Financially supported by FCT Fundação para a Ciência e Tecnologia through grant POSC/EIA/58367/2004, co-financed by FEDER through Programa Operacional Sociedade do Conhecimento POS_Conhecimento.

The Web currently poses a number of interesting research problems. From the User’s point of view (see Roles below), the Web is becoming too large, too dynamic and increasingly unknown. From the Editor’s point of view, the Web is a constant demand for new information and timely updates. Moreover, the Editor should not only maintain the contents of the site, but also permanently choose the site’s navigational structure that best helps achieving the aims of the site’s Owner, User, or both. From the Owner’s point of view the need for such a constant labour intensive effort implies very high financial or personal costs.

In this project we aim to develop a platform and a methodology for automating several of the management activities of a Web site, such as the retrieval of new, relevant content, monitoring and management of existing content and how it is structured, provision of recommendation and personalization of the structure. This is done taking into account the behaviour of the Users, and the aims of the Owner. One of the effects of automation is the reduction of the Editor’s effort, and consequently of the costs for the Owner. The other effect is that the site can more timely adapt to the behaviour of the User, improving the browsing experience and helping the user in achieving his/her own goals when these are in accordance to the goals of the Owner of the site.

Our aims will be pursued by: 1) defining a flexible web site platform that allows the acquisition of quality web data, as well as on line automatic transformation and customization of the site’s structure and interface (view); 2) developing techniques for web adaptation using data mining (association rules, collaborative filtering, Bayesian approaches, Markov models, ranking methods); and 3) allowing the specification of topic focused content retrieval. These efforts will be guided by well defined objectives, automatically monitored by measures of performance defined on usage data. Automated actions must also be controlled by the Editor.

As a test bed for our approach, we will integrate some of the ideas on existing web sites, both commercial (a payed subscription portal with information digests and other services for executives, www.PortalExecutivo.com), and non-commercial (www.appia.pt, the site of a scientific society) and will set up another entirely new web site tentatively popular for the widespread dissemination of scientific knowledge.

Partners

• LIAAD, INESCPorto LA, University of Porto (http://www.liaad.up.pt)
• CRACS, INESCPorto LA, University of Porto (http://cracs.fc.up.pt/)
• Centro de Tecnologia da Ling. Humana e Bioinf., University Beira Interior,  (http://hultig.di.ubi.pt)
• IDMEC, FEUP, University of Porto (http://www.fe.up.pt/idmec)
• Departamento de Informática, University of Minho (http://www.di.uminho.pt)
• Sensoria, (http://www.sensoria.pt/), now Paleta de Ideias.

• PortalExecutivo.com (PE has closed doors)

Publications

Theses

Papers in Journals or with ISI reference

Articles in Conferences

Nuno Escudeiro, Alípio Jorge, A methodology for satisfying persistent information needs on the Web using data mining: 6ta Conf. da Assoc. Port. de Sist. de Inf., CAPSI 05, Bragança, Portugal, Outubro 2005

Papers in Workshops

Mário Amado Alves, Alípio Jorge Minibrain : a generic model of spreading activation in computers, and example specialisations, in ECML/PKDD 2005 workshop "Subsymbolic paradigms for learning in structured domains", Porto, 2005.

José Borges e Mark Levene. A Clustering-Based Approach for Modelling User Navigation With Increased Accuracy, in Proceedings of the Second International Workshop on Knowledge Discovery from Data Streams (IWKDDS), 77-86. Porto, Portugal, Outubro, 2005.

Campos, R. & Dias, G. (2005). Automatic Hierarchical Clustering of Web Pages. In Proceedings of the ELECTRA Workshop associated to 28th Annual International ACM SIGIR Conference, Salvador, Brazil, August 19. pp. 83-85. In association with ACM editions.

C. Carvalho, A. Jorge and C. Soares (2005). Personalização de e-Newsletters com Base nos Acessos dos Utilizadores. In Proceedings of the Data Mining for Business Workshop. Porto, Portugal

Nuno Escudeiro, Alípio Jorge, webTOPIC: Automatic Web Resource Compilation for Persistent Information Needs, ECML/PKDD 2005 workshop European Web Mining Forum  

C. Rebelo, P.Q. Brito (2005). Quantidade de Informação por Detrás de um Clique. In Proceedings of the Data Mining for Business Workshop. Porto, Portugal