Please wait a minute...
Data Analysis and Knowledge Discovery  2023, Vol. 7 Issue (7): 136-145    DOI: 10.11925/infotech.2096-3467.2022.0712
Current Issue | Archive | Adv Search |
Hybrid Recommendation with Category Preferences and Item Timeliness Factor
Yang Huaizhen1,Zhang Jing1,Li Lei2()
1Business School, Guilin University of Electronic Technology, Guilin 541004, China
2Business School, Guilin University of Technology, Guilin 541004, China
Download: PDF (1192 KB)   HTML ( 10 ) 
Export: BibTeX | EndNote (RIS)      
Abstract  

[Objective] This paper addresses the influence of historical data sparsity, category preference, and item timeliness on the performance of recommendation algorithms and improves their accuracy. [Methods] Firstly, we used Huffman Coding to encode the rating data with category preference and item popularity. Then, we computed the score similarity matrices of users and projects. We also extracted their latent feature vectors using the DeepWalk model. Finally, we fused the user and project feature vectors and predicted the project ratings with Extreme Learning Machines. [Results] We examined the new model on the MovieLens and Yahoo! R3 datasets. As the proportion of the training set increased, the highest prediction accuracies reached 95.52% and 98.01%, respectively, with a runtime of only 19.93s and 22.21s. The proposed algorithm outperformed the XGB-CF algorithm in terms of prediction by 0.84 and 2.10 percentage points, respectively, with a runtime reduction of 7.92s and 9.79s. [Limitations] The proposed algorithm did not consider the textual information from user comments and diversified project categories. [Conclusions] Our new algorithm demonstrates higher prediction accuracy than the reference algorithm and can be used for personalized recommendations.
Key words： Hybrid Recommendation      Project Timeliness Factor      Extreme Learning Machine      Category Preference     
Received: 11 July 2022      Published: 07 September 2023
ZTFLH:  TP391  
Fund:National Natural Science Foundation of China(72074058);National Natural Science Foundation of China(71562008);Innovation Project of Guangxi Graduate Education(YCBZ2022112)
Corresponding Authors: Li Lei，ORCID：0009-0002-8268-6239，E-mail： lileiguilin@foxmail.com。   
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
Huaizhen Yang
Jing Zhang
Lei Li

Cite this article:

Yang Huaizhen, Zhang Jing, Li Lei. Hybrid Recommendation with Category Preferences and Item Timeliness Factor. Data Analysis and Knowledge Discovery, 2023, 7(7): 136-145.

URL:

https://manu44.magtech.com.cn/Jwk_infotech_wk3/EN/10.11925/infotech.2096-3467.2022.0712     OR     https://manu44.magtech.com.cn/Jwk_infotech_wk3/EN/Y2023/V7/I7/136

The Framework of the Hybrid Recommendation Algorithm
类别 标签 类别 标签
Comedy 1 Western 7
Adventure 2 Horror 8
Fantasy 3 Action 9
Mystery 4 Sci-Fi 10
Thriller 5 Crime 11
War 6 Romance 12
Movie Categories and Their Labels
The Process of the Random Walk
Accuracy of ELM under Different Similarity Functions of Training Sets with Different Proportions
Prediction Accuracy of Different Numbers of Neurons in Different Hidden Layers
MAE and PA of the Proposed Model in Different Dimensions
训练集比例 MAE
λ =0.6 λ =0.7 λ =0.8 λ =0.9
0.2 1.301 8 1.100 1 1.014 0 1.223 2
0.4 1.105 8 1.005 6 0.998 5 1.019 0
0.6 1.005 8 0.998 5 0.858 9 0.849 8
0.8 0.885 6 0.786 5 0.709 8 0.778 9
MAE of Different Weights of Training Sets with Different Proportions
训练集比例 评价指标 ICF UCF ELM RBF-CF XGB-CF 本文
0.2 PA/% 78.89 80.96 82.79 83.52 85.88 87.85
T/s 10.07 9.92 18.25 22.38 19.89 16.06
0.4 PA/% 80.59 83.89 85.95 86.98 88.99 90.12
T/s 11.22 10.58 19.07 23.97 21.01 17.11
0.6 PA/% 85.36 84.79 88.05 90.62 91.37 93.29
T/s 16.23 16.02 19.91 26.88 23.58 18.66
0.8 PA/% 88.69 89.67 89.11 92.09 94.68 95.52
T/s 17.07 16.97 21.22 30.12 27.85 19.93
The Prediction Accuracy and Running Time of Every Algorithm on Different Ratio Training Sets
MAE of Each Algorithm on Different Proportion Training Sets
训练集比例 评价指标 ICF UCF ELM RBF-CF XGB-CF 本文
0.1 PA/% 79.66 76.53 81.99 84.38 85.63 88.91
T/s 8.81 9.01 12.82 15.03 16.18 13.06
0.3 PA/% 82.32 83.09 86.12 87.01 87.71 90.92
T/s 10.41 9.98 14.01 16.89 18.84 15.03
0.5 PA/% 84.22 85.19 87.51 89.01 90.97 94.11
T/s 12.01 12.85 16.99 19.00 21.11 18.42
0.7 PA/% 85.69 86.78 89.11 93.31 94.88 96.21
T/s 15.33 16.18 19.11 25.63 29.88 21.47
0.9 PA/% 88.18 89.01 91.88 94.08 95.91 98.01
T/s 19.01 18.99 22.31 28.19 32.00 22.21
The Prediction Accuracy and Running Time of Each Algorithm on Different Proportion Training Sets
[1] Gupta M, Kumar P. Recommendation Generation Using Personalized Weight of Meta-Paths in Heterogeneous Information Networks[J]. European Journal of Operational Research, 2020, 284(2): 660-674.
