A Personalized Collaborative Digital Library Environment [chapter]

M. Elena Renda, Umberto Straccia
2002 Lecture Notes in Computer Science  
We envisage a Digital Library not only as an information resource where users may submit queries to satisfy their information need, but also as a collaborative working and meeting space. We will present a personalized collaborative Digital Library environment, where users may organise the information space according to their own subjective view, may become aware of each other, exchange information and knowledge with each other, may build communities and may get recommendations based on
more » ... e patterns of the users. of the user's information need). It can be acquired either automatically (by usersystem interaction) or set-up manually (by the user). The acquisition of a user profile and the successive matching of documents against it, in order to filter out the relevant ones, is known as Information or Content-based Filtering [2, 12]. Very seldom, except e.g. [8], DLs can also be considered as collaborative meeting or working places, where users may become aware of each other, open communication channels, and exchange information and knowledge with each other or with experts. Indeed, usually users access a DL in search of some information. This means that it is quite probable that users may have overlapping interests if the information available in a DL matches their expectations, backgrounds, or motivations. Such users might well profit from each other's knowledge by sharing opinions or experiences or offering advice. Some users might enter into long-term relationships and eventually evolve into a community if only they were to become aware of each other. Such a service might be important for a DL as it supplies very focussed information. Concerning the information seek task, the recommendation of items based on preference patterns of others users is probably the most important one. The use of opinions and knowledge of other users to predict the relevance value of items to be recommended to each user in a community is known as Collaborative or Social Filtering [3, 5, 15, 16, 20] . These methods are built on the assumption that a good way to find interesting content is to find other users who have similar interests, and then recommend items that those similar users like. In contrast to information filtering methods, collaborative filtering methods do not require any content analysis as they are based on aggregated user ratings of these items.
doi:10.1007/3-540-36227-4_30 fatcat:jjxqcvflwba4tgebec45weqila