000001072 001__ 1072
000001072 005__ 20181220113723.0
000001072 022__ $$a0897-1889
000001072 0247_ $$2DOI$$a10.1007/s10278-015-9792-6
000001072 037__ $$aARTICLE
000001072 041__ $$aeng
000001072 245__ $$bsemantics and prediction of query results$$aAnalyzing image search behaviour of radiologists :
000001072 260__ $$c2015
000001072 269__ $$a2015-10
000001072 506__ $$avisible
000001072 520__ $$aLog files of information retrieval systems that record user behavior have been used to improve the outcomes of retrieval systems, understand user behavior, and predict events. In this article, a log file of the ARRS GoldMiner search engine containing 222,005 consecutive queries is analyzed. Time stamps are available for each query, as well as masked IP addresses, which enables to identify queries from the same person. This article describes the ways in which physicians (or Internet searchers interested in medical images) search and proposes potential improvements by suggesting query modifications. For example, many queries contain only few terms and therefore are not specific; others contain spelling mistakes or non-medical terms that likely lead to poor or empty results. One of the goals of this report is to predict the number of results a query will have since such a model allows search engines to automatically propose query modifications in order to avoid result lists that are empty or too large. This prediction is made based on characteristics of the query terms themselves. Prediction of empty results has an accuracy above 88 %, and thus can be used to automatically modify the query to avoid empty result sets for a user. The semantic analysis and data of reformulations done by users in the past can aid the development of better search systems, particularly to improve results for novice users. Therefore, this paper gives important ideas to better understand how people search and how to use this knowledge to improve the performance of specialized medical search engines.$$9eng
000001072 592__ $$aHEG-VS
000001072 592__ $$bInstitut Informatique de gestion
000001072 592__ $$cEconomie et Services
000001072 65017 $$aInformatique
000001072 6531_ $$aimage retrieval$$9eng
000001072 6531_ $$ahuman-computer interaction$$9eng
000001072 6531_ $$amachine learning$$9eng
000001072 6531_ $$astatistic analysis$$9eng
000001072 655__ $$ascientifique
000001072 6531_ $$ainformation storage and retrieval$$9eng
000001072 6531_ $$amedical image search$$9eng
000001072 6531_ $$alog file analysis$$9eng
000001072 700__ $$uCarnegie Mellon University$$aDe-Arteaga, Maria
000001072 700__ $$uUniversity of Applied Sciences and Arts Western Switzerland (HES-SO Valais-Wallis)$$aEggel, Ivan
000001072 700__ $$uUniversity of Pennsylvania$$aKahn, Charles
000001072 700__ $$aMüller, Henning$$uUniversity of Applied Sciences and Arts Western Switzerland (HES-SO Valais-Wallis)
000001072 773__ $$gOctober 2015, vol. 28, Issue 5, pp. 537-546$$tJournal of digital imaging
000001072 8564_ $$uhttps://hesso.tind.io/record/1072/files/muller_analyzingimagesearch_2015.pdf$$s1031424
000001072 909CO $$pGLOBAL_SET$$ooai:hesso.tind.io:1072
000001072 906__ $$aNONE
000001072 950__ $$aI2
000001072 980__ $$ascientifique