Modeling and application of implicit feedback in personalized recommender systems

Hui Li; Shuai Wu; Ronghui Wang; Wenbin Hu; Haining Li; Hui Li; Shuai Wu; Ronghui Wang; Wenbin Hu; Haining Li

doi:10.3934/era.2025053

Electronic Research Archive

2025, Volume 33, Issue 2: 1185-1206. doi: 10.3934/era.2025053

Previous Article Next Article

Research article

Modeling and application of implicit feedback in personalized recommender systems

Hui Li ¹,
Shuai Wu ¹,
Ronghui Wang ¹,
Wenbin Hu ^{1
,
,},
Haining Li ^{2
,
,}

1.
School of Computer Engineering, Jiangsu Ocean University, Jiangsu 222000, China
2.
Department of Neurology, General Hospital of Ningxia Medical University, Ningxia 750003, China

Received: 17 December 2024 Revised: 13 February 2025 Accepted: 17 February 2025 Published: 03 March 2025

Traditional recommendation algorithms usually rely on the user's existing data and historical behavioral records to make recommendations, which often leads to low recommendation accuracy and insufficient personalized experience. To solve these problems, this paper proposes an innovative recommendation algorithm model, neural collaborative filtering with multiple attention mechanism (NCF-MAH). The goal of this model is to enhance the effectiveness of the recommender system. The specific implementation includes constructing a negative sample set and applying matrix decomposition techniques to map user and item IDs to a low-dimensional embedding vector space. In addition, the model processes these embedding vectors using a multi-head attention mechanism to transform them into query vectors, key vectors, and value vectors, and further computes the attention scores and the corresponding weighted sums. Finally, the score prediction is accomplished by fusing the output of the multi-head attention mechanism with the results of the multilayer perceptual machine. The experimental results show that the NCF-MAH model exhibits significant advantages over the baseline model in two key evaluation metrics, hit rate and normalized discount cumulative gain (NDCG), on the MOOC platform and other datasets. Specifically, hit rate and NDCG improved by 13% vs. 9.8% and 15.7% vs. 12.8% when Top-k was set to 10 and 20, respectively.
- neural collaborative filtering,
- multi-head attention mechanism,
- implicit feedback,
- multiple attention force mechanisms,
- score prediction
Citation: Hui Li, Shuai Wu, Ronghui Wang, Wenbin Hu, Haining Li. Modeling and application of implicit feedback in personalized recommender systems[J]. Electronic Research Archive, 2025, 33(2): 1185-1206. doi: 10.3934/era.2025053

Related Papers:

Abstract

Traditional recommendation algorithms usually rely on the user's existing data and historical behavioral records to make recommendations, which often leads to low recommendation accuracy and insufficient personalized experience. To solve these problems, this paper proposes an innovative recommendation algorithm model, neural collaborative filtering with multiple attention mechanism (NCF-MAH). The goal of this model is to enhance the effectiveness of the recommender system. The specific implementation includes constructing a negative sample set and applying matrix decomposition techniques to map user and item IDs to a low-dimensional embedding vector space. In addition, the model processes these embedding vectors using a multi-head attention mechanism to transform them into query vectors, key vectors, and value vectors, and further computes the attention scores and the corresponding weighted sums. Finally, the score prediction is accomplished by fusing the output of the multi-head attention mechanism with the results of the multilayer perceptual machine. The experimental results show that the NCF-MAH model exhibits significant advantages over the baseline model in two key evaluation metrics, hit rate and normalized discount cumulative gain (NDCG), on the MOOC platform and other datasets. Specifically, hit rate and NDCG improved by 13% vs. 9.8% and 15.7% vs. 12.8% when Top-k was set to 10 and 20, respectively.

