Cognitive Personalised Interfaces for Web-based Library Catalogues

Current Digital Libraries (DLs) are becoming more complex systems than traditional libraries, because they provide mixed-mode, multimodal, and multimedia content. In comparison with traditional libraries, DLs make information directly available to users via both intranets and the Internet. Without the mediation of librarians, it is necessary for DLs to bridge the terminological and cognitive gap between the producers and the users of the content. Indeed, previous studies of Web-Based Library Catalogues (WBLC) indicate that unassisted online searching causes difficulties for end-users, with a failure rate often approaching 50% of the users requests. In addition, end-users have problems in choosing search terms to represent their needs and in judging the relevance of the documents. Several factors contribute to these problems: (a) bibliographic descriptions do not provide relevance according to users’ preferences; (b) there is a lack of appropriate navigation support for users with different/special needs; and (c) search options and format presentations are not flexible enough to align with different users’ tasks, behaviours, and experiences.

Although personalisation is recognised as a promising approach to accommodate users’ needs, existing applications in DLs mainly consider users’ preferences based on explicit information that users provide. Such an approach ignores individual differences, including prior knowledge, gender, and cognitive style. However, empirical evidence indicates that individual differences have significant effects on information seeking. In particular, cognitive style plays an important role because it refers to an individual’s preferred and habitual approach to organising and representing information.

To this end, the project aims to demonstrate the importance of individual differences in the use of personalised WBLC. In particular, it will develop a formal requirement specification, which defines the content presentation and navigation support for each cognitive style group; create user models for recording user actions and changes in observed navigational and interactive behaviour depending on a user's cognitive style; produce a personalisation engine that supports adaptivity and adaptablity for users with different cognitive styles; produce a prototype of the personalised WBLC evaluated through appropriate usability inspection methods, including user testing and heuristic evaluation; create the final personalised WBLC and evaluate it, generating design guidelines that are capable of accommodating different cognitive styles through the effective use of personalisation technologies.

Project Team: G.D. Magoulas (Birkbeck); S. Y. Chen, R. Macredie and E. Frias-Martinez (Brunel)

Support: A.H.R.B. (MRG/AN9183/APN16300)

Duration: 2003-2006.

Home  - Teaching  -  Research  -  Publications  -  Bio  -  Links