Content-Based Relevance Estimation in Retrieval Settings with Ranking-Incentivized Document Manipulations

Ziv Vasilisky, Oren Kurland, Moshe Tennenholtz, Fiana Raiber

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

Abstract

In retrieval settings such as the Web, many document authors are ranking incentivized: they opt to have their documents highly ranked for queries of interest. Consequently, they often respond to rankings by modifying their documents. These modifications can hurt retrieval effectiveness even if the resultant documents are of high quality. We present novel content-based relevance estimates which are "ranking-incentives aware"; that is, the underlying assumption is that content can be the result of ranking incentives rather than of pure authorship considerations. The suggested estimates are based on inducing information from past dynamics of the document corpus. Empirical evaluation attests to the clear merits of our most effective methods. For example, they substantially outperform state-of-the-art approaches that were not designed to address ranking-incentivized document manipulations.

Original languageEnglish
Title of host publicationICTIR 2023 - Proceedings of the 2023 ACM SIGIR International Conference on the Theory of Information Retrieval
Pages205-214
Number of pages10
ISBN (Electronic)9798400700736
DOIs
StatePublished - 9 Aug 2023
Event9th ACM SIGIR International Conference on the Theory of Information Retrieval, ICTIR 2023 - Taipei, Taiwan, Province of China
Duration: 23 Jul 2023 → …

Publication series

NameICTIR 2023 - Proceedings of the 2023 ACM SIGIR International Conference on the Theory of Information Retrieval

Conference

Conference9th ACM SIGIR International Conference on the Theory of Information Retrieval, ICTIR 2023
Country/TerritoryTaiwan, Province of China
CityTaipei
Period23/07/23 → …

Keywords

  • competitive retrieval
  • language modeling
  • learning-to-rank

ASJC Scopus subject areas

  • Computer Science (miscellaneous)
  • Information Systems

Fingerprint

Dive into the research topics of 'Content-Based Relevance Estimation in Retrieval Settings with Ranking-Incentivized Document Manipulations'. Together they form a unique fingerprint.

Cite this