English

应用科学学报 >

2025 , Vol. 43 >Issue 2: 222 - 233

DOI: https://doi.org/10.3969/j.issn.0255-8297.2025.02.003

通信工程

基于用户画像相似性的电影评分预测模型

展开
  • 上海理工大学 光电信息与计算机工程学院, 上海 200093

收稿日期: 2022-12-09

  网络出版日期: 2025-04-03

基金资助

国家自然科学基金（No.61803264）资助

收起

A Movie Rating Prediction Model Leveraging User Profile Similarity

Expand
  • School of Optical-Electrical and Computer Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China

Received date: 2022-12-09

  Online published: 2025-04-03

Fold

摘要

协同过滤算法在推荐算法中应用广泛，如何实现用户聚类并发现更相似的邻居集合一直是协同过滤推荐算法的研究重点。为了有效提高该类算法分类和预测的准确性，本文提出了一种基于用户画像相似性的电影推荐算法。首先，基于电影内容特征的标签集合，计算用户评分在不同电影内容标签上的频数，建立基于电影内容标签的用户偏好画像矩阵。然后通过该矩阵计算用户间的相似性并进行用户复杂网络建模，计算用户在该网络中的中心性权重。最后，结合用户网络K-core分解得到用户网络的社区权重，并利用邻居用户的中心性权重和社区权重改进评分预测。实验结果表明，该算法在评测指标预测准确性和分类准确性上分别提高2.72%和3.17%，验证了基于用户画像相似性进行复杂网络建模对推荐系统信息利用的有效性。

关键词： 用户画像; 协同过滤; 相似性; 复杂网络; 分类准确性

本文引用格式

艾均, 李明浩, 苏湛 . 基于用户画像相似性的电影评分预测模型[J]. 应用科学学报, 2025 , 43(2) : 222 -233 . DOI: 10.3969/j.issn.0255-8297.2025.02.003

Abstract

Collaborative filtering algorithms are widely used in recommendation systems, with a key research focus on how to achieve effective user clustering and identify more accurate sets of similar neighbors. One of the key research focuses is to achieve user clustering and identify more similar neighbor sets. To enhance the accuracy of classification and prediction in these algorithms, this paper proposes a movie recommendation algorithm based on user profile similarity. First, based on a tag set of movie content features, a user preference profile matrix is constructed by calculating the frequency of user ratings among different movie content tags. Then, user similarity is calculated through this matrix, and a user complex network is modeled to determine the centrality weight of users within the network. Finally, the community weight is obtained through K-core decomposition of the user network. The rating predictions are improved by integrating the centrality weight and community weight of neighboring users. Experimental results show that the proposed algorithm improves prediction accuracy and classification accuracy by 2.72% and 3.17%, respectively. These results validate the effectiveness of complex network modeling based on user profile similarity for enhancing information utilization in recommendation systems.

Key words： user profile; collaborative filtering; similarity; complex network; classification accuracy

