitude perception theory, and user behavior theory, this paper summarizes and explains existing sentiment analysis methods, and seeks practical paths and methods for analyzing and visualizing user reviews from the perspective of social networks. The paper aims to obtain the most authentic and effective feedback from the public. This enables the adoption of correct strategies to guide online public opinion, thereby fully leveraging the information and emotional feedback effects of comments, and promoting the shaping of a good social network environment.

Social network trust relationship environment based advanced ovarian cancer treatment decision-making model: An approach based on linguistic information with experts’ multiple confidence levels

Advanced ovarian cancer is the deadliest gynecologic cancer in World. The survival rate is not significant, and it depends on how well cancer responds to treatment. Generally, the treatment decision depends on Gynecologic oncology experts, which treatment is best for the patient. However, a Gynecologic oncology expert’s limited rationality and personality traits strongly impact a patient’s treatment decision. In addition, according to the American Cancer Society, a patient’s treatment decision may change if Gynecologic oncology experts change. To solve this kind of medical problem, we design a group decision-making model (GDM) based on linguistic preference relations (LPRs) with multiple confidence levels like confidence and doubting levels of experts to analyse experts’ treatment decision opinions digitally for improving the survival rate of patients. In a GDM, consistency analysis and obtaining expert weights are two keys. Hence, this paper design an LPRs with confidence and doubting levels (LPRs-CDLs) based GDM model under a unique consistency improvement algorithm and Pythagorean linguistic trust relations social network analysis driven expert weight determination. First, we define the additive consistency of LPRs-CDLs based on minimum confidence and maximum doubting levels. Second, a consistency reaching process (CRP) algorithm with convergence theorem is offered to improve the consistency of experts’ opinion decisions. Third, develop a trust propagation model based on Pythagorean linguistic trust relations under a social network environment for expert’s weights determination. Then, a social network trust relationship-based GDM model with LPRs-CDLs information is presented to the advanced ovarian cancer patient’s treatment final decision. Finally, we show the rationality of this study with some comparative analysis.

Komunikasi Nabawi Sebagai Asas Panduan Interaksi Media Sosial

Social media interactions are more widespread in the digital world than conventional social interactions that take place physically and are limited to small groups of people. Although various social media applications have made people’s lives easier, on the other hand, they also cause users to engage in interactions that are free to violate boundaries, resulting in negative phenomena and harming other users. Religion should play an important role in digital social interactions on social media, just as it does in conventional social interactions. Prophet Muhammad SAW is the best example for social media interaction. This paper examines the problem of social media misconduct and presents a general guide to digital interaction, especially in the use of social media, with reference to several hadiths with the theme of Prophetic communication as the main reference. This research involves qualitative data through literature review by examining research documents and reports related to social media. Thematic analysis or mawḍū‘ī is done by collecting some selected hadith that have the theme of communication. The general guide for social media interaction that was developed is not only focused on worldly factors and implications, but also has a spiritual dimension by referring to Prophetic communication and following religious recommendations that emphasize the concept of Hablu min al-Nas. It is hoped that this guide can be used for social media interactions that indirectly create a safe social networking environment.

Optimization Model Construction of Online Public Opinion Dissemination Based on Behavioral Data Mining

Abstract In this paper, we propose an optimization method based on behavioral data mining for the emergence of negative emotions in network public opinion in unexpected situations leading to problems that endanger social stability and use data mining to confirm the correspondence of the kNN algorithm. In the opinion propagation model, the radius of opinion radiation is assumed to use the network node density and distribution density as features of node exchange information. Then, the kNN algorithm is used to train the comment set for the analysis of user sentiment evolution of network opinion in the social network environment, and the web crawler technology is used to obtain the output interface data APIs of microblogs and WeChat, and the social media user comment data is used as the data for the empirical analysis of network opinion. snowNLP and kNN algorithms are used to analyze the sentiment score of network opinion and the sentiment score less than 0.5, i.e., the sentiment polarity. There were 15 days when the sentiment score tended to be negative and 65 days when the sentiment score was greater than 0.5, i.e., the sentiment polarity tended to be positive.

