Web Personalization

During the last few years, Web personalization has become an important field of research in many application areas that are based on hypermedia and the Web, such as e-commerce, information retrieval, Web search system, e-learning, etc. The main goal of Web personalisation is to deliver to a given user information that is tailored to his/her preferences and interests.  Mobasher [1] defined Web personalization as any action that tailors the Web experience to a particular user, or set of users. Nasraoui [2] consider that personalization aims to customize the interactions on a website depending on the user’s explicit and/or implicit interests and desires. By these definitions, we can deduce three main pillars composing the personalization task. The first pillar is the “user” who will express (implicitly or/and explicitly) his/her needs and preferences, and according to whom, personalization will be achieved. The second pillar is the Web site (content) that will be personalized in many levels as the content, the presentation and the navigation. The third pillar is represented by the system which will apply the suitable techniques to produce personalization effect. It is to be noted that the customization term is generally used when the user participate directly in the personalization process by delivering explicitly his/her preferences when choosing from a list or filling a form or answering a questionnaire. This process tends to be manual and static or at best semi-automatic. The term adaptive Web is rather used when personalization is accomplished in an automatic way i.e data about users are collected implicitly and the Web is adapted automatically according to the user needs and preferences. Indeed, to make a Web system providing an adaptation effect taking into account user preferences and interests, a specific representation of information about the user is needed : User profiles and user models. In the adaptive hypermedia area, adaptation concerned mainly the content of pages and links from pages. Therefore, as explained in [3], two different classes of adaptation can be considered: adaptive presentation and adaptive navigation support. Later, in [4], the taxonomy of adaptive hypermedia technologies was updated to add some extensions in relation with new technologies. Then, the distinction between two modes of adaptive navigation support became a necessity, especially with the growth of recommender systems. In fact, adapting links that were already prepared and presented on a certain page is quite different from generating new ones. Automatic recommendation implies that the user profiles are created and eventually maintained dynamically by the system without explicit user information. Examples include amazon.com’s personalized recommendations, music recommenders like Mystrand.com in commercial systems [5] and smart recommenders in e-learning system [6], and Hybrid Recommender System for E-Learning Personalization [7], etc. In general, such systems differ in the input data, in user profiling strategies, and in prediction techniques. Several approaches for automatic personalization were reported in the literature, such as content based or item based filtering, collaborative filtering, rule based filtering, and techniques relying on Web usage mining, etc [2].

[1] Mobasher. B, Dai. H, Luo. T, Sun. Y and Zhu.J, Combining Web usage and content mining for effective personalization, In Proc. Of the International Conference on Ecommerce and Web Technologies (ECWeb), 2000.

[2] Nasraoui, O. (2005) World Wide Web Personalization, Invited chapter in “Encyclopedia of Data Mining and Data Warehousing”, J. Wang, Ed, Idea Group, 2005.

[3] Brusilovsky, P. “Methods and techniques of adaptive hypermedia”, User Modeling and User-Adapted Interaction, pp.87-129, 1996.

[4] Brusilovsky, P. (2001). Adaptive hypermedia. User Modeling and User Adapted Interaction, Ten Year Anniversary Issue (Alfred Kobsa, ed.) 11 (1/2), 87-110. 2001.

[5] Mobasher, B. (2006) Data Mining for Web Personalization. The Adaptive Web: Methods and Strategies of Web Personalization. Lecture Notes in Computer Science, Vol. Springer-Verlag, Berlin-Heidelberg New York, 2006.

[6] Zaiane, OR. (2002) Building a Recommender Agent for e-Learning Systems, in Proc. of the 7th International Conference on Computers in Education (ICCE 2002) pp 55-59, Auckland, New Zealand, December 3 - 6, 2002.

[7] Khribi, M.K., Jemni, M. and Nasraoui, O.: “Toward a Hybrid Recommender System for E-Learning Personalization Based on Web Usage Mining Techniques and Information Retrieval”, In Proceedings of World Conference on E-Learning in Corporate, Government, Healthcare, and Higher Education, 2007, (pp. 6136-6145). Chesapeake, VA: AACE.