Dynamic Web Personalization Using a Hybrid Recommender System with Sequential Pattern Detection and Link Sequence Similarity
الموضوعات : International Journal of Data Envelopment Analysis
Vahid Saffari
1
,
Karamolah BagheriFard
2
,
Hamid Parvin
3
,
Samad Nejatian
4
,
Vahide Rezaie
5
1 - Department of Computer Engineering, Islamic Azad University, Yasooj, Iran
2 - Department of Computer Engineering, Yasooj Branch, Islamic Azad University, Yasooj, Iran
3 - Department of Computer Engineering, Nourabad Mamasani Branch, Islamic Azad University, Nourabad Mamasani, Iran
4 - دانDepartment of Electronic Engineering, Yasooj Branch, Islamic Azad University, Yasooj, Iran شگاه آزاد اسلامی واحد یاسوج
5 - Department of Mathematics Engineering, Yasooj Branch, Islamic Azad University, Yasooj, Iran
الکلمات المفتاحية: Web Recommender System, Website Personalization, Sequential Pattern Discovery, Link Sequence Similarity, Hybrid Model,
ملخص المقالة :
In this paper, we propose a dynamic hybrid web recommender system aimed at personalizing websites through sequential pattern discovery and link sequence similarity detection. The system is evaluated on two standard datasets, Zanbil and NASA, containing extensive web server logs. After preprocessing the logs by removing irrelevant data and segmenting user interactions into sessions, we perform user clustering using the PAM algorithm with three similarity metrics: Levenshtein Distance, Longest Common Subsequence (LCS), and Needleman-Wunsch (NW). The optimal number of clusters is determined through evaluation of Precision, Recall, and F-measure, with the best results found at 350 clusters for Zanbil and 500 for NASA.
User profiles are generated using FP-Growth and SPADE, which help in identifying frequent navigation patterns. The model is then evaluated, yielding optimal Precision of 0.91 and Recall of 0.83 for SPADE combined with LCS. Results show that this combination produces the best performance, effectively capturing user behavior and providing superior personalized recommendations.
The study demonstrates that this hybrid approach enhances the personalization of web, delivering more relevant suggestions to users based on their previous interactions.
Aggarwal, C. C. (2016). Recommender Systems: The Textbook. Springer.
Cooley, R. M. (1999). Data Preparation for Mining World Wide Web Browsing Patterns. Knowledge and Information Systems 1, 5–32.
Dacrema, M. F. (2021). A Troubling Analysis of Reproducibility and Progress in Recommender Systems Research. ACM Transactions on Information Systems Volume 39, 1–49.
Fan, Y. M. (2021). Continuous-time sequential recommendation with temporal graph collaborative networks. The 30th ACM International Conference on Information and Knowledge Management.
Gao, C. G. (2020). A state-preserving RNN framework for sequential recommendation. Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining.
Gong, S. C. (2021). Contrastive self-supervised sequential recommendation with robust augmentation. Proceedings of the 30th ACM International Conference on Information and Knowledge Management (CIKM).
Li, S. W. (2020). Time interval aware self-attention for sequential recommendation. Proceedings of the 13th International Conference on Web Search and Data Mining (WSDM).
Liu, B. L. (2018). Sequence-Aware Recommender Systems: An Overview. ACM Computing Surveys (CSUR), 54(4), 1-36.
Ma, R. S. (2020). Memory augmented graph neural networks for sequential recommendation. Proceedings of the AAAI Conference on Artificial Intelligence 34(04), (pp. 5045-5052).
Mobasher, B. D. (2002). Discovery and Evaluation of Aggregate Usage Profiles for Web Personalization. Data Mining and Knowledge Discovery 6, 61-82.
N.S. (2018). Retrieved from NASA: https://www.kaggle.com/datasets/souhagaa/nasa-access-log-dataset
Navarro, G. (2021). A Guided Tour to Approximate String Matching. ACM Computing Surveys., 33.
Ricci, F. R. (2015). Recommender Systems Handbook. Springer.
S. Latifi, D. J. (2022). Sequential recommendation : A study on transformers, nearest neighbors and sampled metrics. Inf. Sci.(Ny)., vol. 609, 660–678.
Sun, F. L. (2019). BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer. Proceedings of the 28th ACM International Conference on Information and Knowledge Management, (pp. 1441–1450).
Tan, P. N. (2018). Introduction to Data Mining. Pearson Education. Pearson.
Wang, S. Y. (2021). Denoising implicit feedback for recommendation. Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval.
Xie, Y. Z. (2020). Sequential recommender system based on hierarchical attention network. Proceedings of the 13th ACM International Conference on Web Search and Data Mining (WSDM).
Zaker, F. (2019). Harvard Dataverse, V1. Retrieved from Online Shopping Store - Web Server Logs: https://doi.org/10.7910/DVN/3QBYB5
Zaki, M. (2020). An efficient algorithm for mining frequent sequences. Machine Learning, 42, 31–60.
Zhou, K. W. (2020). S3-Rec: Self-supervised learning for sequential recommendation with mutual information maximization. Proceedings of the 29th ACM International Conference on Information & Knowledge Management, (pp. 1893–1902).
