Stance classification with target-specific neural attention networks
- Submitting institution
-
The University of Warwick
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 6007
- Type
- E - Conference contribution
- DOI
-
10.24963/ijcai.2017/557
- Title of conference / published proceedings
- Twenty-Sixth International Joint Conference on Artificial Intelligence (IJCAI)
- First page
- 3988
- Volume
- -
- Issue
- -
- ISSN
- -
- Open access status
- -
- Month of publication
- August
- 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
-
3
- Research group(s)
-
I - Artificial Intelligence and Human-Centred Computing
- Citation count
- -
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Published in one of the two top AI conferences, the paper proposed a novel neural attention model for target-specific stance classification, which achieved the state-of-the-art results on both English and Chinese stance detection benchmarking datasets. It impacted work on topical stance detection on Twitter (Dey, IBM; Magdy, Edinburgh), stance detection in fake news classification (Yilmaz, UCL), stance detection in argumentative opinions (Mukherjee, Houston), and stance detection based on consistent cues (Weikum, Microsoft). It contributed to the award of the MSCA Fellowship "DeepPatient: Deep Understanding of Patient Experience of Healthcare from Social Media" (2018-2020, €183k).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -