Personalized project recommendations: using reinforcement learning
Abstract With the development of the Internet and the progress of human-centered computing (HCC), the mode of man-machine collaborative work has become more and more popular. Valuable information in the Internet, such as user behavior and social labels, is often provided by users. A recommendation b...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2019-12-01
|
| Series: | EURASIP Journal on Wireless Communications and Networking |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s13638-019-1619-6 |
| _version_ | 1819274961436540928 |
|---|---|
| author | Faxin Qi Xiangrong Tong Lei Yu Yingjie Wang |
| author_facet | Faxin Qi Xiangrong Tong Lei Yu Yingjie Wang |
| author_sort | Faxin Qi |
| collection | DOAJ |
| description | Abstract With the development of the Internet and the progress of human-centered computing (HCC), the mode of man-machine collaborative work has become more and more popular. Valuable information in the Internet, such as user behavior and social labels, is often provided by users. A recommendation based on trust is an important human-computer interaction recommendation application in a social network. However, previous studies generally assume that the trust value between users is static, unable to respond to the dynamic changes of user trust and preferences in a timely manner. In fact, after receiving the recommendation, there is a difference between actual evaluation and expected evaluation which is correlated with trust value. Based on the dynamics of trust and the changing process of trust between users, this paper proposes a trust boost method through reinforcement learning. Recursive least squares (RLS) algorithm is used to learn the dynamic impact of evaluation difference on user’s trust. In addition, a reinforcement learning method Deep Q-Learning (DQN) is studied to simulate the process of learning user’s preferences and boosting trust value. Experiments indicate that our method applied to recommendation systems could respond to the changes quickly on user’s preferences. Compared with other methods, our method has better accuracy on recommendation. |
| first_indexed | 2024-12-23T23:16:45Z |
| format | Article |
| id | doaj.art-18f56c0da775408c9dcf5e9bd616ed6a |
| institution | Directory Open Access Journal |
| issn | 1687-1499 |
| language | English |
| last_indexed | 2024-12-23T23:16:45Z |
| publishDate | 2019-12-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | EURASIP Journal on Wireless Communications and Networking |
| spelling | doaj.art-18f56c0da775408c9dcf5e9bd616ed6a2022-12-21T17:26:28ZengSpringerOpenEURASIP Journal on Wireless Communications and Networking1687-14992019-12-012019111710.1186/s13638-019-1619-6Personalized project recommendations: using reinforcement learningFaxin Qi0Xiangrong Tong1Lei Yu2Yingjie Wang3School of Computer and Control Engineering, Yantai UniversitySchool of Computer and Control Engineering, Yantai UniversitySchool of Computer and Control Engineering, Yantai UniversitySchool of Computer and Control Engineering, Yantai UniversityAbstract With the development of the Internet and the progress of human-centered computing (HCC), the mode of man-machine collaborative work has become more and more popular. Valuable information in the Internet, such as user behavior and social labels, is often provided by users. A recommendation based on trust is an important human-computer interaction recommendation application in a social network. However, previous studies generally assume that the trust value between users is static, unable to respond to the dynamic changes of user trust and preferences in a timely manner. In fact, after receiving the recommendation, there is a difference between actual evaluation and expected evaluation which is correlated with trust value. Based on the dynamics of trust and the changing process of trust between users, this paper proposes a trust boost method through reinforcement learning. Recursive least squares (RLS) algorithm is used to learn the dynamic impact of evaluation difference on user’s trust. In addition, a reinforcement learning method Deep Q-Learning (DQN) is studied to simulate the process of learning user’s preferences and boosting trust value. Experiments indicate that our method applied to recommendation systems could respond to the changes quickly on user’s preferences. Compared with other methods, our method has better accuracy on recommendation.https://doi.org/10.1186/s13638-019-1619-6HCCReinforcement learningTrustRLSDQN |
| spellingShingle | Faxin Qi Xiangrong Tong Lei Yu Yingjie Wang Personalized project recommendations: using reinforcement learning EURASIP Journal on Wireless Communications and Networking HCC Reinforcement learning Trust RLS DQN |
| title | Personalized project recommendations: using reinforcement learning |
| title_full | Personalized project recommendations: using reinforcement learning |
| title_fullStr | Personalized project recommendations: using reinforcement learning |
| title_full_unstemmed | Personalized project recommendations: using reinforcement learning |
| title_short | Personalized project recommendations: using reinforcement learning |
| title_sort | personalized project recommendations using reinforcement learning |
| topic | HCC Reinforcement learning Trust RLS DQN |
| url | https://doi.org/10.1186/s13638-019-1619-6 |
| work_keys_str_mv | AT faxinqi personalizedprojectrecommendationsusingreinforcementlearning AT xiangrongtong personalizedprojectrecommendationsusingreinforcementlearning AT leiyu personalizedprojectrecommendationsusingreinforcementlearning AT yingjiewang personalizedprojectrecommendationsusingreinforcementlearning |