Abstract
Monitoring user-system performance in interactive search is a challenging task. Traditional measures
of retrieval evaluation, based on recall and precision, are not of any use in real time, for they require
a priori knowledge of relevant documents. This paper shows how a Shannon entropy-based measure
of user-system performance naturally falls in the framework of (interactive) probabilistic information
retrieval. The value of entropy of the distribution of probability of relevance associated with the
documents in the collection can be used to monitor search progress in live testing, to allow for example
the system to select an optimal combination of search strategies. User profiling and tuning parameters
of retrieval systems are other important applications.
| Original language | English |
|---|---|
| Title of host publication | RIAO 2004 |
| Subtitle of host publication | conference proceedings Coupling approaches, coupling media and coupling languages for information retrieval, University of Avignon (Vaucluse), France, April 26-28, 2004 |
| Place of Publication | Paris |
| Publisher | Centre de Hautes Etudes Internationales d'Informatique Documentaire (CID) |
| Pages | 474-483 |
| Number of pages | 10 |
| ISBN (Print) | 9782905450098 |
| Publication status | Published - Apr 2004 |
| Event | 7th International Conference on Computer-Assisted Information Retrieval, RIAO 2004: (Recherche d'Information et ses Applications) - Avignon, France Duration: 1 Apr 2004 → 1 Apr 2004 Conference number: 7 |
Conference
| Conference | 7th International Conference on Computer-Assisted Information Retrieval, RIAO 2004 |
|---|---|
| Abbreviated title | RIAO |
| Country/Territory | France |
| City | Avignon |
| Period | 1/04/04 → 1/04/04 |
Keywords
- DB-IR: INFORMATION RETRIEVAL
- EWI-7176
- IR-63495
- METIS-221593