Lexicon based feature extraction for emotion text classification.
- Submitting institution
-
Robert Gordon University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- Massie_1
- Type
- D - Journal article
- DOI
-
10.1016/j.patrec.2016.12.009
- Title of journal
- Pattern Recognition Letters
- Article number
- -
- First page
- 133
- Volume
- 93
- Issue
- -
- ISSN
- 1872-7344
- Open access status
- Compliant
- Month of publication
- December
- Year of publication
- 2016
- 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
-
-
- Research group(s)
-
-
- Citation count
- 32
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This novel feature extraction approach used for building domain specific emotion lexicons has had commercial impact with Bandhakavi (www.linkedin.com/in/anil-bandhakavi) applying the approach with London-based start-up company SentiSum (CEO: sharad@sentisum.com), and contributing to their gaining $700k seed funding (Sept 2017) via crunchbase (www.crunchbase.com/funding_round/sentisum-seed--8420c344). The work continues to underpin subsequent research funding awards including a £430k award from OGIC (18OP_19 AI Automated Regulatory Compliance) that employs a similar approach for text representation of regulatory compliance documents.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -