Venue2Vec: An efficient embedding model for fine-grained user location prediction in geo-social networks
- Submitting institution
-
University of the West of England, Bristol
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 847017
- Type
- D - Journal article
- DOI
-
10.1109/JSYST.2019.2913080
- Title of journal
- IEEE Systems Journal
- Article number
- -
- First page
- 1740
- Volume
- 14
- Issue
- 2
- ISSN
- 1932-8184
- Open access status
- Compliant
- Month of publication
- May
- Year of publication
- 2019
- URL
-
http://dx.doi.org/10.1109/JSYST.2019.2913080
- 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
-
4
- Research group(s)
-
-
- Citation count
- 1
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper describes a novel embedding approach, Venue2Vec, that can be used to identify next and future geo-location check-ins, based on the subset of prior check-ins. We conduct experiments on three real-world GSN datasets to verify the performance of the proposed model, showing that accuracy can be improved compared to other similar models, and that runtime can be improved due to the model being parallelizable. The work has formed the basis for further research in this area that we are actively pursuing with relevant funders.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
