Dual memory network model for sentiment analysis of review text
- Submitting institution
-
University of Nottingham, The
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 2647405
- Type
- D - Journal article
- DOI
-
10.1016/j.knosys.2019.105004
- Title of journal
- Knowledge-Based Systems
- Article number
- 105004
- First page
- -
- Volume
- 188
- Issue
- -
- ISSN
- 0950-7051
- Open access status
- Compliant
- Month of publication
- September
- Year of publication
- 2019
- 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
- Yes
- Number of additional authors
-
7
- Research group(s)
-
-
- Citation count
- 0
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Our dual learning model for sentiment analysis provides performance gain when compared with current models, achieved using separate memory networks to learn user profiles and product information for review classification. This work has consolidated an international research network between the UK, USA, Hong Kong and China and an ongoing industry collaboration with online service provider Kooth.com. Ramifications from this initial work have attracted external funding from URRA HDI Network+ and NIHR.
Kooth contact: Aaron Sefi, Aaron@Kooth.com, Research Director
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
