Expert ranking techniques for online rated forums. (November 2019)

• Record Type: Journal Article
• Authors: Faisal, Muhammad Shahzad; Daud, Ali; Akram, Abubakr Usman; Abbasi, Rabeeh Ayaz; Aljohani, Naif Radi; Mehmood, Irfan
• Is Part Of: Computers in human behavior. Volume 100(2019)
• Page Start: 168
• Page End: 176
• Publication Date: 2019-11
• Subjects: Expert finding -- Online rated forums -- StackOverflow -- Information retrieval -- Social media; Interactive computer systems -- Periodicals; Man-machine systems -- Periodicals; 004.019
• DOI: 10.1016/j.chb.2018.06.013
• Languages: English
• ISSNs: 0747-5632

Abstract

Abstract: Web 2.0 or social web applications such as online discussion forums, blogs and Wikipedia have improved knowledge sharing by providing an environment in which users can generate and find their favorite content in, a flexible way. With the passage of time, online discussion forums accumulate a huge amount of content and this can introduce issues of content quality and user credibility. A poor-quality answer in a discussion forum indicates the presence of unprofessional or unqualified users; therefore, a priority is to find experts or reputable users. Most of the existing expert-ranking approaches consider basic features, such as the total number of answers provided by a user, but ignore the quality and consistency of the user's answer. In this paper, expert-ranking techniques using g-index are proposed, and are applied to a StackOverflow forum dataset. Three techniques are proposed including Exp-PC, Rep-FS and Weighted Exp-PC. Exp-PC is an adaptation of g-index for ranking experts in StackOverflow forum. In Rep-FS, several features like voters reputation, vote ratio are proposed to measure users' expertise while Weighted Exp-PC computes user expertise by combining their Exp-PC and Rep-FS scores. We measure users' reputation and expertise according to both the quality of their answer and their consistency in providing quality answers. The experimental results of the proposed expert-ranking techniques, Exp-PC and Weighted Exp-PC in particular, validate that these methods identify genuine experts in a more effective way. Highlights: Proposal of Exp-PC and REP-FS techniques for ranking experts. Exp-PC considers users consistency in providing quality answers. Usage of large benchmark StackOverflow dataset for evaluation purposes. Performance evaluation in terms of standard ranking performance measures.