Detecting Real-World Influence Through Twitter

TL;DR

This paper explores methods to identify real-world influence of Twitter users by analyzing account features and applying machine learning techniques, outperforming existing ranking approaches on a benchmark dataset.

Contribution

It introduces novel machine learning approaches using NLP and social network analysis to accurately detect influential Twitter users, challenging traditional metrics.

Findings

Traditional metrics like followers and Klout score are ineffective.

Proposed methods outperform state-of-the-art ranking techniques.

Effective influence prediction achieved on CLEF RepLab 2014 dataset.

Abstract

In this paper, we investigate the issue of detecting the real-life influence of people based on their Twitter account. We propose an overview of common Twitter features used to characterize such accounts and their activity, and show that these are inefficient in this context. In particular, retweets and followers numbers, and Klout score are not relevant to our analysis. We thus propose several Machine Learning approaches based on Natural Language Processing and Social Network Analysis to label Twitter users as Influencers or not. We also rank them according to a predicted influence level. Our proposals are evaluated over the CLEF RepLab 2014 dataset, and outmatch state-of-the-art ranking methods.