A Deep Recurrent Collaborative Filtering Framework for Venue Recommendation
- Submitting institution
-
University of Glasgow
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 11-09898
- Type
- E - Conference contribution
- DOI
-
10.1145/3132847.3133036
- Title of conference / published proceedings
- 26th ACM International Conference on Information and Knowledge Management (CIKM 2017)
- First page
- 1429
- Volume
- -
- Issue
- -
- ISSN
- -
- Open access status
- -
- Month of publication
- -
- Year of publication
- 2017
- URL
-
http://eprints.gla.ac.uk/147487/
- 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)
-
-
- Citation count
- 21
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- ORIGINALITY: First known work that applies deep learning techniques to venue recommendation. Proposes new and effective sequence-aware sampling methods that capture the order of users' venue visits and their geographical locations during learning, addressing 6 limitations of existing approaches. RIGOUR: Extensive experiments using 3 large-scale real-world datasets from location-based social networks, and demonstrate that our approach improves over 7 existing baselines. SIGNIFICANCE: Published in a top IR conference. Improved performance over the existing state-of-the-art by 23%. Hence this work has significant possible impact for improving the recommendations made by location-based social networks such as TripAdvisor, Google Maps, Facebook and Foursquare.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -