Cumulated gain-based indicators of IR performance

TamPub

Näytä suppeat kuvailutiedot

dc.contributor.author Järvelin, Kalervo -
dc.contributor.author Kekäläinen, Jaana -
dc.date.accessioned 2012-06-17T20:11:23Z
dc.date.available 2012-06-15 06:36:24 -
dc.date.available 2012-06-17T20:11:23Z
dc.date.issued 2002 -
dc.identifier.uri http://tampub.uta.fi/handle/10024/65718
dc.description.abstract Modern large retrieval environments tend to overwhelm their users by their large output. Since all documents are not of equal relevance to their users, highly relevant documents should be identified and ranked first for presentation to the users. In order to develop IR techniques to this direction, it is necessary to develop evaluation approaches and methods that credit IR methods for their ability to retrieve highly relevant documents. This can be done by extending traditional evaluation methods, i.e., recall and precision based on binary relevance assessments, to graded relevance assessments. Alternatively, novel measures based on graded relevance assessments may be developed. This paper proposes three novel measures that compute the cumulative gain the user obtains by examining the retrieval result up to a given ranked position. The first one accumulates the relevance scores of retrieved documents along the ranked result list. The second one is similar but applies a discount factor on the relevance scores in order to devaluate late-retrieved documents. The third one computes the relative-to-the-ideal performance of IR techniques, based on the cumulative gain they are able to yield. The novel measures are defined and discussed and then their use is demonstrated in a case study using TREC data ­ sample system run results for 20 queries in TREC-7. As relevance base we used novel graded relevance assessments on a four-point scale. The test results indicate that the proposed measures credit IR methods for their ability to retrieve highly relevant documents and allow testing of statistical significance of effectiveness differences. The graphs based on the measures also provide insight into the performance IR techniques and allow interpretation, e.g., from the user point of view. -
dc.format.extent 26 -
dc.language.iso en -
dc.title Cumulated gain-based indicators of IR performance -
dc.type fi=Erillisteos | en=Monograph| -
dc.identifier.urn urn:nbn:uta-3-109 -
dc.relation.numberinseries 2002-2 -
dc.type.version fi=Kustantajan versio | en=Publisher's version| -
dc.seriesname Department of Information Studies: Research Notes -
dc.subject.okm fi=Tietojenkäsittelyoppi ja informaatiotieteet | en=Computer and information sciences| -
dc.oldstats 676 -

Viite kuuluu kokoelmiin:

Näytä suppeat kuvailutiedot