On including the user dynamic in learning to rank
Ferro N., Lucchese C., Maistro M., Perego R.
Effectiveness Ranking User dynamics Learning to rank
Ranking query results effectively by considering user past behaviour and preferences is a primary concern for IR researchers both in academia and industry. In this context, LtR is widely believed to be the most effective solution to design ranking models that account for user-interaction features that have proved to remarkably impact on IR effectiveness. In this paper, we explore the possibility of integrating the user dynamic directly into the LtR algorithms. Specifically, we model with Markov chains the behaviour of users in scanning a ranked result list and we modify Lambdamart, a state-of-the-art LtR algorithm, to exploit a new discount loss function calibrated on the proposed Markovian model of user dynamic. We evaluate the performance of the proposed approach on publicly available LtR datasets, finding that the improvements measured over the standard algorithm are statistically significant.
Source: SIGIR '17 - 40th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 1041–1044, Shinjuku, Tokyo, Japan, 7 - 11 August, 2017
Publisher: ACM, Association for computing machinery, New York, USA
Metrics
Back to previous page
@inproceedings{oai:it.cnr:prodotti:381005,
title = {On including the user dynamic in learning to rank},
author = {Ferro N. and Lucchese C. and Maistro M. and Perego R.},
publisher = {ACM, Association for computing machinery, New York, USA},
doi = {10.1145/3077136.3080714},
booktitle = {SIGIR '17 - 40th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 1041–1044, Shinjuku, Tokyo, Japan, 7 - 11 August, 2017},
year = {2017}
}
0000-0002-2545-0425