Social Media and Some Notes When Using

The world currently exists, moves and develops as a “flat world”, which is both unified, contradictory, cooperative and struggling. Participating in that process is the great role of the mass media, which is now the power of multimedia and, more specifically, social media. Thanks to the exploitation and application of outstanding achievements of information technology, social media exists on digital platforms with many faces. However, besides the outstanding advantages compared to other types of multimedia communication, social media also has disadvantages that users need to be aware of when using. The article is going to investigate the relationship between social media and social networks. Besides, a number of advantages and disadvantages of social media are also indicated clearly, which serves as the basis for the author to propose certain measures to improve the social network environment as well as reduce inconvenience to users. In the article, the Code of Conduct on social networks promulgated by the Ministry of Information and Communications of Vietnam is analyzed to help users to be aware of ethical standards of behavior on social networks as well as maintain and develop personal freedom, business freedom, and non-discriminatory service providers at home and abroad, contributing to building a safe and healthy social network in Vietnam.

International Experience of State Regulation of Business in Social Networks

State regulation of business in social networks provides for the protection of personal data, intellectual property rights and ensuring the confidentiality of information of legal entities and individuals. The purpose of the academic paper is to analyse the international experience of state regulation of business in social networks and to determine the approach to the model of its implementation. Features of the development of digital technologies make it possible to improve the selection of methods for carrying out the research, which will be based on the use of expert evaluation. The research methodology consists in conducting a comprehensive study of the modern environment of social networks and identifying key areas for state intervention and defining the legal framework for conducting business in social networks. In the course of analysing the state regulation of business in social networks, the search method, induction and deduction, and the empirical method were used. With the help of the latter, an analysis of the level of state presence in the activities of the corporate sector and the implementation of characteristic principles was carried out. The results of the academic paper characterize the trends of strengthening the influence of the state on the regulation of business activities in social networks, the need to introduce reporting and the existing system of user data protection. Thus, the academic paper provides a comprehensive analysis of state regulation of business in social networks.

Retracted: Analyzing the Relationship between Hotel Brand Image, Service Quality, Experience Marketing, and Customer Satisfaction under the Environment of Social Network.

[This retracts the article DOI: 10.1155/2022/1064712.].

Retracted: Analysis on the Key Influence of Adolescent Health Information Literacy Using Big Data Analysis Technology under Social Network Environment.

[This retracts the article DOI: 10.1155/2022/4126217.].

Popularisation of Science and Science Journalism on Social Media in Slovakia

This study focuses on the presentation and interpretation of scientific information and data by Slovak creators on the social platform Instagram. Media content presented on social media often becomes problematic, as popular science posts are more in an entertaining than scientific form. It happens that popular science content is presented inaccurately, without deeper context. In addition, scientific misinformation and misleading information appears, which can pose a danger to audience members who trust such information. Science journalism has found its place not only in traditional media, but also on social media platforms, where problematic information on scientific topics goes viral and achieves a high level of user interaction. In an unregulated or under-regulated social networking environment, it is also more difficult for users to discern the credibility and relevance of the information presented, especially when referring to existing scientific studies or authorities. However, data from these sources may be taken out of context, interpreted in a misleading way or accompanied by completely fabricated or distorted conclusions. Such false scientific content undermines confidence in objective science journalism and discredits the work of science journalists. Several digital tools are now available that can help readers distinguish real scientific information from false information. Critical thinking, media literacy and scientific literacy are key skills that can be used to detect manipulative techniques and navigate the issue of false media content. In this paper, we therefore clarify the importance of media, scientific and information literacy skills to help identify misinformation in media content related to science and research.

