|
|
|
| Dynamic Movie Recommendation Considering Long-Term and Short-Term Interest and Its Evolution |
Liu Rui1,Chen Ye2( ) |
1School of Information Management, Central China Normal University, Wuhan 430079, China
2School of Information Management, Nanjing University, Nanjing 210023, China |
|
|
|
|
Abstract [Objective] This paper proposes a personalized dynamic recommendation model for movies. It considered the evolution of long-term interest and short-term interest, capturing the dynamic changes of users’ interests to improve the accuracy of recommendation. [Methods] Firstly, users’ interest is divided into the long-term interest and the short-term interest based on their psychological motivation. And then the model used interest rating and attention frequency to calculate the interest values. Secondly, the model combined the time window with the forgetting function to obtain the time weight. The short-term interest value and the time weight are combined to reflect the evolution of short-term interest. Finally, the model constructed a user-project scoring matrix to predict the score of target user, by integrating the movie score with the long-term and the short-term interest values. [Results] Taking the data set of Douban as an example, the score prediction error of the method was smaller overall than that of other recommendation methods, and it performed best on MAE (1.0031) and RMSE (1.2160), and the number of neighbors is 20 when reaching the optimal values of MAE and RMSE. [Limitations] The explicit feedback information and the implicit feedback information are needed to calculate long-term and short-term interest values, so the computational complexity of the proposed method is relatively high. [Conclusions] The recommendation method can accurately capture the dynamic change of user interest, effectively reduce the error of score prediction, and improve the accuracy of recommendation.
|
|
Received: 06 November 2022
Published: 30 March 2023
|
|
|
| Fund:National Natural Science Foundation of China(72274077);National Natural Science Foundation of China(71904057) |
|
Corresponding Authors:
Chen Ye，ORCID：0000-0002-7619-3246，E-mail：chenye@nju.edu.cn。
|
| [1] |
Cai Y, Leung H F, Li Q, et al. Typicality-Based Collaborative Filtering Recommendation[J]. IEEE Transactions on Knowledge and Data Engineering, 2014, 26(3): 766-779.
doi: 10.1109/TKDE.2013.7
|
| [2] |
Pazzani M J, Billsus D. Content-Based Recommendation Systems[A]//The Adaptive Web[M]. Berlin, Heidelberg: Springer, 2007: 325-341.
|
| [3] |
Burke R. Hybrid Recommender Systems: Survey and Experiments[J]. User Modeling and User-Adapted Interaction, 2002, 12(4): 331-370.
doi: 10.1023/A:1021240730564
|
| [4] |
王明佳, 韩景倜. 基于用户对项目属性偏好的协同过滤算法[J]. 计算机工程与应用, 2017, 53(6): 106-110.
doi: 10.3778/j.issn.1002-8331.1610-0381
|
| [4] |
(Wang Mingjia, Han Jingti. Collaborative Filtering Algorithm Based on Item Attribute Preference[J]. Computer Engineering and Applications, 2017, 53(6): 106-110.)
doi: 10.3778/j.issn.1002-8331.1610-0381
|
| [5] |
Hu Y T, Xiong F, Lu D Y, et al. Movie Collaborative Filtering with Multiplex Implicit Feedbacks[J]. Neurocomputing, 2020, 398: 485-494.
doi: 10.1016/j.neucom.2019.03.098
|
| [6] |
Bhalse N, Thakur R. WITHDAWN: Algorithm for Movie Recommendation System Using Collaborative Filtering[J]. Materials Today: Proceedings, DOI: 10.1016/j.matpr.2021.01.235.
|
| [7] |
Xu Y S, Yin J W. Collaborative Recommendation with User Generated Content[J]. Engineering Applications of Artificial Intelligence, 2015, 45: 281-294.
doi: 10.1016/j.engappai.2015.07.012
|
| [8] |
蒋武轩, 易明, 汪玲. 融合用户兴趣漂移特征的个性化推荐研究[J]. 情报理论与实践, 2022, 45(1): 38-45.
doi: 10.16353/j.cnki.1000-7490.2022.01.006
|
| [8] |
(Jiang Wuxuan, Yi Ming, Wang Ling. Research on Personalized Recommendation Combining User Interest Drift[J]. Information Studies: Theory & Application, 2022, 45(1): 38-45.)
doi: 10.16353/j.cnki.1000-7490.2022.01.006
|
| [9] |
陆航, 师智斌, 刘忠宝. 融合用户兴趣和评分差异的协同过滤推荐算法[J]. 计算机工程与应用, 2020, 56(7): 24-29.
