PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
August 15, 20051,409 citations

Accurately interpreting clickthrough data as implicit feedback

View Full Paper
TJThorsten JoachimsLGLaura GrankaBPBing Pan

Key Points

  • The aim is to assess the reliability of implicit feedback from clickthrough data in web search contexts.
  • Analyzed user decision processes through eyetracking.
  • Compared implicit feedback from clicks with manual relevance judgments.
  • Clicks provide informative but biased representations of relevance.
  • Relative preferences derived from clicks are reasoned to be accurate on average.

Abstract

This paper examines the reliability of implicit feedback generated from clickthrough data in WWW search. Analyzing the users' decision process using eyetracking and comparing implicit feedback against manual relevance judgments, we conclude that clicks are informative but biased. While this makes the interpretation of clicks as absolute relevance judgments difficult, we show that relative preferences derived from clicks are reasonably accurate on average.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Joachims et al. (2005) studied this question.

synapsesocial.com/papers/69d8ab72a5ecc596b5d182a1https://doi.org/10.1145/1076034.1076063
Ask AI
Helpful
Bookmark
Share
View Full Paper