IRiX/ExplicitMeasures

User metadata

Searcher's contextual information can be captured by a set of metadata provided by the searcher. For example, HARD Track in TREC 2003 gathered the following aspects in the user metadata (See [WWW] http://ciir.cs.umass.edu/research/hard/guidelines2003.html):

  • Purpose: why the user is searching for the information

  • Genre: the type of material the searcher is interested in

  • Familiarity: how familiar the searcher is with the topic (Presumably a user who is fully aware of the details of a topic would not be interested in background material)

  • Granularity: the amount of text that the searcher is anticipating in a value response

  • Related text: sample relevant text

Relevance feedback

Traditioinal way to capture the relevant information from searchers is to use relevance feedback where the searcher explicitly indicate the relevance of retrieved documents.

last edited 2005-12-01 15:30:44 by HideoJoho