References

[1]	D. Jannach, Evaluating conversational recommender systems: A landscape of research, Artif. Intell. Rev., 56 (2023), 2365–2400. https://doi.org/10.1007/s10462-022-10229-x doi: 10.1007/s10462-022-10229-x
[2]	Y. Shi, M. Larson, A. Hanjalic, Collaborative filtering beyond the user-item matrix: A survey of the state of the art and future challenges, ACM Comput. Surv., 47 (2014), 1–45. https://doi.org/10.1145/2556270 doi: 10.1145/2556270
[3]	X. Yue, C. Tian'e, The design of personalized learning resource recommendation system for ideological and political courses, Int. J. Reliab. Qual. Saf. Eng., 30 (2023). https://doi.org/10.1142/S0218539322500206 doi: 10.1142/S0218539322500206
[4]	G. Honglei, An online education course recommendation method based on knowledge graphs and reinforcement learning, J. Circuits, Syst. Comput., 32 (2023). https://doi.org/10.1142/S0218126623500998 doi: 10.1142/S0218126623500998
[5]	V. Narjes, M. Mahdieh, S. Hajar, S. M. Fakhrahmad, Application of k-means clustering algorithm to improve effectivenes of the results recommended by journal recommender system, Scientometrics, 127 (2022), 3237–3252. https://doi.org/10.1007/s11192-022-04397-4 doi: 10.1007/s11192-022-04397-4
[6]	B. Sinha, R. Dhanalakshmi, DNN-MF: Deep neural network matrix factorization approach for filtering information in multi-criteria recommender systems, Neural Comput. Appl., 34 (2022), 10807–10821. https://doi.org/10.1007/s00521-022-07012-y doi: 10.1007/s00521-022-07012-y
[7]	X. He, L. Liao, H. Zhang, L. Nie, X. Hu, T. Chua, Neural collaborative filtering, in Proceedings of the 26^th International Conference on World Wide Web, (2017), 173–182. https://doi.org/10.1145/3038912.3052569
[8]	M. Fu, H. Qu, Z. Yi, L. Lu, Y. Liu, A novel deep learning-based collaborative filtering model for recommendation system, IEEE Trans. Cybern., 49 (2019), 1084–1096. http://dx.doi.org/10.1109/TCYB.2018.2795041 doi: 10.1109/TCYB.2018.2795041
[9]	Y. Pan, F. He, H. Yu, Learning social representations with deep autoencoderfor recommender system, World Wide Web, 23 (2020), 2259–2279. https://doi.org/10.1007/s11280-020-00793-z doi: 10.1007/s11280-020-00793-z
[10]	J. Feng, Z. Xia, X. Feng, J. Peng, RBPR: A hybrid model for the new user cold start problem in recommender systems, Knowledge-Based Syst., 214 (2021), 106732. https://doi.org/10.1016/j.knosys.2020.106732 doi: 10.1016/j.knosys.2020.106732
[11]	Y. Bai, X. Li, Z. Liu, Y. Huang, T. Guo, M. Hou, et al., csKT: Addressing cold-start problem in knowledge tracing via kernel bias and cone attention, Expert Syst. Appl., 266 (2025), 125988. https://doi.org/10.1016/j.eswa.2024.125988 doi: 10.1016/j.eswa.2024.125988
[12]	M. Alfarhood, J. Cheng, DeepHCF: A deep learning based hybrid collaborative filtering approach for recommendation systems, in 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA), IEEE, (2018), 89–96. http://dx.doi.org/10.1109/ICMLA.2018.00021
[13]	I. Saifudin, T. Widiyaningtyas, Systematic literature review on recommender system: Approach, problem, evaluation techniques, datasets, IEEE Access, 12 (2024), 19827–19847. https://doi.org/10.1109/ACCESS.2024.3359274 doi: 10.1109/ACCESS.2024.3359274
[14]	P. Cremonesi, Y. Koren, R. Turrin, Performance of recommender algorithms on top-n recommendation tasks, in Proceedings of the Fourth ACM Conference on Recommender Systems, (2010), 39–46. https://doi.org/10.1145/1864708.1864721