Consensus reaching process with noncooperative behaviors in large-scale group social network environment

Large-scale group decision-making (LSGDM) problems have drawn general attention from scholars. The distribution linguistic preference relation (DLPR) is a flexible and practical tool to describe the preferences of decision makers (DMs) in the decision-making process. Opinion conflict is inevitable among large-scale DMs due to self-interest and individual perception. Thus, it is essential to establish a consensus reaching process (CRP), but there may be non-cooperative behaviors for DMs when they are required to accept the opinions adjustment. As the social network becomes more ubiquitous, moreover, the trust relationship among decision members has implications for the consensus reaching process. Hence, this study proposes a new consensus model that manages non-cooperative behaviors from the cooperative degree, trust relationship, and individual self-confidence level three aspects, and discusses the specific influence of these factors on the penalty for non-cooperative behaviors. In addition, hesitancy-based similarity measure of linguistic distributed assessment is proposed for clustering and measuring consensus level. Finally, a numerical example of a price hearing system demonstrates the feasibility and efficacy of the proposed method, and a comparative analysis illustrates its features and advantages.

On the problem of recommendation for sensitive users and influential items: Simultaneously maintaining interest and diversity

Recommender systems, in real-world circumstances, tend to limit user exposure to certain topics and to overexpose them to others to maximize performance. However, repeated exposure to biased content could lead to the so-called echo chamber phenomenon: especially in social network environments, people encounter only information that reflects their previous beliefs and opinions, reinforcing them. This phenomenon could have worrying consequences for society, including the spread of aggressive, unhealthy, or risky behaviors. Some persons can be more affected than others by echo-chambers. We define as sensitive the users whose behavior could be influenced by the over- or under-exposure to certain items due to the echo-chamber effect, and as influential the items that could influence the behavior of such users. In this paper, we address the problem of recommending influential items to sensitive users. We formalize the problem and propose three techniques that can be used to diversify the distributions of influential items in order to positively affect sensitive users’ behavior. Recommendations that meet this diversity criterion could potentially avoid dangerous societal consequences and simultaneously promote healthier lifestyles. We tested the proposed techniques in a real-world dataset by considering two different case studies that involved potentially aggressive and potentially depressed users. All techniques have been proven to be effective and allow high performance to be maintained while diversifying recommendations.

Does personalized advertising have their best interests at heart? A quantitative study of narcissists’ SNS use among Generation Z consumers

Artificial intelligence (AI)-enabled technology has generated a new dynamic that empowers the advertising business and social networking environment. In terms of convenience, consumers benefit from the generation of customized ad content through their activities on social network sites (SNS). However, concerns about data privacy and impaired well-being remain, notably in relation to Generation Z consumers, who are considered tech-savvy, narcissistically-oriented, and vulnerable in their SNS usage. Drawing on cognitive dissonance theory, we show how a dilemma of convenience vs. privacy drives their technology dissonance and their dependence on SNS. Our empirical study in the US demonstrates the trade-off between convenience and privacy that results from the customizability of technology, the opposite functions of these facets in technology dissonance, and the negative impact on SNS dependence. When the key role of the ego in the dissonance in Generation Z’s SNS behavior is recognized, vulnerable narcissism is found to show nuances of psychological dissonance induced by privacy concerns. Our findings enhance the discussion on the customizability of AI-enabled technology by indicating how advertisers can improve targeted marketing and ensure the well-being of Generation Z consumers.

The impact of cookie regime change on the effectiveness of automatic retargeting in advertising

The constantly evolving legislation concerning the usage of cookies raises many concerns about the effectiveness of targeted online advertisements. Retargeting represents an advanced targeting strategy requiring detailed user data and thus may be potentially highly sensitive to cookie restrictions. The retargeting effectiveness is tested in terms of type (standard, dynamic), advertising platform (Meta Ads, Google Ads), and the ad performance development in time. The data were collected through a Czech home goods online retailer. This paper tests the effectiveness of 432 retargeting ads collected during the opt-out cookie regime by comparing them with 432 retargeting ads collected after the transition to the opt-in cookie regime. The study created 216 ads on Google and 216 ads on Facebook. The entire experiment took one month to be implemented in 2021 and repeated in precisely the same manner in 2022. After this period, data were processed with SPSS Statistics. Both Facebook and Google (Conversion Lift) provide A/B testing tools. The results suggest that standard retargeting ads are more effective in utilitarian browsing. In contrast, dynamic retargeting is more successful in reaching users in the hedonic environment of social networks. Moreover, the performance of retargeting ads evolves in the different stages along the customer journey. There are differences in the total number of tracked users in terms of the transition from the opt-out to the opt-in cookie regime. However, the performance of programmatic advertising appears moderately affected. AcknowledgmentThis work is supported by the Technology Agency of the Czech Republic under the Program of Applied Research ZETA through the Grant TJ02000206 – Developing the skills necessary for the digital business transformation.

