An Attention-Based Recommender System to Predict Contextual Intent Based on Choice Histories across and within Sessions
Recent years have witnessed the growth of recommender systems, with the help of deep learning techniques. Recurrent Neural Networks (RNNs) play an increasingly vital role in various session-based recommender systems, since they use the user’s sequential history to build a comprehensive use...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2018-11-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/8/12/2426 |
| _version_ | 1819266739559464960 |
|---|---|
| author | Ruo Huang Shelby McIntyre Meina Song Haihong E Zhonghong Ou |
| author_facet | Ruo Huang Shelby McIntyre Meina Song Haihong E Zhonghong Ou |
| author_sort | Ruo Huang |
| collection | DOAJ |
| description | Recent years have witnessed the growth of recommender systems, with the help of deep learning techniques. Recurrent Neural Networks (RNNs) play an increasingly vital role in various session-based recommender systems, since they use the user’s sequential history to build a comprehensive user profile, which helps improve the recommendation. However, a problem arises regarding how to be aware of the variation in the user’s contextual preference, especially the short-term intent in the near future, and make the best use of it to produce a precise recommendation at the start of a session. We propose a novel approach named Attention-based Short-term and Long-term Model (ASLM), to improve the next-item recommendation, by using an attention-based RNNs integrating both the user’s short-term intent and the long-term preference at the same time with a two-layer network. The experimental study on three real-world datasets and two sub-datasets demonstrates that, compared with other state-of-the-art methods, the proposed approach can significantly improve the next-item recommendation, especially at the start of sessions. As a result, our proposed approach is capable of coping with the cold-start problem at the beginning of each session. |
| first_indexed | 2024-12-23T21:06:04Z |
| format | Article |
| id | doaj.art-b28834ac78164b69aa993ec0419b60e1 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-12-23T21:06:04Z |
| publishDate | 2018-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-b28834ac78164b69aa993ec0419b60e12022-12-21T17:31:14ZengMDPI AGApplied Sciences2076-34172018-11-01812242610.3390/app8122426app8122426An Attention-Based Recommender System to Predict Contextual Intent Based on Choice Histories across and within SessionsRuo Huang0Shelby McIntyre1Meina Song2Haihong E3Zhonghong Ou4School of Computer Science, Beijing University of Posts & Telecommunications, Beijing 100876, ChinaLeavey School of Business, Santa Clara University, Santa Clara, CA 95053, USASchool of Computer Science, Beijing University of Posts & Telecommunications, Beijing 100876, ChinaSchool of Computer Science, Beijing University of Posts & Telecommunications, Beijing 100876, ChinaSchool of Computer Science, Beijing University of Posts & Telecommunications, Beijing 100876, ChinaRecent years have witnessed the growth of recommender systems, with the help of deep learning techniques. Recurrent Neural Networks (RNNs) play an increasingly vital role in various session-based recommender systems, since they use the user’s sequential history to build a comprehensive user profile, which helps improve the recommendation. However, a problem arises regarding how to be aware of the variation in the user’s contextual preference, especially the short-term intent in the near future, and make the best use of it to produce a precise recommendation at the start of a session. We propose a novel approach named Attention-based Short-term and Long-term Model (ASLM), to improve the next-item recommendation, by using an attention-based RNNs integrating both the user’s short-term intent and the long-term preference at the same time with a two-layer network. The experimental study on three real-world datasets and two sub-datasets demonstrates that, compared with other state-of-the-art methods, the proposed approach can significantly improve the next-item recommendation, especially at the start of sessions. As a result, our proposed approach is capable of coping with the cold-start problem at the beginning of each session.https://www.mdpi.com/2076-3417/8/12/2426session-based recommender systemattention mechanismcontextual user intentrecurrent neural network |
| spellingShingle | Ruo Huang Shelby McIntyre Meina Song Haihong E Zhonghong Ou An Attention-Based Recommender System to Predict Contextual Intent Based on Choice Histories across and within Sessions Applied Sciences session-based recommender system attention mechanism contextual user intent recurrent neural network |
| title | An Attention-Based Recommender System to Predict Contextual Intent Based on Choice Histories across and within Sessions |
| title_full | An Attention-Based Recommender System to Predict Contextual Intent Based on Choice Histories across and within Sessions |
| title_fullStr | An Attention-Based Recommender System to Predict Contextual Intent Based on Choice Histories across and within Sessions |
| title_full_unstemmed | An Attention-Based Recommender System to Predict Contextual Intent Based on Choice Histories across and within Sessions |
| title_short | An Attention-Based Recommender System to Predict Contextual Intent Based on Choice Histories across and within Sessions |
| title_sort | attention based recommender system to predict contextual intent based on choice histories across and within sessions |
| topic | session-based recommender system attention mechanism contextual user intent recurrent neural network |
| url | https://www.mdpi.com/2076-3417/8/12/2426 |
| work_keys_str_mv | AT ruohuang anattentionbasedrecommendersystemtopredictcontextualintentbasedonchoicehistoriesacrossandwithinsessions AT shelbymcintyre anattentionbasedrecommendersystemtopredictcontextualintentbasedonchoicehistoriesacrossandwithinsessions AT meinasong anattentionbasedrecommendersystemtopredictcontextualintentbasedonchoicehistoriesacrossandwithinsessions AT haihonge anattentionbasedrecommendersystemtopredictcontextualintentbasedonchoicehistoriesacrossandwithinsessions AT zhonghongou anattentionbasedrecommendersystemtopredictcontextualintentbasedonchoicehistoriesacrossandwithinsessions AT ruohuang attentionbasedrecommendersystemtopredictcontextualintentbasedonchoicehistoriesacrossandwithinsessions AT shelbymcintyre attentionbasedrecommendersystemtopredictcontextualintentbasedonchoicehistoriesacrossandwithinsessions AT meinasong attentionbasedrecommendersystemtopredictcontextualintentbasedonchoicehistoriesacrossandwithinsessions AT haihonge attentionbasedrecommendersystemtopredictcontextualintentbasedonchoicehistoriesacrossandwithinsessions AT zhonghongou attentionbasedrecommendersystemtopredictcontextualintentbasedonchoicehistoriesacrossandwithinsessions |