A time-aware trajectory embedding model for next-location recommendation
Next-location recommendation is an emerging task with the proliferation of location-based services. It is the task of recommending the next location to visit for a user, given her past check-in records. Although several principled solutions have been proposed for this task, existing studies have not...
| Main Authors: | , , , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2020
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/139251 |
| _version_ | 1811682536235991040 |
|---|---|
| author | Zhao, Wayne Xin Zhou, Ningnan Sun, Aixin Wen, Ji-Rong Han, Jialong Chang, Edward Y. |
| author2 | School of Computer Science and Engineering |
| author_facet | School of Computer Science and Engineering Zhao, Wayne Xin Zhou, Ningnan Sun, Aixin Wen, Ji-Rong Han, Jialong Chang, Edward Y. |
| author_sort | Zhao, Wayne Xin |
| collection | NTU |
| description | Next-location recommendation is an emerging task with the proliferation of location-based services. It is the task of recommending the next location to visit for a user, given her past check-in records. Although several principled solutions have been proposed for this task, existing studies have not well characterized the temporal factors in the recommendation. From three real-world datasets, our quantitative analysis reveals that temporal factors play an important role in next-location recommendation, including the periodical temporal preference and dynamic personal preference. In this paper, we propose a Time-Aware Trajectory Embedding Model (TA-TEM) to incorporate three kinds of temporal factors in next-location recommendation. Based on distributed representation learning, the proposed TA-TEM jointly models multiple kinds of temporal factors in a unified manner. TA-TEM also enhances the sequential context by using a longer context window. Experiments show that TA-TEM outperforms several competitive baselines. |
| first_indexed | 2024-10-01T03:58:24Z |
| format | Journal Article |
| id | ntu-10356/139251 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T03:58:24Z |
| publishDate | 2020 |
| record_format | dspace |
| spelling | ntu-10356/1392512020-05-18T06:52:09Z A time-aware trajectory embedding model for next-location recommendation Zhao, Wayne Xin Zhou, Ningnan Sun, Aixin Wen, Ji-Rong Han, Jialong Chang, Edward Y. School of Computer Science and Engineering Engineering::Computer science and engineering Next-location Recommendation Distributed Representation Learning Next-location recommendation is an emerging task with the proliferation of location-based services. It is the task of recommending the next location to visit for a user, given her past check-in records. Although several principled solutions have been proposed for this task, existing studies have not well characterized the temporal factors in the recommendation. From three real-world datasets, our quantitative analysis reveals that temporal factors play an important role in next-location recommendation, including the periodical temporal preference and dynamic personal preference. In this paper, we propose a Time-Aware Trajectory Embedding Model (TA-TEM) to incorporate three kinds of temporal factors in next-location recommendation. Based on distributed representation learning, the proposed TA-TEM jointly models multiple kinds of temporal factors in a unified manner. TA-TEM also enhances the sequential context by using a longer context window. Experiments show that TA-TEM outperforms several competitive baselines. 2020-05-18T06:52:08Z 2020-05-18T06:52:08Z 2017 Journal Article Zhao, W. X., Zhou, N., Sun, A., Wen, J.-R., Han, J., & Chang, E. Y. (2018). A time-aware trajectory embedding model for next-location recommendation. Knowledge and Information Systems, 56(3), 559-579. doi:10.1007/s10115-017-1107-4 0219-1377 https://hdl.handle.net/10356/139251 10.1007/s10115-017-1107-4 2-s2.0-85030562483 3 56 559 579 en Knowledge and Information Systems © 2017 Springer-Verlag London Ltd. All rights reserved. |
| spellingShingle | Engineering::Computer science and engineering Next-location Recommendation Distributed Representation Learning Zhao, Wayne Xin Zhou, Ningnan Sun, Aixin Wen, Ji-Rong Han, Jialong Chang, Edward Y. A time-aware trajectory embedding model for next-location recommendation |
| title | A time-aware trajectory embedding model for next-location recommendation |
| title_full | A time-aware trajectory embedding model for next-location recommendation |
| title_fullStr | A time-aware trajectory embedding model for next-location recommendation |
| title_full_unstemmed | A time-aware trajectory embedding model for next-location recommendation |
| title_short | A time-aware trajectory embedding model for next-location recommendation |
| title_sort | time aware trajectory embedding model for next location recommendation |
| topic | Engineering::Computer science and engineering Next-location Recommendation Distributed Representation Learning |
| url | https://hdl.handle.net/10356/139251 |
| work_keys_str_mv | AT zhaowaynexin atimeawaretrajectoryembeddingmodelfornextlocationrecommendation AT zhouningnan atimeawaretrajectoryembeddingmodelfornextlocationrecommendation AT sunaixin atimeawaretrajectoryembeddingmodelfornextlocationrecommendation AT wenjirong atimeawaretrajectoryembeddingmodelfornextlocationrecommendation AT hanjialong atimeawaretrajectoryembeddingmodelfornextlocationrecommendation AT changedwardy atimeawaretrajectoryembeddingmodelfornextlocationrecommendation AT zhaowaynexin timeawaretrajectoryembeddingmodelfornextlocationrecommendation AT zhouningnan timeawaretrajectoryembeddingmodelfornextlocationrecommendation AT sunaixin timeawaretrajectoryembeddingmodelfornextlocationrecommendation AT wenjirong timeawaretrajectoryembeddingmodelfornextlocationrecommendation AT hanjialong timeawaretrajectoryembeddingmodelfornextlocationrecommendation AT changedwardy timeawaretrajectoryembeddingmodelfornextlocationrecommendation |