A Social Curiosity Inspired Recommendation Model to Improve Precision, Coverage and Diversity
- Submitting institution
-
Swansea University / Prifysgol Abertawe
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 49639
- Type
- E - Conference contribution
- DOI
-
10.1109/WI.2016.0042
- Title of conference / published proceedings
- 2016 IEEE/WIC/ACM International Conference on Web Intelligence (WI)
- First page
- 240
- Volume
- -
- Issue
- -
- ISSN
- -
- Open access status
- -
- 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
- 5
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- A subtle and elusive concept in predicting users’ interests is the concept of social curiosity. The paper builds the first computational model of curiosity considering socially connected users’ behaviours in recommender systems. The experiments based on large-scale real datasets demonstrate that the incorporation of social curiosity significantly improves the performance of recommender systems in terms of precision, coverage, and diversity. The paper won the best paper award in the IEEE/WIC/ACM international Conference on Web Intelligence in 2016, and led to collaborations with Alibaba, one of the most famous e-commerce platforms worldwide.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -