Improving Web Recommendation Systems via Feature Engineering for Anticipating User's Subsequent Links
Subject Areas : Computer Engineering and ITVahid Saffari 1 , Karamolah BagheriFard 2 , Hamid Parvin 3 , Samad Nejatian 4 , Vahide Rezaie 5
1 - Department of Computer Engineering, Yasooj Branch, Islamic Azad University, Yasooj, Iran
2 - Department of Computer Engineering, Yasooj Branch, Islamic Azad University, Yasooj, Iran
3 - 3 Department of Computer Engineering, Nourabad Mamasani Branch, Islamic Azad University, Nourabad Mamasani, Iran
4 - Department of Electrical Engineering, Yasooj Branch, Islamic Azad University, Yasooj, Iran
5 - Mathematics Dept., Yasooj Branch, Islamic Azad University, Yasooj, Iran
Keywords: Web mining, Future Engineering, User Behavior Modeling, Next Web Page Prediction,
Abstract :
Given the remarkable growth in online content and extensive user engagement, understanding user behavior and providing accurate content recommendations stands as a significant challenge in data mining and recommendation systems. This article introduces a comprehensive approach to enhance user profiling accuracy and increase precision in web page recommendations. It initiates this process by introducing an innovative feature called "user engagement duration with web pages," significantly aiding in improving user profiles. Leveraging these enriched profiles facilitates predicting a user's next web page visit. Evaluating this model, comparison with a scenario lacking this new feature demonstrates a substantial increase in prediction accuracy upon its inclusion. Additionally, we delve into cluster analysis, employing k-means and k-medoids algorithms, where k-medoids demonstrate greater diversity in sample clustering. The paper establishes the superiority of using k-medoids in this domain and emphasizes the importance of determining optimal cluster sizes. Ultimately, this research culminates in developing a web recommendation system capable of highly accurate predictions regarding the user's next web destination. Hence, the proposed approach enhances the model's precision in recommending links to users and promises further advancements in this field.
L. WangBin, "Web Mining Research," in 5th International Conference on Computational Intelligence and Multimedia Applications, 2003.
F.O. Isinkaye, Y.O. Folajimi, B.A. Ojokoh,, "Recommendation systems: Principles, methods and evaluation," Egyptian Informatics Journal, vol. 16, no. Issue 3, pp. 261-273, 2015.
Zhang, Q., Lu, J. & Jin, Y, " Artificial intelligence in recommender systems," Complex Intell, vol. 7, no. 1, p. 439–457, 2021.
V. P. a. M. P. F. Mansur, "A review on recommender systems," in International Conference on Innovations in Information, Embedded and Communication Systems (ICIIECS), Coimbatore, India, 2017.
I. T. Afolabi, "Semantic Web mining for Content-Based Online Shopping Recommender Systems," . International Journal of Intelligent Information Technologies (IJIIT), vol. 15, no. 4, pp. 41-56, 2019.
"www.Ehadish.com," [Online].
H. Hasija, "Recommender system with web usage mining based on fuzzy c means and neural networks," in International Conference on Next Generation Computing Technologies, Dehradun, India, 2015.
Katarya, R., Verma, O.P, "An effective web page recommender system with fuzzy," Multimed Tools Appl, vol. 76, no. 20, p. 21481–21496, 2017.
F. Darbandi Monfared, "A novel web page recommender using data automatic clustering," SN Applied Sciences, vol. 1, p. 1719, 2019.
María N. Moreno, Saddys Segrera, Vivian F. López, María Dolores Muñoz, "Web mining based framework for solving usual problems," Neurocomputing, vol. 176, pp. 72-80, 2016.
T. Bhattacharya, A. Jaiswal and V. Nagpal, "Web usage mining and text mining in the environment of web personalization for ontology development of recommender systems," in 5th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions) (ICRITO), Noida, India, 2016.
A. G. M. E. Badr Hssina, "Recommendation system using the k-nearest neighbors and singular value decomposition algorithms," International Journal of Electrical and Computer Engineering (IJECE), Vols. 11,No 6, pp. 5541-5548, 2021.
Muhammad Waqar, Nadeem Majeed, Hassan Dawood, Ali Daud & Naif Radi, "An adaptive doctor-recommender system," Behaviour & Information Technology, vol. 38, no. 9, pp. 959-973, 2019.
R. &. P. J. Wagh, "A Novel Web Page Recommender System for Anonymous Users Based on Clustering," Asian Journal For Convergence In Technology (AJCT), vol. 5, no. 1, 2019.
Manikandan, R., Saravanan, V, "A novel approach on Particle Agent Swarm Optimization (PASO) in semantic mining for web page recommender system of multimedia data: a health care perspective," Multimed Tools Appl, vol. 79, p. 3807–3829, 2020.
