Extraction of Influencers Across Twitter Using Credibility and Trend Analysis

Abstract

Influence maximization facilitates in selection of individuals that can help in diffusing the information to maximum people in least time. Credible individuals are selected based on twitter or influencer score. This paper proposes a novel method to find the influencers. Scoring is computed using the features of individuals. Generally these features are based on activity; authority and audience of a user on twitter. First, influence score of a person has been computed using the features like retweets, followers, posts etc. Second, tweet score is computed. For tweet score, user tweets are mined to find their opinion about the subject. Further, Trend score is computed using the opinion of public that are extracted by textual data mining to get better insight about the subject in context. Finally, both influence score and tweet score of a person are correlated with the trend score to infer the final influencers.