What question did this study set out to answer?

To develop a click model that incorporates content and context information for better prediction of user interactions.

A Content- and Context-Aware Click Model based on Dynamic Graph Neural Networks

View Full Paper

Ask AI

Bookmark

Authors

Novel dynamic graph model enhances click prediction and relevance estimation in search results, indicating improved user engagement.

To develop a click model that incorporates content and context information for better prediction of user interactions.
Develop a Dynamic Graph Neural Click Model (DGCM) that uses nodes to represent content and context.
Utilize a dynamic graph attention network to predict clicks over time.
Conduct experiments on the Sogou-SRR and a proprietary WeChat dataset.
DGCM significantly outperforms existing click models in predicting user clicks.
The model effectively utilizes content and context to improve relevance estimation.
Experimental results demonstrate enhanced user engagement metrics compared to traditional methods.

Yang et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark