Topic-based influential user detection: a survey

Abstract

Online Social networks have become an easy means of communication for users to share their opinion on various topics, including breaking news, public events, and products. The content posted by a user can influence or affect other users, and the users who could influence or affect a high number of users are called influential users. Identifying such influential users has a wide range of applications in the field of marketing, including product advertisement, recommendation, and brand evaluation. However, the users’ influence varies in different topics, and hence a tremendous interest has been shown towards identifying topic-based influential users over the past few years. Topic-level information in the content posted by the users can be used in various stages of the topic-based influential user detection (IUD) problem, including data gathering, construction of influence network, quantifying the influence between two users, and analyzing the impact of the detected influential user. This has opened up a wide range of opportunities to utilize the existing techniques to model and analyze the topic-level influence in online social networks. In this paper, we perform a comprehensive study of existing techniques used to infer the topic-based influential users in online social networks. We present a detailed review of these approaches in a taxonomy while highlighting the challenges and limitations associated with each technique. Moreover, we perform a detailed study of different evaluation techniques used in the literature to overcome the challenges that arise in evaluating topic-based IUD approaches. Furthermore, closely related research topics and open research questions in topic-based IUD are discussed to provide a deep understanding of the literature and future directions.

Analyzing the worldwide perception of the Russia-Ukraine conflict through Twitter

“…The comparison between Botometer and BotRGCN revealed an interesting detail regarding the distribution of tweets that can be associated with humans or bots. In fact, in spite of the fact that BotRGCN conducts an exclusively binary classification, we can see that when we add up the number of tweets associated with bots by Botometer (11,244), with those by BotRGCN (11,818), we are faced with sufficiently comparable numbers. However, compared to tweets that are instead linked to Human accounts, the numbers differ by no small margin (16,860 from Botometer VS 23,137 from BotRGCN).…”

“…In recent years, social networks have attracted the attention of many users who use them not only for communication purposes, but also for following topic-specific discussions [11] expressing their viewpoints on global events [12,13]. Moreover, social media networks have been found to be useful in supporting early warning systems for disaster relief agencies to obtain rapid disaster assessments.…”

Generating Attribute Similarity Graphs: A User Behavior-Based Approach from Real- Time Microblogging Data on Platform X

“…Followers receive noti cations from the user, and their interaction with the user's tweets can enhance the user's reach and in uence. The number of a user's followers is equivalent to the in-degree of the corresponding node in a graph, which can be used as a measure to comprehend the spread of information within online social networks (Panchendrarajan & Saxena, 2023).…”

Recognition of opinion leaders in blockchain-based social networks by structural information and content contribution

“…The blockchain social network allows users to achieve self-control of information, encourages users to generate high-quality content and spreads quality content by communicating with other users ( Zhan, Xiong & Xing, 2023 ). Therefore, it is crucial to analyze the behavioral characteristics generated by users in the interaction process and identify influential users ( Panchendrarajan & Saxena, 2022 ). In the process of information dissemination, influential opinion leaders have a great impact on other users and lead the public opinion ( Bamakan, Nurgaliev & Qu, 2019 ).…”