doi: 10.3778/j.issn.1002-8331.1909-0129
|
| [9] |
(Lu Hang, Shi Zhibin, Liu Zhongbao. Collaboration Filtering Recommendation Algorithm Based on User Interest and Ratings Difference[J]. Computer Engineering and Applications, 2020, 56(7): 24-29.)
doi: 10.3778/j.issn.1002-8331.1909-0129
|
| [10] |
王维, 高岭, 高全力. 融合用户信任和用户兴趣漂移的协同过滤算法[J]. 微电子学与计算机, 2019, 36(7): 103-108.
|
| [10] |
(Wang Wei, Gao Ling, Gao Quanli. Collaborative Filtering Algorithm Based on User Trust and Interest Drift Detecting[J]. Microelectronics & Computer, 2019, 36(7): 103-108.)
|
| [11] |
Li J, Xu W T, Wan W B, et al. Movie Recommendation Based on Bridging Movie Feature and User Interest[J]. Journal of Computational Science, 2018, 26: 128-134.
doi: 10.1016/j.jocs.2018.03.009
|
| [12] |
Zhang P F, Zhang Z J, Tian T, et al. Collaborative Filtering Recommendation Algorithm Integrating Time Windows and Rating Predictions[J]. Applied Intelligence, 2019, 49(8): 3146-3157.
doi: 10.1007/s10489-019-01443-2
|
| [13] |
Luo L, Xie H R, Rao Y H, et al. Personalized Recommendation by Matrix Co-factorization with Tags and Time Information[J]. Expert Systems with Applications, 2019, 119:311-321.
doi: 10.1016/j.eswa.2018.11.003
|
| [14] |
Ahmadian S, Joorabloo N, Jalili M, et al. Alleviating Data Sparsity Problem in Time-Aware Recommender Systems Using a Reliable Rating Profile Enrichment Approach[J]. Expert Systems with Applications, 2022, 187: 115849.
doi: 10.1016/j.eswa.2021.115849
|
| [15] |
吕学强, 王腾, 李雪伟, 等. 基于内容和兴趣漂移模型的电影推荐算法研究[J]. 计算机应用研究, 2018, 35(3): 717-720, 802.
|
| [15] |
(Lyu Xueqiang, Wang Teng, Li Xuewei, et al. Research on Movie Recommendation Algorithm Based on Content and Interest Drift Model[J]. Application Research of Computers, 2018, 35(3): 717-720, 802.)
|
| [16] |
Hu L M, Li C, Shi C, et al. Graph Neural News Recommendation with Long-term and Short-term Interest Modeling[J]. Information Processing & Management, 2020, 57(2): 102142.
doi: 10.1016/j.ipm.2019.102142
|
| [17] |
Du Y P, Peng Z, Niu J Y, et al. A Unified Hierarchical Attention Framework for Sequential Recommendation by Fusing Long and Short-Term Preferences[J]. Expert Systems with Applications, 2022, 201: 117102.
doi: 10.1016/j.eswa.2022.117102
|
| [18] |
Xu Y, Li Y, Yang W, et al. A Multi-factor Influencing POI Recommendation Model Based on Matrix Factorization[C]// Proceedings of the 10th International Conference on Advanced Computational Intelligence. 2018: 514-519.
|
| [19] |
张爱卿. 论人类行为的动机——一种新的动机理论构理[J]. 华东师范大学学报(教育科学版), 1996, 14(1): 71-80.
|
| [19] |
Zhang Aiqing. On the Motivation of Human Behavior — A New Motivation Theory Structure[J]. Journal of East China Normal University (Educational Sciences), 1996, 14(1): 71-80.)
|
| [20] |
李则然. 院线纪录片受众观影动机与行为研究[D]. 广州: 华南理工大学, 2020.
|
| [20] |
(Li Zeran. Study on the Motivation and Behavior of Cinematic Documentary Audience[D]. Guangzhou: South China University of Technology, 2020.)
|
| [21] |
池建宇. 演员与导演谁更重要——中国电影票房明星效应的实证研究[J]. 新闻界, 2016(21): 36-41.
|
| [21] |
(Chi Jianyu. Who’s More Important, the Actor or the Director—An Empirical Study on the Box Office Star Effect of Chinese Movies[J]. Journalism and Mass Communication, 2016(21): 36-41.)
