Incorporating Vision Bias into Click Models for Image-oriented Search Engine
This work is significant for search engine developers and researchers working on image-oriented search, as it provides a more accurate model for user behavior by accounting for visual appeal, which is an incremental improvement over existing models.
This paper addresses the limitation of traditional click models in image-oriented search engines by incorporating vision bias, a factor reflecting the visual appearance of documents, into the examination probability. The proposed extended model, evaluated on a real-world dataset, significantly improves data fitness and sparsity handling compared to its baseline.
Most typical click models assume that the probability of a document to be examined by users only depends on position, such as PBM and UBM. It works well in various kinds of search engines. However, in a search engine where massive candidate documents display images as responses to the query, the examination probability should not only depend on position. The visual appearance of an image-oriented document also plays an important role in its opportunity to be examined. In this paper, we assume that vision bias exists in an image-oriented search engine as another crucial factor affecting the examination probability aside from position. Specifically, we apply this assumption to classical click models and propose an extended model, to better capture the examination probabilities of documents. We use regression-based EM algorithm to predict the vision bias given the visual features extracted from candidate documents. Empirically, we evaluate our model on a dataset developed from a real-world online image-oriented search engine, and demonstrate that our proposed model can achieve significant improvements over its baseline model in data fitness and sparsity handling.