doi: 10.1016/j.ejor.2020.01.010
[2] Zheng G P, Yu H Y, Xu W F. Collaborative Filtering Recommendation Algorithm with Item Label Features[J]. International Core Journal of Engineering, 2020, 6(1): 160-170.
[3] Yao P Y. A Disease Interaction Retrieval and Recommendation System Based on NLP Technology[J]. Journal of Physics: Conference Series, 2021, 1771(1): 012001.
doi: 10.1088/1742-6596/1771/1/012001
[4] 郭蕾, 刘文菊, 王赜, 等. 融合谱聚类和多因素影响的兴趣点推荐方法[J]. 数据分析与知识发现, 2022, 6(5): 77-88.
[4] (Guo Lei, Liu Wenju, Wang Ze, et al. Point-of-Interest Recommendation with Spectral Clustering and Multi-Factors[J]. Data Analysis and Knowledge Discovery, 2022, 6(5): 77-88.)
[5] Hafshejani Z Y, Kaedi M, Fatemi A. Improving Sparsity and New User Problems in Collaborative Filtering by Clustering the Personality Factors[J]. Electronic Commerce Research, 2018, 18: 813-836.
doi: 10.1007/s10660-018-9287-x
[6] Zhang Z P, Kudo Y, Murai T, et al. Improved Covering-Based Collaborative Filtering for New Users’ Personalized Recommendations[J]. Knowledge and Information Systems, 2020, 62(8): 3133-3154.
doi: 10.1007/s10115-020-01455-2
[7] 张青博, 王斌, 崔宁宁, 等. 基于注意力机制的规范化矩阵分解推荐算法[J]. 软件学报, 2020, 31(3): 778-793.
[7] (Zhang Qingbo, Wang Bin, Cui Ningning, et al. Attention-Based Regularized Matrix Factorization for Recommendation[J]. Journal of Software, 2020, 31(3): 778-793.)
[8] Han X, Wang Z, Xu H J. Time-Weighted Collaborative Filtering Algorithm Based on Improved Mini Batch K-Means Clustering[J]. Advances in Science and Technology, 2021, 105: 309-317.
[9] 张润莲, 张瑞, 武小年, 等. 基于混合相似度和差分隐私的协同过滤推荐算法[J]. 计算机应用研究, 2021, 38(8): 2334-2339.
[9] (Zhang Runlian, Zhang Rui, Wu Xiaonian, et al. Collaborative Filtering Recommendation Algorithm Based on Mixed Similarity and Differential Privacy[J]. Application Research of Computers, 2021, 38(8): 2334-2339.)
[10] 任永功, 石佳鑫, 张志鹏. 融合关系挖掘与协同过滤的物品冷启动推荐算法[J]. 模式识别与人工智能, 2020, 33(1): 75-85.
doi: 10.16451/j.cnki.issn1003-6059.202001009
[10] (Ren Yonggong, Shi Jiaxin, Zhang Zhipeng. Recommendation Algorithm Combining Interrelationship Mining and Collaborative Filtering for Items Cold Start[J]. Pattern Recognition and Artificial Intelligence, 2020, 33(1): 75-85.)
doi: 10.16451/j.cnki.issn1003-6059.202001009
[11] Alhijawi B, Al-Naymat G, Obeid N, et al. Novel Predictive Model to Improve the Accuracy of Collaborative Filtering Recommender Systems[J]. Information Systems, 2021, 96: 101670.
