1 / 16

The Role of Automated Categorization in E-Government Information Retrieval

The Role of Automated Categorization in E-Government Information Retrieval. Tanja Svarre & Marianne Lykke, Aalborg University, DK ISKO conference , 8th of July , 2013. Agenda. Background of the study Theoretical framework Research methods Results Summary and closing remarks.

lorand
Download Presentation

The Role of Automated Categorization in E-Government Information Retrieval

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. The Role of Automated Categorization in E-Government Information Retrieval Tanja Svarre & Marianne Lykke, Aalborg University, DK ISKO conference, 8th of July, 2013.

  2. Agenda • Background of the study • Theoreticalframework • Research methods • Results • Summary and closing remarks

  3. Background to the search test • Initiated and partiallycofinanced by the Danish National IT and Telecom Agency • Purpose: To investigatehowautomaticassignment of metadata cancontribute to the intention of increasedefficiency and effectivenessin (Danish) e-government

  4. Building on indexing/categorization: Early Cranfield tests Categorization is helpful: when the query is vague, broad, general, or ambiguous whenresultrakingsaredeficient (Käki, 2005) in supportingexploratorysearches in understanding large search sets (Kules & Shneiderman, 2004; 2005)

  5. Research methods • Case studyin the Danish TaxAuthorities • Search test: • Controlled lab test • Comparison test • Professional users • Domain specificsearchtasks • Pre test questionnaire • Log data • Post search interview

  6. Data: Search test • System characteristics: • Prototype of the corporateintranet • www.skat.dkcontentand internal information • 2 search systems: • Freetextindexing (SYSTEM A) • Categorization (SYSTEM B) • 32 test persons • 3 controlled and 1 naturalsearchtask per session, 2 tasks per system

  7. Search test: General findings

  8. Success at tasklevel • At tasklevel the success of the two systems differs

  9. Tasklevelresults

  10. Reformulations

  11. System B (cat.) omissions

  12. System B (cat.) omissions • Highly relevant documentsarediscoveredbefore a category has beenselected • Relevant documentsarelocatedwhile waiting for B (cat.) to categorizesearchresults • Categorizationis not relevant whenfewdocumentsareretrieved

  13. Summary • Categorization is useful: • Whenemployees do not posessextensiveknowledgeabout the task at hand • In offering new perspectives on the composition of a qury • In understanding facets of queries • Whentaskknowledge is present, categorization is used to support the assumptions of a correctsearch

  14. Summary • Categorization is omittedwhen: • Search resultsarelimited • When relevant documentsareranked at the top of the results

  15. National IT & Telecom Agency: Findings • The participants start out with freetextindexing and supplement with the otherwhennecessary • The indexingmethodscomparedarecomplementary • To meet the variety of information needsseveralindexingme-thodsshouldberepresentedsimultaneously

  16. Thankyou for your attention! ?

More Related