%0 Journal Article %1 citeulike:6695326 %A Godoy, Daniela %A Amandi, Anal\'ıa %C Oxford, UK, UK %D 2006 %I Elsevier Science Ltd. %J Inf. Syst. %K clustering user-model %N 4 %P 247--265 %R 10.1016/j.is.2005.02.008 %T Modeling user interests by conceptual clustering %U http://dx.doi.org/10.1016/j.is.2005.02.008 %V 31 %X As more information becomes available on the Web, there has been a crescent interest in effective personalization techniques. Personal agents providing assistance based on the content of Web documents and the user interests emerged as a viable alternative to this problem. Provided that these agents rely on having knowledge about users contained into user profiles, i.e., models of user preferences and interests gathered by observation of user behavior, the capacity of acquiring and modeling user interest categories has become a critical component in personal agent design. User profiles have to summarize categories corresponding to diverse user information interests at different levels of abstraction in order to allow agents to decide on the relevance of new pieces of information. In accomplishing this goal, document clustering offers the advantage that an a priori knowledge of categories is not needed, therefore the categorization is completely unsupervised. In this paper we present a document clustering algorithm, named WebDCC (Web Document Conceptual Clustering), that carries out incremental, unsupervised concept learning over Web documents in order to acquire user profiles. Unlike most user profiling approaches, this algorithm offers comprehensible clustering solutions that can be easily interpreted and explored by both users and other agents. By extracting semantics from Web pages, this algorithm also produces intermediate results that can be finally integrated in a machine-understandable format such as an ontology. Empirical results of using this algorithm in the context of an intelligent Web search agent proved it can reach high levels of accuracy in suggesting Web pages.

@article{citeulike:6695326, abstract = {{As more information becomes available on the Web, there has been a crescent interest in effective personalization techniques. Personal agents providing assistance based on the content of Web documents and the user interests emerged as a viable alternative to this problem. Provided that these agents rely on having knowledge about users contained into user profiles, i.e., models of user preferences and interests gathered by observation of user behavior, the capacity of acquiring and modeling user interest categories has become a critical component in personal agent design. User profiles have to summarize categories corresponding to diverse user information interests at different levels of abstraction in order to allow agents to decide on the relevance of new pieces of information. In accomplishing this goal, document clustering offers the advantage that an a priori knowledge of categories is not needed, therefore the categorization is completely unsupervised. In this paper we present a document clustering algorithm, named WebDCC (Web Document Conceptual Clustering), that carries out incremental, unsupervised concept learning over Web documents in order to acquire user profiles. Unlike most user profiling approaches, this algorithm offers comprehensible clustering solutions that can be easily interpreted and explored by both users and other agents. By extracting semantics from Web pages, this algorithm also produces intermediate results that can be finally integrated in a machine-understandable format such as an ontology. Empirical results of using this algorithm in the context of an intelligent Web search agent proved it can reach high levels of accuracy in suggesting Web pages.}}, added-at = {2018-03-19T12:24:51.000+0100}, address = {Oxford, UK, UK}, author = {Godoy, Daniela and Amandi, Anal\'{\i}a}, biburl = {https://www.bibsonomy.org/bibtex/28f3ce388b6c1d09b893c7dd4c8a52009/aho}, citeulike-article-id = {6695326}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1140596}, citeulike-linkout-1 = {http://dx.doi.org/10.1016/j.is.2005.02.008}, doi = {10.1016/j.is.2005.02.008}, interhash = {8a1fdd79534dea36d732cc772fe5973c}, intrahash = {8f3ce388b6c1d09b893c7dd4c8a52009}, issn = {0306-4379}, journal = {Inf. Syst.}, keywords = {clustering user-model}, month = jun, number = 4, pages = {247--265}, posted-at = {2011-03-30 03:42:03}, priority = {2}, publisher = {Elsevier Science Ltd.}, timestamp = {2018-03-19T12:24:51.000+0100}, title = {{Modeling user interests by conceptual clustering}}, url = {http://dx.doi.org/10.1016/j.is.2005.02.008}, volume = 31, year = 2006 }