Inferring User Preference in Good Abandonment from Eye Movements

Many studies have been done to investigate good abandonment, but only a few have utilized it to improve search engine performance. In this paper, we aim at inferring user preference in good abandonment. Particularly, we use eye movement data to infer which search result has satisfied user's information need in each good abandonment instance. An eye-tracking experiment was conducted to capture user's eye movement data in good abandonment search tasks. These data were transformed into histograms and sequences on which we applied popular machine learning algorithms for the inference. Our results show that the approach can infer user preference with reasonable accuracy.