Improving search result comprehension by topic-relevance map visualization

Jaakko Peltonen, Kseniia Belorustceva, Tuukka Ruotsalo

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Abstract

We introduce topic-relevance map, an interactive search result visualization that assists rapid information comprehension across a large ranked set of results. The topicrelevance map visualizes a topical overview of the search result space as keywords with respect to two essential information retrieval measures: relevance and topical similarity. Non-linear dimensionality reduction is used to embed highdimensional keyword representations of search result data into angles on a radial layout. Relevance of keywords is estimated by a ranking method and visualized as radiuses on the layout. Similar keywords are modeled by nearby points and more relevant keywords are closer to the center of the radial display. We evaluated the effect of the topic-relevance map in a search result comprehension task where 24 participants were summarizing search results and produced a conceptualization of the result space. Topic-relevance map significantly improves participants' comprehension capability compared to a ranked list. Copyright is held by the owner/author(s).

Original languageEnglish
Title of host publicationIUI 2017 - Companion of the 22nd International Conference on Intelligent User Interfaces
PublisherACM
Pages149-152
Number of pages4
ISBN (Electronic)9781450348935
DOIs
Publication statusPublished - 7 Mar 2017
MoE publication typeA4 Article in a conference publication
EventInternational Conference on Intelligent User Interfaces - Limassol, Cyprus
Duration: 13 Mar 201716 Mar 2017
Conference number: 22

Conference

ConferenceInternational Conference on Intelligent User Interfaces
Abbreviated titleIUI
CountryCyprus
CityLimassol
Period13/03/201716/03/2017

Keywords

  • Exploratory search
  • Sense-making
  • Visualization

Fingerprint

Dive into the research topics of 'Improving search result comprehension by topic-relevance map visualization'. Together they form a unique fingerprint.

Cite this