Query Abandonment Prediction with Recurrent Neural Models of Mouse Cursor Movements

TL;DR

This paper demonstrates that recurrent neural networks analyzing mouse cursor movements can effectively predict query abandonment, providing valuable insights into user satisfaction without relying on click data.

Contribution

It introduces a novel approach using RNNs to model mouse movements for abandonment prediction, avoiding handcrafted features and specific SERP structures.

Findings

Mouse movements are a valuable signal for abandonment prediction.

RNN models outperform baseline methods in accuracy.

Data augmentation techniques improve model robustness.

Abstract

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.