Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Research › peer-review
Evaluating and analyzing click simulation inweb search. / Malkevich, Stepan; Markov, Ilya; Michailova, Elena; De Rijke, Maarten.
ICTIR 2017 - Proceedings of the 2017 ACM SIGIR International Conference on the Theory of Information Retrieval. Association for Computing Machinery, 2017. p. 281-284.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Research › peer-review
}
TY - GEN
T1 - Evaluating and analyzing click simulation inweb search
AU - Malkevich, Stepan
AU - Markov, Ilya
AU - Michailova, Elena
AU - De Rijke, Maarten
PY - 2017/10/1
Y1 - 2017/10/1
N2 - We evaluate and analyze the quality of click models with respect to their ability to simulate users' click behavior. To this end, we propose distribution-based metrics for measuring the quality of click simulation in addition to metrics that directly compare simulated and real clicks. We perform a comparison of widely-used click models in terms of the quality of click simulation and analyze this quality for queries with different frequencies. We find that click models fail to accurately simulate user clicks, especially when simulating sessions with no clicks and sessions with a click on the first position. We also find that click models with higher click prediction performance simulate clicks better than other models.
AB - We evaluate and analyze the quality of click models with respect to their ability to simulate users' click behavior. To this end, we propose distribution-based metrics for measuring the quality of click simulation in addition to metrics that directly compare simulated and real clicks. We perform a comparison of widely-used click models in terms of the quality of click simulation and analyze this quality for queries with different frequencies. We find that click models fail to accurately simulate user clicks, especially when simulating sessions with no clicks and sessions with a click on the first position. We also find that click models with higher click prediction performance simulate clicks better than other models.
UR - http://www.scopus.com/inward/record.url?scp=85033236658&partnerID=8YFLogxK
U2 - 10.1145/3121050.3121096
DO - 10.1145/3121050.3121096
M3 - Conference contribution
AN - SCOPUS:85033236658
SP - 281
EP - 284
BT - ICTIR 2017 - Proceedings of the 2017 ACM SIGIR International Conference on the Theory of Information Retrieval
PB - Association for Computing Machinery
T2 - 7th ACM SIGIR International Conference on the Theory of Information Retrieval, ICTIR 2017
Y2 - 1 October 2017 through 4 October 2017
ER -
ID: 38401093