Discourse-aware rumour stance classification in social media using sequential classifiers
- Submitting institution
-
The University of Sheffield
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 2499
- Type
- D - Journal article
- DOI
-
10.1016/j.ipm.2017.11.009
- Title of journal
- Information Processing & Management
- Article number
- -
- First page
- 273
- Volume
- 54
- Issue
- 2
- ISSN
- 0306-4573
- Open access status
- Compliant
- Month of publication
- December
- Year of publication
- 2017
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
7
- Research group(s)
-
D - Natural Language Processing
- Citation count
- 20
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- The first paper to take discourse context into account in detecting stance in online conversations about rumours. It builds on work published at A*-rated ACL'2016 (71 citations) and WWW'2015 (46 citations) conferences. This research was an output of the PHEME EU project (FP7-ICT-611233), one of the first projects to study computational methods for detecting and tracking online disinformation, and rated “outstanding” by the expert FP7 reviewer panel. It led to new impact-generating collaborations with Nesta https://www.nesta.org.uk/blog/introducing-the-political-futures-tracker/ and Buzzfeed https://www.buzzfeed.com/tomphillips/twitter-abuse-of-mps-during-the-election-doubled-after-the
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -