Bootstrap Domain-Specific Sentiment Classifiers from Unlabeled Corpora
- Submitting institution
-
Birkbeck College
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 172
- Type
- D - Journal article
- DOI
-
10.1162/tacl_a_00020
- Title of journal
- Transactions of the Association for Computational Linguistics
- Article number
- -
- First page
- 269-285
- Volume
- 6
- Issue
- -
- ISSN
- 2307-387X
- Open access status
- Compliant
- Month of publication
- -
- Year of publication
- 2018
- URL
-
http://eprints.bbk.ac.uk/id/eprint/22000/
- 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
-
2
- Research group(s)
-
2 - Experimental Data Science
- Citation count
- -
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This journal paper enhances the hybrid lexicon and machine learning based sentiment classifier described by the authors in the Workshop on Issues of Sentiment Discovery and Opinion Mining (WISDOM@KDD), 2012. That paper has 215+ Google Scholar citations (it was not returned to REF 2014 as it reported on work still in progress). The software is available at https://www.dcs.bbk.ac.uk/~andrius/psenti/.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -