AdSight: Scalable and Accurate Quantification of User Attention in Multi-Slot Sponsored Search

TL;DR

AdSight is a Transformer-based method that accurately quantifies user attention on complex search engine results pages using mouse cursor trajectories, aiding web design and advertising strategies.

Contribution

It introduces a novel attention modeling approach leveraging cursor data and Transformer architecture for multi-slot SERPs, improving prediction accuracy.

Findings

High-precision attention prediction demonstrated

Effective in regression and classification tasks

Provides actionable insights for web design and advertising

Abstract

Modern Search Engine Results Pages (SERPs) present complex layouts where multiple elements compete for visibility. Attention modelling is crucial for optimising web design and computational advertising, whereas attention metrics can inform ad placement and revenue strategies. We introduce AdSight, a method leveraging mouse cursor trajectories to quantify in a scalable and accurate manner user attention in multi-slot environments like SERPs. AdSight uses a novel Transformer-based sequence-to-sequence architecture where the encoder processes cursor trajectory embeddings, and the decoder incorporates slot-specific features, enabling robust attention prediction across various SERP layouts. We evaluate our approach on two Machine Learning tasks: (1) regression, to predict fixation times and counts; and (2) classification, to determine some slot types were noticed. Our findings demonstrate the model's ability to predict attention with unprecedented precision, offering actionable insights for researchers and practitioners.