[15]	C. Chen, M. Zhang, Y. Zhang, Y. Liu, S. Ma, Efficient neural matrix factorization without sampling for recommendation, ACM Trans. Inf. Syst., 38 (2020), 1–28. https://doi.org/10.1145/3373807 doi: 10.1145/3373807
[16]	C. Li, L. Wang, S. Cheng, Enhanced transformer encoder and hybrid cascaded upsampler for medical image segmentation, Expert Syst. Appl., 238 (2024), 121965. https://doi.org/10.1016/j.eswa.2023.121965 doi: 10.1016/j.eswa.2023.121965
[17]	R. Salakhutdinov, G. Hinton, Multimodal learning with deep boltzmann machines, Adv. Neural Inf. Process. Syst., 24 (2012), 1967–2006. https://doi.org/10.1162/NECO_a_00311 doi: 10.1162/NECO_a_00311
[18]	Y. Koren, R. Bell, C. Volinsky, Matrix factorization techniques for recommender systems, Computer, 42 (2009), 30–37. https://doi.org/10.1109/MC.2009.263 doi: 10.1109/MC.2009.263
[19]	Y. Koren, Factor in the neighbors: Scalable and accurate collaborative filtering, ACM Trans. Knowl. Discovery Data, 4 (2010), 1–24. https://doi.org/10.1145/1644873.1644874 doi: 10.1145/1644873.1644874
[20]	T. Luong, H. Pham, C. D. Manning, Effective approaches to attention-based neural machine translation, in Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, (2015), 1412–1421. https://doi.org/10.18653/v1/D15-1166
[21]	H. Yang, L. Yao, J. Cai, Y. Wang, X. Zhao, A new interest extraction method based on multi-head attention mechanism for CTR prediction, Knowl. Inf. Syst., 65 (2023), 3337–3352. http://dx.doi.org/10.1007/s10115-023-01867-w doi: 10.1007/s10115-023-01867-w
[22]	J. Yu, G. Luo, T. Xiao, Q. Zhong, Y. Wang, W. Feng, et al., MOOCCube: A large-scale data repository for NLP applications in MOOCs, in Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, (2020), 3135–3142. ttps://doi.org/10.18653/v1/2020.acl-main.285
[23]	J. Zhang, B. Hao, B. Chen, C. Li, H. Chen, J. Sun, Hierarchical reinforcement learning for course recommendation in MOOCs, in Proceedings of the AAAI Conference on Artificial Intelligence, 33 (2019), 435–442. https://doi.org/10.1609/aaai.v33i01.3301435
[24]	X. He, Z. He, J. Song, Z. Liu, Y. Jiang, T. Chua, NAIS: Neural attentive item similarity model for recommendation, IEEE Trans. Knowl. Data Eng., 30 (2018), 2354–2366. http://dx.doi.org/10.1109/TKDE.2018.2831682 doi: 10.1109/TKDE.2018.2831682
[25]	S. Juneja, A. Nauman, M. Uppal, D. Gupta, R. Alroobaea, B. Muminov, et al., Machine learning-based defect prediction model using multilayer perceptron algorithm for escalating the reliability of the software, J. Supercomput., 80 (2024), 10122–10147. http://dx.doi.org/10.1007/s11227-023-05836-6 doi: 10.1007/s11227-023-05836-6
[26]	X. Sun, H. Zhang, M. Wang, M. Yu, M. Yin, B. Zhang, Deep plot-aware generalized matrix factorization for collaborative filtering, Neural Process. Lett., 52 (2020), 1983–1995. https://doi.org/10.1007/s11063-020-10333-5 doi: 10.1007/s11063-020-10333-5
[27]	A. Pujahari, D. Sisodia, Item feature refinement using matrix factorization and boosted learning based user profile generation for content-based recommender systems, Expert Syst. Appl., 206 (2022). https://doi.org/10.1016/j.eswa.2022.117849 doi: 10.1016/j.eswa.2022.117849
[28]	J. Bobadilla, R. Lara-Cabrera, Á. González-Prieto, F. Ortega, DeepFair: Deep learning for improving fairness in recommender systems, Int. J. Interact. Multimedia Artif. Intell., 6 (2021), 86–94. https://doi.org/10.9781/ijimai.2020.11.001 doi: 10.9781/ijimai.2020.11.001

Reader Comments

Your name:*

Email:*
© 2025 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)