Scientific article
Open access

Topic modelling of clickthrough data in image search

Published inMultimedia Tools and Applications, vol. 66, no. 3, p. 493-515
  • Open Access - Licence nationale Springer 
Publication date2013

In this paper we explore the benefits of latent variable modelling of clickthrough data in the domain of image retrieval. Clicks in image search logs are regarded as implicit relevance judgements that express both user intent and important relations between selected documents. We posit that clickthrough data contains hidden topics and can be used to infer a lower dimensional latent space that can be subsequently employed to improve various aspects of the retrieval system. We use a subset of a clickthrough corpus from the image search portal of a news agency to evaluate several popular latent variable models in terms of their ability to model topics underlying queries. We demonstrate that latent variable modelling reveals underlying structure in clickthrough data and our results show that computing document similarities in the latent space improves retrieval effectiveness compared to computing similarities in the original query space. These results are compared with baselines using visual and textual features. We show performance substantially better than the visual baseline, which indicates that content-based image retrieval systems that do not exploit query logs could improve recall and precision by taking this historical data into account.

Citation (ISO format)
MORRISON, Donn Alexander et al. Topic modelling of clickthrough data in image search. In: Multimedia Tools and Applications, 2013, vol. 66, n° 3, p. 493–515. doi: 10.1007/s11042-012-1038-8
Main files (1)
Article (Published version)
ISSN of the journal1380-7501

Technical informations

Creation03/05/2019 11:37:00 AM
First validation03/05/2019 11:37:00 AM
Update time03/15/2023 3:50:06 PM
Status update03/15/2023 3:50:05 PM
Last indexation01/17/2024 5:04:01 AM
All rights reserved by Archive ouverte UNIGE and the University of GenevaunigeBlack