Query Abandonment Prediction with Recurrent Neural Models of Mouse Cursor Movements
This work addresses the challenge for search providers in gauging user satisfaction for queries without clicks, though it is incremental in applying existing neural methods to a new signal.
The paper tackled the problem of predicting query abandonment when click-through data is unavailable by using mouse cursor movements as a behavioral signal, achieving discrimination between good and bad abandonment with recurrent neural networks.
Most successful search queries do not result in a click if the user can satisfy their information needs directly on the SERP. Modeling query abandonment in the absence of click-through data is challenging because search engines must rely on other behavioral signals to understand the underlying search intent. We show that mouse cursor movements make a valuable, low-cost behavioral signal that can discriminate good and bad abandonment. We model mouse movements on SERPs using recurrent neural nets and explore several data representations that do not rely on expensive hand-crafted features and do not depend on a particular SERP structure. We also experiment with data resampling and augmentation techniques that we adopt for sequential data. Our results can help search providers to gauge user satisfaction for queries without clicks and ultimately contribute to a better understanding of search engine performance.