University of Birmingham > Talks@bham > Artificial Intelligence and Natural Computation seminars > Rumour Stance and Veracity Classification in Social Media Conversations

Rumour Stance and Veracity Classification in Social Media Conversations

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Hector Basevi.

Host: Dr Harish Madabushi

Abstract: Automatic resolution of rumours is a challenging task that can be broken down into smaller components that make up a pipeline, including rumour detection, rumour tracking and stance classification, leading to the final outcome of determining the veracity of a rumour. Stance classification implies determining the attitude of responses discussing a rumour towards its veracity. We consider a set of rumours circulating on Twitter from a publicly available dataset and classify tweets discussing them into supporting, denying, questioning or commenting the underlying rumours. We explore the benefits of exploiting the conversational structure of the Twitter threads in stance classification, considering and comparing different representations for the conversations. Also, we study the relations between these tasks in rumour resolution pipeline, as patterns of support and denial can be indicative of the final veracity label. In previous work, these steps in the process of rumour verification have been developed as separate components where the output of one feeds into the next. We propose a multi-task learning approach that allows joint training of the main and auxiliary tasks, improving the performance of rumour verification. We examine the connection between the dataset properties and the outcomes of the multi-task learning models used.

Biography: I am, Elena Kochkina, a final year PhD student in Computer Science supervised by Dr. Maria Liakata and Prof. Rob Procter. I am affiliated with the Warwick Institute for the Science of Cities (WISC) CDT and funded by the Leverhulme Trust via the Bridges Programme. I am also a visiting student at the Alan Turing Institute in London. My background is Applied Mathematics (BSc, MSc) and Complexity Science (MSc).


This talk is part of the Artificial Intelligence and Natural Computation seminars series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.


Talks@bham, University of Birmingham. Contact Us | Help and Documentation | Privacy and Publicity.
talks@bham is based on from the University of Cambridge.