Mining Influentials and their Bot Activities on Twitter Campaigns

TL;DR

This paper presents a comprehensive methodology for analyzing Twitter campaigns, focusing on identifying influential users and bot activities, demonstrated through the 2017 German federal election case study.

Contribution

It introduces a novel, multi-step approach combining topic detection, scientometrics, user interest modeling, and influence scoring to analyze Twitter campaigns and detect bots.

Findings

Effective identification of influential users using adapted PageRank

Successful detection of bot-like activities through metrics and visualization

Demonstrated methodology on the 2017 German federal election campaign

Abstract

Twitter is increasingly used for political, advertising and marketing campaigns, where the main aim is to influence users to support specific causes, individuals or groups. We propose a novel methodology for mining and analyzing Twitter campaigns, which includes: (i) collecting tweets and detecting topics relating to a campaign; (ii) mining important campaign topics using scientometrics measures; (iii) modelling user interests using hashtags and topical entropy; (iv) identifying influential users using an adapted PageRank score; and (v) various metrics and visualization techniques for identifying bot-like activities. While this methodology is generalizable to multiple campaign types, we demonstrate its effectiveness on the 2017 German federal election.