Modeling Topic-Specific Influential Users in QA Forums Using Association Rule Mining

• Published in: IEEE access Vol. 12; pp. 196498 - 196516
• Main Authors: Ishfaq, Umar, Ali, Tassawar, Daud, Ali, Alreshoodi, Mohammed, Irshad, Azeem
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2024; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Association rule learning; classification; Clustering algorithms; Data mining; Datasets; Decision support systems; deep learning; influential users; Itemsets; Message systems; Prediction algorithms; QA forum; social network analysis; Social networking (online); Social networks; StackOverflow; System effectiveness; Technological innovation; Text mining
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2024.3517702

Social networks have enabled the exchange of information that has accelerated the diffusion of online content. Social networks offer multiple forms of social interaction that facilitate users in generating online content. The increasing popularity of social networks has attracted many researchers to investigate their impact on users and confirmed significant influence of social networks on markets, social life, and politics. Therefore, identification of the influential users in social networks has become a popular research area due to several of its applications in diverse domains such as e-commerce, viral marketing, political campaigns etc. However, earlier research either consider linguistic content or utilize network-based representation for finding the influential users in social networks. This paper incorporates association rule mining (ARM) based algorithms, that are mostly used for market-basket analysis, for exploring the behavior of users and predict their participation in social interactions. The study identifies topic-based influential users using Apriori and FPGrowth on the dataset of a popular online question-answer community. In addition, the study employs standard evaluation metrics such as confidence, support, lift, and conviction for computing association rules. Subsequently, the obtained results are validated using conventional measures including accuracy, precision, and recall in accordance with the perspective of association rules. The experiments are performed on multiple social networking datasets and the obtained results prove the visibility and quality of the proposed method against well-established degree centrality, PageRank, and HITS. In addition, the results validate the effectiveness of ARM in identifying influential users in social networks. The generated rule set can help create efficient decision support systems that are becoming prevalent in providing solutions to real-world problems.