AdSight: Scalable and Accurate Quantification of User Attention in Multi-Slot Sponsored Search
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912364336513024 |
|---|---|
| author | Villaizán-Vallelado, Mario Salvatori, Matteo Latifzadeh, Kayhan Penta, Antonio Leiva, Luis A. Arapakis, Ioannis |
| author_facet | Villaizán-Vallelado, Mario Salvatori, Matteo Latifzadeh, Kayhan Penta, Antonio Leiva, Luis A. Arapakis, Ioannis |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_01451 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AdSight: Scalable and Accurate Quantification of User Attention in Multi-Slot Sponsored Search Villaizán-Vallelado, Mario Salvatori, Matteo Latifzadeh, Kayhan Penta, Antonio Leiva, Luis A. Arapakis, Ioannis Information Retrieval 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. |
| title | AdSight: Scalable and Accurate Quantification of User Attention in Multi-Slot Sponsored Search |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2505.01451 |