Sentiment Analysis of Social Network Text Based on HDBSCAN and SO-PMI

With the rapid development of the Internet, the length and themes of text content in social network environments are becoming more and more abundant. The probability and degree of semantic similarity between different words in different texts are also increasing. It is difficult to effectively identify text topics and their sentiment tendencies. This paper takes the text data of the Ford Forum of the PCauto as the research object, builds a word vector model based on Word2vec, uses HDBSCAN to classify social network context, and calculates the sentiment value of different topic through SO-PMI. It aims to explore the complexity of the semantic evolution and feature extraction process and its generating text topics, based on which we further analyze the variability of sentiment tendencies between words and topics and then summarize their characteristics.

Deep learning-based credibility conversation detection approaches from social network.

In recent years, the social networks that have become most exploited sources of information, such as Facebook, Instagram, LinkedIn, and Twitter, have been considered the main sources of non-credible information. False information on these social networks has a negative impact on the credibility of conversations. In this article, we propose a new deep learning-based credibility conversation detection approach in social network environments, called CreCDA. CreCDA is based on: (i) the combination of post and user features in order to detect credible and non-credible conversations; (ii) the integration of multi-dense layers to represent features more deeply and to improve the results; (iii) sentiment calculation based on the aggregation of tweets. In order to study the performance of our approach, we have used the standard PHEME dataset. We compared our approach with the main approaches we have studied in the literature. The results of this evaluation show the effectiveness of sentiment analysis and the combination of text and user levels to analyze conversation credibility. We recorded the mean precision of credible and non-credible conversations at 79%, the mean recall at 79%, the mean F1-score at 79%, the mean accuracy at 81%, and the mean G-Mean at 79%.

Analysis of the Usage of Social Media for Marketing and Promotion

With the development of online information and network communication technology, the Internet is entering people's work and life. In recent years, as an emerging shopping method, online shopping has attracted more and more consumers for its fashion and convenience. In the past two years, live streaming and short videos have become the most important carriers of online marketing and communication activities. Among them, the network anchors represented by Internet celebrities and traffic stars either focus on content marketing, create scenes to endorse brands or use live streaming to bring goods. Different business models are tried in the industry, gradually forming a relatively complete live video industry chain. This article analyzes how businesses use social media for marketing and promotion from two aspects of how companies use social media for marketing and advertising. The paper focuses on the rapid development period of the Internet economy in the post-epidemic era. It analyzes the new way out of brand marketing, such as live streaming and delivery. Consumer groups love social media because of its social and interactive features, which reduce the cost of acquiring customers for brands. Finally, the article starts from two aspects of the social environment and network environment, summarizes the general environment of China's online shopping, and promotes the healthy development of China's online shopping.

Fake news detection: a systematic literature review of machine learning algorithms and datasets

Fake news (i.e., false news created to have a high capacity for dissemination and malicious intentions) is a problem of great interest to society today since it has achieved unprecedented political, economic, and social impacts. Taking advantage of modern digital communication and information technologies, they are widely propagated through social media, being their use intentional and challenging to identify. In order to mitigate the damage caused by fake news, researchers have been seeking the development of automated mechanisms to detect them, such as algorithms based on machine learning as well as the datasets employed in this development. This research aims to analyze the machine learning algorithms and datasets used in training to identify fake news published in the literature. It is exploratory research with a qualitative approach, which uses a research protocol to identify studies with the intention of analyzing them. As a result, we have the algorithms Stacking Method, Bidirectional Recurrent Neural Network (BiRNN), and Convolutional Neural Network (CNN), with 99.9%, 99.8%, and 99.8% accuracy, respectively. Although this accuracy is expressive, most of the research employed datasets in controlled environments (e.g., Kaggle) or without information updated in real-time (from social networks). Still, only a few studies have been applied in social network environments, where the most significant dissemination of disinformation occurs nowadays. Kaggle was the platform identified with the most frequently used datasets, being succeeded by Weibo, FNC-1, COVID-19 Fake News, and Twitter. For future research, studies should be carried out in addition to news about politics, the area that was the primary motivator for the growth of research from 2017, and the use of hybrid methods for identifying fake news.

