Spatial-temporal distance metric embedding for time-specific POI recommendation
With the growing popularity of location-based social networks (LBSNs), time-specific POI recommendation has become important in recent years, which provides more accurate recommendation services for users in specific spatio–temporal contexts. In this paper, we propose a spatio–temporal distance metr...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2018
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/89331 http://hdl.handle.net/10220/47032 |
| _version_ | 1826112522334240768 |
|---|---|
| author | Ding, Ruifeng Chen, Zhenzhong Li, Xiaolei |
| author2 | School of Computer Science and Engineering |
| author_facet | School of Computer Science and Engineering Ding, Ruifeng Chen, Zhenzhong Li, Xiaolei |
| author_sort | Ding, Ruifeng |
| collection | NTU |
| description | With the growing popularity of location-based social networks (LBSNs), time-specific POI recommendation has become important in recent years, which provides more accurate recommendation services for users in specific spatio–temporal contexts. In this paper, we propose a spatio–temporal distance metric embedding model (ST-DME) for time–specific recommendation, which exploits both temporal and geo-sequential property of a check-in to effectively model users’ time-specific preferences. Specifically, we divide timestamps of user’ check-ins into different time slots and adopt Euclidean distance rather than inner product of latent vectors to measure users’ preferences for POIs in a given time slot. We also apply a transition coefficient based on users’ most recent check-ins to incorporate geo-sequential influence in users’ check-in behaviors. A weighted pairwise loss with a hard sampling strategy is adopted to optimize latent vectors of users, POIs, and time slots in a metric space. Extensive experiments are conducted to demonstrate the effectiveness of our proposed method and results show that ST-DME outperforms state-of-the-art algorithms for time-specific POI recommendation on two public LBSNs data sets. |
| first_indexed | 2024-10-01T03:08:25Z |
| format | Journal Article |
| id | ntu-10356/89331 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T03:08:25Z |
| publishDate | 2018 |
| record_format | dspace |
| spelling | ntu-10356/893312020-03-07T11:49:00Z Spatial-temporal distance metric embedding for time-specific POI recommendation Ding, Ruifeng Chen, Zhenzhong Li, Xiaolei School of Computer Science and Engineering Location-based Social Networks DRNTU::Engineering::Computer science and engineering Time-specific POI Recommendation With the growing popularity of location-based social networks (LBSNs), time-specific POI recommendation has become important in recent years, which provides more accurate recommendation services for users in specific spatio–temporal contexts. In this paper, we propose a spatio–temporal distance metric embedding model (ST-DME) for time–specific recommendation, which exploits both temporal and geo-sequential property of a check-in to effectively model users’ time-specific preferences. Specifically, we divide timestamps of user’ check-ins into different time slots and adopt Euclidean distance rather than inner product of latent vectors to measure users’ preferences for POIs in a given time slot. We also apply a transition coefficient based on users’ most recent check-ins to incorporate geo-sequential influence in users’ check-in behaviors. A weighted pairwise loss with a hard sampling strategy is adopted to optimize latent vectors of users, POIs, and time slots in a metric space. Extensive experiments are conducted to demonstrate the effectiveness of our proposed method and results show that ST-DME outperforms state-of-the-art algorithms for time-specific POI recommendation on two public LBSNs data sets. Published version 2018-12-18T02:41:08Z 2019-12-06T17:23:04Z 2018-12-18T02:41:08Z 2019-12-06T17:23:04Z 2018 Journal Article Ding, R., Chen, Z., & Li, X. (2018). Spatial-temporal distance metric embedding for time-specific POI recommendation. IEEE Access, 6, 67035-67045. doi: 10.1109/ACCESS.2018.2869994 https://hdl.handle.net/10356/89331 http://hdl.handle.net/10220/47032 10.1109/ACCESS.2018.2869994 en IEEE Access © 2018 IEEE. Translations and content mining are permitted for academic research only. Personal use is also permitted, but republication/redistribution requires IEEE permission. See http://www.ieee.org/publications_standards/publications/rights/index.html for more information. 11 p. application/pdf |
| spellingShingle | Location-based Social Networks DRNTU::Engineering::Computer science and engineering Time-specific POI Recommendation Ding, Ruifeng Chen, Zhenzhong Li, Xiaolei Spatial-temporal distance metric embedding for time-specific POI recommendation |
| title | Spatial-temporal distance metric embedding for time-specific POI recommendation |
| title_full | Spatial-temporal distance metric embedding for time-specific POI recommendation |
| title_fullStr | Spatial-temporal distance metric embedding for time-specific POI recommendation |
| title_full_unstemmed | Spatial-temporal distance metric embedding for time-specific POI recommendation |
| title_short | Spatial-temporal distance metric embedding for time-specific POI recommendation |
| title_sort | spatial temporal distance metric embedding for time specific poi recommendation |
| topic | Location-based Social Networks DRNTU::Engineering::Computer science and engineering Time-specific POI Recommendation |
| url | https://hdl.handle.net/10356/89331 http://hdl.handle.net/10220/47032 |
| work_keys_str_mv | AT dingruifeng spatialtemporaldistancemetricembeddingfortimespecificpoirecommendation AT chenzhenzhong spatialtemporaldistancemetricembeddingfortimespecificpoirecommendation AT lixiaolei spatialtemporaldistancemetricembeddingfortimespecificpoirecommendation |