参考文献

[1] Darban Z Z, Valipour M H. GHRS: graph-based hybrid recommendation system with application to movie recommendation [J]. Expert Systems with Applications, 2022, 200: 116850.
[2] Jena K K, Bhoi S K, Mallick C, et al. Neural model based collaborative filtering for movie recommendation system [J]. International Journal of Information Technology, 2022: 1-11.
[3] Zhang T T, Liu S N. Hybrid music recommendation algorithm based on music gene and improved knowledge graph [DB/OL]. 2022[2022-12-09]. https://doi.org/10.1155/2022/5889724.
[4] Schedl M, Knees P, Mcfee B, et al. Music recommendation systems: techniques, use cases, and challenges [M]//Recommender Systems Handbook, Springer, 2022.
[5] Wu C, Wu F, Qi T, et al. Feedrec: news feed recommendation with various user feedbacks [DB/OL]. 2021[2022-12-09]. https://arxiv.org/abs/2102.04903.
[6] Naghiaei M, Rahmani H A, Dehghan M. The unfairness of popularity bias in book recommendation [DB/OL]. 2022[2022-12-09]. https://doi.org/10.48550/arXiv.2202.13446.
[7] Gao C, Lei W, He X, et al. Advances and challenges in conversational recommender systems: a survey [DB/OL]. 2021[2022-12-09]. https://doi.org/10.48550/arXiv.2101.09459.
[8] 贾丹, 孙静宇. 基于用户会话的TF-Ranking推荐方法[J]. 应用科学学报, 2021, 39(3): 495-507. Jia D, Sun J Y. TF-Ranking recommendation method based on user session [J]. Journal of Applied Sciences, 2021, 39(3): 495-507. (in Chinese)
[9] Wu L, He X, Wang X, et al. A survey on accuracy-oriented neural recommendation: from collaborative filtering to information-rich recommendation [J]. IEEE Transactions on Knowledge and Data Engineering, 2023, 35(5): 4425-4445.
[10] Koren Y, Rendle S, Bell R. Advances in collaborative filtering [M]//Recommender Systems Handbook, Springer, 2022.
[11] Zhang F, Bai L, Gao F. A user trust-based collaborative filtering recommendation algorithm [C]//International Conference on Information and Communications Security, 2009: 411-424.
[12] Sarwar B, Karypis G, Konstan J, et al. Item-based collaborative filtering recommendation algorithms [C]//10th International Conference on World Wide Web, 2001: 285-295.
[13] Javed U, Shaukat K, Hameed I A, et al. A review of content-based and context-based recommendation systems [J]. International Journal of Emerging Technologies in Learning, 2021, 16(3): 274-306.
[14] Jalili M, Ahmadian S, Izadi M, et al. Evaluating collaborative filtering recommender algorithms: a survey [J]. IEEE Access, 2018, 6: 74003-74024.
[15] 季德强, 王海荣, 车淼. KNN-GWD推荐模型及其应用[J]. 应用科学学报, 2022, 40(1): 145-154. Ji D Q, Wang H R, Che M. KNN-GWD recommendation model and its application [J]. Journal of Applied Sciences, 2022, 40(1): 145-154. (in Chinese)
[16] Su X, Khoshgoftaar T M. A survey of collaborative filtering techniques [DB/OL]. 2009[2022-12-09]. https://doi.org/10.1155/2009/421425.
[17] Widiyaningtyas T, Hidayah I, Adji T B. User profile correlation-based similarity (UPCSim) algorithm in movie recommendation system [J]. Journal of Big Data, 2021, 8(1): 1-21.
[18] Xu H, Hou R, Yang N, et al. Kitchen appliance recommendation based on user profile and interest evolution network [C]//IEEE Advanced Information Technology, Electronic and Automation Control Conference (IAEAC), 2021: 2096-2100.
[19] Pan Y, Huo Y, Tang J, et al. Exploiting relational tag expansion for dynamic user profile in a tag-aware ranking recommender system [J]. Information Sciences, 2021, 545: 448-464.
[20] Li Z, Zhang L. Fast neighbor user searching for neighborhood-based collaborative filtering with hybrid user similarity measures [J]. Soft Computing, 2021, 25(7): 5323-5338.
[21] Polatidis N, Georgiadis C K. A multi-level collaborative filtering method that improves recommendations [J]. Expert Systems with Applications, 2016, 48: 100-110.
[22] Su Z, Lin Z, Ai J, et al. Rating prediction in recommender systems based on user behavior probability and complex network modeling [J]. IEEE Access, 2021, 9: 30739-30749.
[23] Ahmadian S, Afsharchi M, Meghdadi M. An effective social recommendation method based on user reputation model and rating profile enhancement [J]. Journal of Information Science, 2019, 45(5): 607-642.
[24] Jiang L C, Liu R R, Jia C X. User-location distribution serves as a useful feature in itembased collaborative filtering [J]. Physica A: Statistical Mechanics and Its Applications, 2022, 586: 126491.
[25] Singh P K, Sinha M, Das S, et al. Enhancing recommendation accuracy of item-based collaborative filtering using Bhattacharyya coefficient and most similar item [J]. Applied Intelligence, 2020, 50(12): 4708-4731.
[26] Mehal A S, Meena K, Singh R B, et al. Movie genres and beyond: an analytical survey of classification techniques [C]//5th International Conference on Trends in Electronics and Informatics, 2021: 1193-1198.
[27] Harper F M, Konstan J A. The movielens datasets: history and context [J]. ACM Transactions on Interactive Intelligent Systems, 2015, 5(4): 1-19.
[28] De Campos L M, Fernández-Luna J M, Huete J F, et al. Group recommending: a methodological approach based on Bayesian networks [C]// IEEE 23rd International Conference on Data Engineering Workshop, 2007: 835-844.
[29] Ai J, Liu Y, Su Z, et al. K-core decomposition in recommender systems improves accuracy of rating prediction [J]. International Journal of Modern Physics C, 2021, 32(7): 2150087.
[30] Ai J, Liu Y, Su Z, et al. Link prediction in recommender systems based on multi-factor network modeling and community detection [J]. Europhysics Letters, 2019, 126(3): 38003.
[31] Jaramillo-Garzón J A, Castellanos-Domínguez C G. Improving protein sub-cellular localization prediction through semi-supervised learning [C]//16th International Conference on Bioinformatics, Biocomputational Systems and Biotechnologies, 2014: 99-103.
[32] Ai J, Cai Y, Su Z, et al. Predicting user-item links in recommender systems based on similaritynetwork resource allocation [J]. Chaos, Solitons & Fractals, 2022, 158: 112032.
[33] Ai J, Li L, Su Z, et al. Online-rating prediction based on an improved opinion spreading approach [C]//29th Chinese Control and Decision Conference (CCDC), 2017: 1457-1460.
[34] Lee S. Using entropy for similarity measures in collaborative filtering [J]. Journal of Ambient Intelligence and Humanized Computing, 2020, 11(1): 363-374.
[35] Madadipouya K, Chelliah S. A literature review on recommender systems algorithms, techniques and evaluations [J]. BRAIN. Broad Research in Artificial Intelligence and Neuroscience, 2017, 8(2): 109-124.
[36] Billsus D, Pazzani M J, et al. Learning collaborative information filters [C]//Recommender Systems Workshop, American Association for Artificial Intelligence (AAAI), 1998: 46-54.
[37] Castells P, Hurley N, Vargas S. Novelty and diversity in recommender systems [M]//Recommender Systems Handbook. Springer, 2022.
[38] Shani G, Gunawardana A. Evaluating recommendation systems [M]//Recommender Systems Handbook. Springer, 2011.
Options
文章导航

/

〈 〉