Long- and Short-Term Preference Modeling Based on Multi-Level Attention for Next POI Recommendation
The next point-of-interest (POI) recommendation is one of the most essential applications in location-based social networks (LBSNs). Its main goal is to research the sequential patterns of user check-in activities and then predict a user’s next destination. However, most previous studies have failed...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-05-01
|
| Series: | ISPRS International Journal of Geo-Information |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2220-9964/11/6/323 |
| _version_ | 1797486712151080960 |
|---|---|
| author | Xueying Wang Yanheng Liu Xu Zhou Zhaoqi Leng Xican Wang |
| author_facet | Xueying Wang Yanheng Liu Xu Zhou Zhaoqi Leng Xican Wang |
| author_sort | Xueying Wang |
| collection | DOAJ |
| description | The next point-of-interest (POI) recommendation is one of the most essential applications in location-based social networks (LBSNs). Its main goal is to research the sequential patterns of user check-in activities and then predict a user’s next destination. However, most previous studies have failed to make full use of spatio-temporal information to analyze user check-in periodic regularity, and some studies omit the user’s transition preference for the category at the POI semantic level. These are important for analyzing the user’s preference for check-in behavior. Long- and short-term preference modeling based on multi-level attention (LSMA) is put forward to solve the above problem and enhance the accuracy of the next POI recommendation. This can capture the user’s long-term and short-term preferences separately, and consider the multi-faceted utilization of spatio-temporal information. In particular, it can analyze the periodic hobbies contained in the user’s check-in. Moreover, a multi-level attention mechanism is designed to study the multi-factor dynamic representation of user check-in behavior and non-linear dependence between user check-ins, which can multi-angle and comprehensively explore a user’s check-in interest. We also study the user’s category transition preference at a coarse-grained semantic level to help construct the user’s long-term and short-term preferences. Finally, experiments were carried out on two real-world datasets; the findings showed that LSMA modeling outperformed state-of-the-art recommendation systems. |
| first_indexed | 2024-03-09T23:37:12Z |
| format | Article |
| id | doaj.art-9d90d6cf7ec84a258ff52ae6ccf47129 |
| institution | Directory Open Access Journal |
| issn | 2220-9964 |
| language | English |
| last_indexed | 2024-03-09T23:37:12Z |
| publishDate | 2022-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | ISPRS International Journal of Geo-Information |
| spelling | doaj.art-9d90d6cf7ec84a258ff52ae6ccf471292023-11-23T16:58:47ZengMDPI AGISPRS International Journal of Geo-Information2220-99642022-05-0111632310.3390/ijgi11060323Long- and Short-Term Preference Modeling Based on Multi-Level Attention for Next POI RecommendationXueying Wang0Yanheng Liu1Xu Zhou2Zhaoqi Leng3Xican Wang4College of Computer Science and Technology, Jilin University, Changchun 130012, ChinaCollege of Computer Science and Technology, Jilin University, Changchun 130012, ChinaKey Laboratory of Symbolic Computation and Knowledge Engineering, Ministry of Education, Jilin University, Changchun 130012, ChinaCollege of Software, Jilin University, Changchun 130012, ChinaCollege of Software, Jilin University, Changchun 130012, ChinaThe next point-of-interest (POI) recommendation is one of the most essential applications in location-based social networks (LBSNs). Its main goal is to research the sequential patterns of user check-in activities and then predict a user’s next destination. However, most previous studies have failed to make full use of spatio-temporal information to analyze user check-in periodic regularity, and some studies omit the user’s transition preference for the category at the POI semantic level. These are important for analyzing the user’s preference for check-in behavior. Long- and short-term preference modeling based on multi-level attention (LSMA) is put forward to solve the above problem and enhance the accuracy of the next POI recommendation. This can capture the user’s long-term and short-term preferences separately, and consider the multi-faceted utilization of spatio-temporal information. In particular, it can analyze the periodic hobbies contained in the user’s check-in. Moreover, a multi-level attention mechanism is designed to study the multi-factor dynamic representation of user check-in behavior and non-linear dependence between user check-ins, which can multi-angle and comprehensively explore a user’s check-in interest. We also study the user’s category transition preference at a coarse-grained semantic level to help construct the user’s long-term and short-term preferences. Finally, experiments were carried out on two real-world datasets; the findings showed that LSMA modeling outperformed state-of-the-art recommendation systems.https://www.mdpi.com/2220-9964/11/6/323next POI recommendationrecurrent neural networkLSTMattentional mechanismlocation-based social networks |
| spellingShingle | Xueying Wang Yanheng Liu Xu Zhou Zhaoqi Leng Xican Wang Long- and Short-Term Preference Modeling Based on Multi-Level Attention for Next POI Recommendation ISPRS International Journal of Geo-Information next POI recommendation recurrent neural network LSTM attentional mechanism location-based social networks |
| title | Long- and Short-Term Preference Modeling Based on Multi-Level Attention for Next POI Recommendation |
| title_full | Long- and Short-Term Preference Modeling Based on Multi-Level Attention for Next POI Recommendation |
| title_fullStr | Long- and Short-Term Preference Modeling Based on Multi-Level Attention for Next POI Recommendation |
| title_full_unstemmed | Long- and Short-Term Preference Modeling Based on Multi-Level Attention for Next POI Recommendation |
| title_short | Long- and Short-Term Preference Modeling Based on Multi-Level Attention for Next POI Recommendation |
| title_sort | long and short term preference modeling based on multi level attention for next poi recommendation |
| topic | next POI recommendation recurrent neural network LSTM attentional mechanism location-based social networks |
| url | https://www.mdpi.com/2220-9964/11/6/323 |
| work_keys_str_mv | AT xueyingwang longandshorttermpreferencemodelingbasedonmultilevelattentionfornextpoirecommendation AT yanhengliu longandshorttermpreferencemodelingbasedonmultilevelattentionfornextpoirecommendation AT xuzhou longandshorttermpreferencemodelingbasedonmultilevelattentionfornextpoirecommendation AT zhaoqileng longandshorttermpreferencemodelingbasedonmultilevelattentionfornextpoirecommendation AT xicanwang longandshorttermpreferencemodelingbasedonmultilevelattentionfornextpoirecommendation |