Research on the Optimization of Collaborative Filtering Algorithm Based on the Fusion of Multidimensional Content Features: Application to Music Recommendation Systems
Abstract
recommendation systems has become an urgent problem to be solved. As one of the core algorithms of recommendation systems, collaborative filtering, despite its remarkable recommendation effects, is still affected by data sparsity and cold start problems in practical applications.
This study proposes an optimized collaborative filtering algorithm that integrates music content features (styles, beats, chords, etc.), and combines deep learning methods to achieve implicit feature mining. At the same time, a dynamic weight adjustment mechanism is designed to enhance the recommendation performance. The experimental results show that the optimized algorithm significantly outperforms the traditional
collaborative filtering method in terms of indicators such as recommendation accuracy, recall rate, and diversity, providing a theoretical basis
and technical support for the design of personalized recommendation systems on digital music platforms.
Keywords
Full Text:
PDFReferences
[1] Li Xiaoju. Research on Data Sparsity and Cold Start Problems in Collaborative Filtering Recommendation Systems [D]. East China
Normal University, 2018.
[2] Xu Lu. Research and Application of Collaborative Filtering Algorithm Based on Similarity Improvement [D]. Dalian Jiaotong University, 2023. DOI: 10.26990/d.cnki.gsltc.2023.000790.
[3] Zhao Yuanshang, Lin Weifang. Research on Typical Scenarios Based on the Fusion of Pearson Correlation Coefficient, Density Peak
and Entropy Weight Method [J]. Electric Power in China, 2023, 56(05): 193-202.
[4] Yan Haiwei, Lin Chunhua, Xu Huanxiao, et al. Research on Music Recommendation Algorithm Based on Apriori Algorithm [J]. Computer Programming Skills & Maintenance, 2025, (02): 49-52. DOI: 10.16184/j.cnki.comprg.2025.02.040.R. Nicole, Title of paper with
only first word capitalized, J. Name Stand. Abbrev., in press.
[5] Zhuang Yan. Research on Music Genre Classification Based on Acoustic Features and Music Features [D]. Jiangnan University, 2014.
[6] Li Yuanjie. Research on Social Recommendation Algorithm Integrating Bias Information and Bilateral Implicit Relationships [D]. Anhui
Jianzhu University, 2023. DOI: 10.27784/d.cnki.gahjz.2023.000206.
[7] Li Zheng, Huang Bo, Wang Chenming, et al. Meta-path Recommendation Algorithm of Knowledge Graph Embedding Based on Heterogeneous Attention Network [J/OL]. Journal of University of Electronic Science and Technology of China, 1-14 [2025-04-08].
[8] Ren Rui, Li Ying, Yang Yali, et al. Review of POI Recommendation Algorithm Research [J/OL]. Computer Engineering and Applications, 1 - 17[20250410]. http://kns.cnki.net/kcms/detail/11.2127.TP.20250213.1106.006.html.
[9] Yue Weiyi. Design of Smart Recommendation System Based on Big Data and Cloud Computing [J]. Electronic Technology, 2024,
53(07): 274-275.
[10] Huang Min, Tao Sunjie. Research on QoE Measurement of Combat Cloud Services [J]. Command Control & Simulation, 2022, 44(02):
116-121.
DOI: http://dx.doi.org/10.70711/aitr.v2i9.6871
Refbacks
- There are currently no refbacks.
