Combining Deep Learning and Argumentative Reasoning for the Analysis of Social Media Textual Content Using Small Data Sets
- Submitting institution
-
King's College London
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 137654696
- Type
- E - Conference contribution
- DOI
-
10.1162/coli_a_00338
- Title of conference / published proceedings
- COMPUTATIONAL LINGUISTICS
- First page
- 833
- Volume
- 44
- Issue
- 4
- ISSN
- 0891-2017
- Open access status
- Compliant
- Month of publication
- December
- Year of publication
- 2018
- 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
-
1
- Research group(s)
-
-
- Citation count
- 7
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Extending a preliminary version published at EMNLP2017, this paper is the first to show how computational argumentation can be used for detecting deceptive product reviews by integrating deep learning for argument mining with symbolic, argumentative reasoning. The paper shows, experimentally, that the novel argumentative features also perform well on small datasets. The paper led to the organisation of a series of workshops on fact extraction and verification (FEVER https://fever.ai/) at NLP conferences: EMNLP2018, EMNLP2019, ACL2020, and to an invited talk at INRIA Wimmics team (https://team.inria.fr/wimmics/seminars/).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