|
| [22] |
梁勰珣. 行为经济学视角下中国电影票房的“粉丝效应”研究[D]. 长沙: 湖南大学, 2020.
|
| [22] |
(Liang Xiexun. Research on the “Fan Effect” of Chinese Film Box Office from the Perspective of Behavioral Economics[D]. Changsha: Hunan University, 2020.)
|
| [23] |
Sandvoss C. Challenging Boundaries:Fans and Cultural Industries[A]// The Routledge Companion to the Cultural Industries[M]. New York: Routledge, 2015.
|
| [24] |
曾耀农. 试论电影观众心理[J]. 社会科学家, 1995(6): 47-53.
|
| [24] |
(Zeng Yaonong. On the Psychology of Movie Audience[J]. Social Scientist Maim Contents, 1995(6): 47-53.)
|
| [25] |
李伟卿, 池毛毛, 王伟军. 面向用户长短期偏好调节的可解释个性化推荐方法研究[J]. 图书情报工作, 2021, 65(12): 101-111.
doi: 10.13266/j.issn.0252-3116.2021.12.010
|
| [25] |
(Li Weiqing, Chi Maomao, Wang Weijun. Explainable Personalized Recommendation Method Based on Adjustment of Users’ Long- and Short-Term Preferences[J]. Library and Information Service, 2021, 65(12): 101-111.)
doi: 10.13266/j.issn.0252-3116.2021.12.010
|
| [26] |
王微微, 夏秀峰, 李晓明. 一种基于用户行为反馈的兴趣度模型更新算法[J]. 辽宁大学学报(自然科学版), 2011, 38(1): 40-45.
|
| [26] |
Wang Weiwei, Xia Xiufeng, Li Xiaoming. A Personal Interest Degree Model Updating Algorithm Based on Consumer Behavior Feedback[J]. Journal of Liaoning University (Natural Sciences Edition), 2011, 38(1): 40-45.)
|
| [27] |
王军, 张子柯. 基于社会化标签信息熵的个性化推荐算法[J]. 图书情报工作, 2013, 57(23): 31-35.
doi: 10.7536/j.issn.0252-3116.2013.23.005
|
| [27] |
(Wang Jun, Zhang Zike. A Personalized Recommendation Algorithm Based on Information Entropy of Social Tags[J]. Library and Information Service, 2013, 57(23): 31-35.)
doi: 10.7536/j.issn.0252-3116.2013.23.005
|
| [28] |
喻頔. 基于用户兴趣与时间效应相融合的个性化推荐算法研究与应用[D]. 湛江: 广东海洋大学, 2021.
|
| [28] |
(Yu Di. Research on Personalized Recommendation Algorithm Based on Combining User’s Interest with Time Effect and Its Application[D]. Zhanjiang: Guangdong Ocean University, 2021.)
|
| [29] |
Zhang Y F, Lai G K, Zhang M, et al. Explicit Factor Models for Explainable Recommendation Based on Phrase-Level Sentiment Analysis[C]// Proceedings of the 37th International ACM SIGIR Conference on Research & Development in Information Retrieval. 2014: 83-92.
|
| [30] |
Deshpande M, Karypis G. Item-Based Top-N Recommendation Algorithms[J]. ACM Transactions on Information Systems, 2004, 22(1): 143-177.
doi: 10.1145/963770.963776
|
| [31] |
Liu H F, Hu Z, Mian A, et al. A New User Similarity Model to Improve the Accuracy of Collaborative Filtering[J]. Knowledge-Based Systems, 2014, 56(C): 156-166.
|
| [32] |
蔡晓娟, 谭文安. 一种改进的融合相似度和信任度的协同过滤算法[J]. 计算机科学, 2022, 49(S1): 238-241.
|
| [32] |
(Cai Xiaojuan, Tan Wenan. Improved Collaborative Filtering Algorithm Combining Similarity and Trust[J]. Computer Science, 2022, 49(S1): 238-241.)
|
| [33] |
于洪, 李转运. 基于遗忘曲线的协同过滤推荐算法[J]. 南京大学学报(自然科学版), 2010, 46(5): 520-527.
|
| [33] |
Yu Hong, Li Zhuanyun. A Collaborative Filtering Recommendation Algorithm Based on Forgetting Curve[J]. Journal of Nanjing University (Natural Sciences), 2010, 46(5): 520-527.)
|
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
| |
Shared |
|
|
|
|
| |
Discussed |
|
|
|
|