THERMOLOGICAL PLURALISM AND INFORMATION DISORDER

The research points out the conditions that motivated the changes in the processes of dissemination of science, presenting the environment of digital social networks as unified spaces of scientific communication and dissemination. From this context, it seeks to show how these spaces are vulnerable to information disorder. To this end, the main factors related to disorder in the digital space were raised, especially in these processes, and some precautions that need to be considered to avoid or minimize this problem were indicated. This is a bibliographic research of a qualitative nature, which sought, from a literature review, inferences and interpretations, to connect the information disorder to the careless with the terminologies used in scientific communication and dissemination. It is considered that, so that the promotion of science mediated by social networks is not permeated by disorders, it is necessary for producers and disseminators of scientific content to consider that this space has peculiarities that combine a heterogeneous audience and a particular form of communication and dissemination.

Novel heuristic-based hybrid ResNeXt with recurrent neural network to handle multi class classification of sentiment analysis

Present-day, interdisciplinary research is increasing in social network-related applications, and it is a daily routine activity in every human life. So, sentiment analysis (SA) based on opinion mining is the most sophisticated concept in the well-known social network environment. Different machine learning methods were implemented to extract different text label features in SA, and all of those methods can detect whether a given text is positive or negative based on the text features. Analysis of sentiment has been suffering from inaccuracies while using machine learning and sentiment-based lexical methods dependent on domain-specific problems. Multi-class SA is an expensive task where memory, label samples, and other parameters are insufficient. So, we propose and implement a novel hybrid model which is a combination of ResNeXt and recurrent neural framework (NH-ResNeXt-RNF) to explore multi-class sentiment from textual features. This framework investigates the polarity of words connected to a specific domain across the entire dataset and eliminates noisy data in an unsupervised manner using pre-processing. Optimization is required to perform efficient multi-class classification to reduce the effort associated with annotation for multi-class SA via unsupervised learning. The proposed model performance is evaluated on two data sets namely: Amazon and Twitter. We increase the accuracy of the sentiment of polarity on each sentence present in the data set. Experimental results of the proposed approach give better and more efficient multi-class (positive, negative, very positive, neutral and highly negative) domain-specific sentiment than traditional approaches related to supervised, semi-supervised, and unsupervised domains. The proposed hybrid model accuracy is 96.5% and 95.37% for Amazon and Twitter datasets respectively.

Environmental Correlates of Physical Activity and Screen-Time in Youth with Autism Spectrum Disorder: A Seven-Country Observational Study.

This cross-sectional observational study sought to examine the environmental correlates of physical activity and screen-time among youth with autism spectrum disorder (ASD). Parents of youth with ASD (n = 1,165) from seven countries/regions provided responses to an online survey form measuring environmental correlates (i.e., physical activity neighborhood environment, social network, social trust and cohesion, bedroom media, social home environment) and outcomes (i.e., physical activity, screen-time). Multiple linear regression analyses were conducted to determine environmental predictors of the outcomes. Physical activity neighborhood environment (B = 0.15, p = 0.047), social network (B = 0.16, p = 0.02), and social home environment (B = 1.07, p < 0.001) were significantly associated with physical activity, whereas social trust and cohesion and bedroom media were not. Further, social trust and cohesion (B = -0.14, p = 0.001), bedroom media (B = 0.10, p = 0.001), and social home environment (B = -0.16, p < 0.001) were significantly associated with screen-time while neighborhood environment and social network were not. The identified environmental attributes of physical activity and screen-time behaviors should be targeted for health promotion among youth with ASD.