doi: 10.1016/j.is.2020.101670
[12] 何瑾琳, 刘学军, 徐新艳, 等. 融合 node2vec和深度神经网络的隐式反馈推荐模型[J]. 计算机科学, 2019, 46(6): 41-48.
doi: 10.11896/j.issn.1002-137X.2019.06.005
[12] (He Jinlin, Liu Xuejun, Xu Xinyan, et al. Implicit Feedback Recommendation Model Combining Node2vec and Deep Neural Networks[J]. Computer Science, 2019, 46(6): 41-48.)
doi: 10.11896/j.issn.1002-137X.2019.06.005
[13] Chen J Y, Wu Y Y, Fan L, et al. N2VSCDNNR: A Local Recommender System Based on Node2vec and Rich Information Network[J]. IEEE Transactions on Computational Social Systems, 2019, 6(3): 456-466.
doi: 10.1109/TCSS.6570650
[14] 冷亚军, 陆青, 张俊岭. 结合类别偏好信息的item-based协同过滤算法[J]. 计算机应用研究, 2016, 33(3): 669-672.
[14] (Leng Yajun, Lu Qing, Zhang Junling. Improved Item-Based Collaborative Filtering Algorithm Combined with Class Preference Information[J]. Application Research of Computers, 2016, 33(3): 669-672.)
[15] 任永功, 张云鹏, 张志鹏. 基于粗糙集规则提取的协同过滤推荐算法[J]. 通信学报, 2020, 41(1): 76-83.
doi: 10.11959/j.issn.1000-436x.2020028
[15] (Ren Yonggong, Zhang Yunpeng, Zhang Zhipeng. Collaborative Filtering Recommendation Algorithm Based on Rough Set Rule Extraction[J]. Journal on Communications, 2020, 41(1): 76-83.)
doi: 10.11959/j.issn.1000-436x.2020028
[16] 陈一然, 郑骏. 基于偏置度量分解与隐反馈的协同过滤推荐算法[J]. 计算机应用研究, 2020, 37(8): 2288-2291, 2296.
[16] (Chen Yiran, Zheng Jun. Collaborative Filtering Recommendation Algorithm Based on Biased Metric Factorization and Implicit Feedback[J]. Application Research of Computers, 2020, 37(8): 2288-2291, 2296.)
[17] 张文, 崔杨波, 李健, 等. 基于聚类矩阵近似的协同过滤推荐研究[J]. 运筹与管理, 2020, 29(4): 171-178.
doi: 10.12005/orms.2020.0104
[17] (Zhang Wen, Cui Yangbo, Li Jian, et al. F-cluMA: A Collaborative Filtering Model Based on Clustered Matrix Approximation[J]. Operations Research and Management Science, 2020, 29(4): 171-178.)
doi: 10.12005/orms.2020.0104
[18] Nahta R, Meena Y K, Gopalani D, et al. Embedding Metadata Using Deep Collaborative Filtering to Address the Cold Start Problem for the Rating Prediction Task[J]. Multimedia Tools and Applications, 2021, 80(12): 18553-18581.
doi: 10.1007/s11042-021-10529-4
[19] Nguyen L V, Nguyen T H, Jung J J, et al. Extending Collaborative Filtering Recommendation Using Word Embedding: A Hybrid Approach[J]. Concurrency and Computation: Practice and Experience, DOI:10.1002/cpe.6232.
doi: 10.1002/cpe.6232
[20] Jain A, Nagar S, Singh P K, et al. EMUCF: Enhanced Multistage User-Based Collaborative Filtering Through Non-Linear Similarity for Recommendation Systems[J]. Expert Systems with Applications, 2020, 161: 113724.
doi: 10.1016/j.eswa.2020.113724
[21] Ghosh S, Aquino B, Gupta V. EventGraD: Event-Triggered Communication in Parallel Machine Learning[J]. Neurocomputing, 2022, 483: 474-487.
doi: 10.1016/j.neucom.2021.08.143
[22] Acharya U K, Kumar S. Genetic Algorithm Based Adaptive Histogram Equalization (GAAHE) Technique for Medical Image Enhancement[J]. Optik, 2021, 230: 166273.
doi: 10.1016/j.ijleo.2021.166273
[23] Nikolakis N, Siaterlis G, Alexopoulos K. A Machine Learning Approach for Improved Shop-Floor Operator Support Using A Two-Level Collaborative Filtering and Gamification Features[J]. Procedia CIRP, 2020, 93:455-460.
doi: 10.1016/j.procir.2020.05.160
[24] Bertani R M, Bianchi R A C, Costa A H R. Combining Novelty and Popularity on Personalized Recommendations Via User Profile Learning[J]. Expert Systems with Application, 2020, 146: 113149.
