Social influence analysis in microblogging platforms – A topic-sensitive based approach

Article type: Research Article

Authors: Cano, Amparo E.^; | Mazumdar, Suvodeep | Ciravegna, Fabio

Affiliations: Department of Computer Science, The University of Sheffield, Sheffield, United Kingdom. E-mail: {firstinitial.surname}@dcs.shef.ac.uk

Note: [] Corresponding author. E-mail: [email protected].

Abstract: The use of Social Media, particularly microblogging platforms such as Twitter, has proven to be an effective channel for promoting ideas to online audiences. In a world where information can bias public opinion it is essential to analyse the propagation and influence of information in large-scale networks. Recent research studying social media data to rank users by topical relevance have largely focused on the “retweet”, “following” and “mention” relations. In this paper we propose the use of semantic profiles for deriving influential users based on the retweet subgraph of the Twitter graph. We introduce a variation of the PageRank algorithm for analysing users' topical and entity influence based on the topical/entity relevance of a retweet relation. Experimental results show that our approach outperforms related algorithms including HITS, InDegree and Topic-Sensitive PageRank. We also introduce VisInfluence, a visualisation platform for presenting top influential users based on a topical query need.

Keywords: Social awareness streams, microblogging, social influence, semantic profiles

DOI: 10.3233/SW-130108

Journal: Semantic Web, vol. 5, no. 5, pp. 357-372, 2014