Information retrieval & information filtering

Acceding easily to information and getting quickly what we need is the aim of all information access methods. In fact, as it was explaines by [1], the main purpose of access information strategies is to make a user retrieving that amount of knowledge which he/she needs in a specific situation for solving his/her current problem.

Eearly definitions of information retrieval (IR), dating from 1960's, considered this field concerned by the structure, analysis, organisation, storage, searching, and retrieval of information. Thus, all the aspects of information have to be included. Over the 1980's and 1990's, most research in IR was focused on document retrieval. Web search engine represent the most common example of this type of IR system. However, it is to be noted that web search and IR are not equivalent, Web search is only a part. Web queries do not represent all information needs. Web search engines are effective for some types of queries in some contexts.

Considering that the Web area has rapidly become one of the most powerful global sources of a wide range of information under several shapes (documents, media, etc), this increase in the volume of available on-line data has led to the fact that users find many difficulties to access and get information they need. To solve this problem of information overload, several approaches have been developped to assist and help users in separating relevant from irrelevant information.  Retrieval/ Filtering systems represent one of the main examples of these approaches. Retrieval refers to the selection of web resources (documents) from a fixed repository, whereas filtering is referring to the selection of relevant information (or rejection of irrelevant information) from a stream of incoming data [2]. These two fields are representing similarities (information representation : user and content modelling, comparaison mechanisms, feedback mechanisms) and dissimilarities (nature of data and user need, used mechanisms, etc).