Real-World Witness Detection in Social Media via Hybrid Crowdsensing

Authors

  • Stefano Cresci Institute of Informatics and Telematics-CNR
  • Andrea Cimino Institute of Computational Linguistics-CNR
  • Marco Avvenuti University of Pisa
  • Maurizio Tesconi Institute of Informatics and Telematics-CNR
  • Felice Dell'Orletta Institute of Computational Linguistics-CNR

DOI:

https://doi.org/10.1609/icwsm.v12i1.15072

Keywords:

witness detection, crowdsensing, machine learning, Twitter

Abstract

The task of witness detection in social media is crucial for many practical applications, including rumor debunking, emergency management, and public opinion mining. Yet to date, it has been approached in an approximated way. We propose a method for addressing witness detection in a strict and realistic fashion. By employing hybrid crowdsensing over Twitter, we contact real-life witnesses and use their reactions to build a strong ground-truth, thus avoiding a manual, subjective annotation of the dataset. Using this dataset, we develop a witness detection system based on a machine learning classifier using a wide set of linguistic features and metadata associated with the tweets.

Downloads

Published

2018-06-15

How to Cite

Cresci, S., Cimino, A., Avvenuti, M., Tesconi, M., & Dell’Orletta, F. (2018). Real-World Witness Detection in Social Media via Hybrid Crowdsensing. Proceedings of the International AAAI Conference on Web and Social Media, 12(1). https://doi.org/10.1609/icwsm.v12i1.15072