[25] 罗洋, 夏鸿斌, 刘渊. 融合注意力LSTM的协同过滤推荐算法[J]. 中文信息学报, 2019, 33(12): 110-118.
[25] (Luo Yang, Xia Hongbin, Liu Yuan. Collaborative Filtering Based on Attention LSTM[J]. Journal of Chinese Information Processing, 2019, 33(12): 110-118.)
[26] 叶兰平, 刘锋, 朱二周. 基于径向基神经网络的新型协同过滤推荐算法[J]. 计算机应用与软件, 2016(11): 180-184.
[26] (Ye Lanping, Liu Feng, Zhu Erzhou. A New Collaborative Filtering Recommendation Algorithm Based on RBF Neural Network[J]. Computer Applications and Software, 2016(11): 180-184.)
[27] 王玉珍, 许艳茹, 常丹. 基于SGA-RBF的协同过滤算法研究[J]. 统计与决策, 2019, 35(4): 75-79.
[27] (Wang Yuzhen, Xu Yanru, Chang Dan. Research on Collaborative Filtering Algorithm Based on SGA-RBF[J]. Statistics and Decision, 2019, 35(4): 75-79.)
[28] 杨贵军, 徐雪, 赵富强. 基于XGBoost算法的用户评分预测模型及应用[J]. 数据分析与知识发现, 2019, 3(1): 118-126.
[28] (Yang Guijun, Xu Xue, Zhao Fuqiang. Predicting User Ratings with XGBoost Algorithm[J]. Data Analysis and Knowledge Discovery, 2019, 3(1): 118-126.)
[29] 崔岩, 祁伟, 庞海龙, 等. 融合协同过滤和 XGBoost 的推荐算法[J]. 计算机应用研究, 2020, 37(1): 62-65.
[29] (Cui Yan, Qi Wei, Pang Hailong, et al. Extreme Gradient Boosting Recommendation Algorithm with Collaborative Filtering[J]. Application Research of Computers, 2020, 37(1): 62-65.)
[30] Thakker U, Patel R, Shah M. A Comprehensive Analysis on Movie Recommendation System Employing Collaborative Filtering[J]. Multimedia Tools and Applications, 2021, 80: 28647-28672.
doi: 10.1007/s11042-021-10965-2
[31] Yassine A, Mohamed L, Achhab M A. Intelligent Recommender System Based on Unsupervised Machine Learning and Demographic Attributes[J]. Simulation Modelling Practice and Theory, 2021, 107: 102198.
doi: 10.1016/j.simpat.2020.102198
[32] Alabdulrahman R, Viktor H. Catering for Unique Tastes: Targeting Grey-Sheep Users Recommender Systems Through One-Class Machine Learning[J]. Expert Systems with Applications, 2021, 166: 114061.
doi: 10.1016/j.eswa.2020.114061
[33] Deng X Y, Zhuang F Z, Zhu Z G. Neural Variational Collaborative Filtering with Side Information for Top-K Recommendation[J]. International Journal of Machine Learning and Cybernetics, 2019, 10: 3273-3284.
doi: 10.1007/s13042-019-01016-2
[34] 石秀金, 雷前春. 基于信息熵和用户兴趣时间性的协同过滤算法[J]. 东华大学学报(自然科学版), 2019, 45(4): 555-558, 570.
[34] (Shi Xiujin, Lei Qianchun. Collaborative Filtering Algorithm Based on Information Entropy and Timeliness of User Interest[J]. Journal of Donghua University (Natural Science Edition), 2019, 45(4):555-558, 570.)
[35] Li G H, Luo J W, Wang D C, et al. Potential circRNA-Disease Association Prediction Using DeepWalk and Network Consistency Projection[J]. Journal of Biomedical Informatics, 2020, 112: 103624.
doi: 10.1016/j.jbi.2020.103624
[1] Yin Cong,Zhang Liyi. Recommendation Algorithm for Post-Context Filtering Based on TF-IDF: Case Study of Catering O2O[J]. 数据分析与知识发现, 2018, 2(11): 28-36.
[2] Ma Jian, Du Zeyu, Li Shuqing. Personalized Book Recommendation Algorithm Based on Multi-interest Analysis in Library[J]. 现代图书情报技术, 2012, 28(6): 1-8.
[3] Wang Yingzi. Research on Ontology-based Personalized Recommendation Method for Library Resources[J]. 现代图书情报技术, 2012, (12): 72-78.
  Copyright © 2016 Data Analysis and Knowledge Discovery   Tel/Fax:(010)82626611-6626，82624938   E-mail:jishu@mail.las.ac.cn