Contextual Attention Recurrent Architecture for Context-aware Venue Recommendation
- Submitting institution
-
University of Glasgow
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 11-02737
- Type
- E - Conference contribution
- DOI
-
10.1145/3209978.3210042
- Title of conference / published proceedings
- 41st International ACM SIGIR Conference on Research and Development in Information Retrieval
- First page
- 555
- Volume
- -
- Issue
- -
- ISSN
- -
- Open access status
- -
- Month of publication
- June
- Year of publication
- 2018
- URL
-
http://eprints.gla.ac.uk/160908/
- 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: Proposes a new form of gated recurrent neural-net architecture that learns how to weight data on successive user time/location information (checkins), to deliver substantially improved recommendations about nearby venues for users to visit (restaurants, etc.). RIGOUR: Experiments using 3 real-world datasets with millions of user checkins. Our neural network architecture addresses 5 limitations of existing approaches. SIGNIFICANCE: Published at the premier IR conference and already highly cited. Achieves state-of-the-art performances across the 3 used datasets. This work has a significant possible impact for improving recommendations made by popular location-based social networks eg. TripAdvisor, Google Maps, Facebook, Foursquare.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -