TY - GEN
T1 - Content-Based Relevance Estimation in Retrieval Settings with Ranking-Incentivized Document Manipulations
AU - Vasilisky, Ziv
AU - Kurland, Oren
AU - Tennenholtz, Moshe
AU - Raiber, Fiana
N1 - Publisher Copyright:
© 2023 ACM.
PY - 2023/8/9
Y1 - 2023/8/9
N2 - 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.
AB - 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.
KW - competitive retrieval
KW - language modeling
KW - learning-to-rank
UR - http://www.scopus.com/inward/record.url?scp=85171424872&partnerID=8YFLogxK
U2 - 10.1145/3578337.3605124
DO - 10.1145/3578337.3605124
M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???
AN - SCOPUS:85171424872
T3 - ICTIR 2023 - Proceedings of the 2023 ACM SIGIR International Conference on the Theory of Information Retrieval
SP - 205
EP - 214
BT - ICTIR 2023 - Proceedings of the 2023 ACM SIGIR International Conference on the Theory of Information Retrieval
T2 - 9th ACM SIGIR International Conference on the Theory of Information Retrieval, ICTIR 2023
Y2 - 23 July 2023
ER -