USER: A Unified Information Search and Recommendation Model based on Integrated Behavior Sequence

Abstract

Search and recommendation are the two most common approaches used by people to obtain information. They share the same goal -- satisfying the user's information need at the right time. There are already a lot of Internet platforms and Apps providing both search and recommendation services, showing us the demand and opportunity to simultaneously handle both tasks. However, most platforms consider these two tasks independently -- they tend to train separate search model and recommendation model, without exploiting the relatedness and dependency between them. In this paper, we argue that jointly modeling these two tasks will benefit both of them and finally improve overall user satisfaction. We investigate the interactions between these two tasks in the specific information content service domain. We propose first integrating the user's behaviors in search and recommendation into a heterogeneous behavior sequence, then utilizing a joint model for handling both tasks based on the unified sequence. More specifically, we design the Unified Information Search and Recommendation model (USER), which mines user interests from the integrated sequence and accomplish the two tasks in a unified way.

arXiv comment10 pages, 5 figures, CIKM 2021

References in corpus (5)

• Knowledge Graph Convolutional Networks for Recommender Systems
• End-to-End Neural Ad-hoc Ranking with Kernel Pooling
• NPA: Neural News Recommendation with Personalized Attention
• Graph Enhanced Representation Learning for News Recommendation
• KRED: Knowledge-Aware Document Representation for News Recommendations

Cited by in corpus (8)

• A Model-Agnostic Causal Learning Framework for Recommendation using Search Data
• When Search Meets Recommendation: Learning Disentangled Search Representation for Recommendation
• An Unified Search and Recommendation Foundation Model for Cold-Start Scenario
• KuaiSAR: A Unified Search And Recommendation Dataset
• Unified Dual-Intent Translation for Joint Modeling of Search and Recommendation
• A Unified Search and Recommendation Framework Based on Multi-Scenario Learning for Ranking in E-commerce
• Enhancing CTR Prediction in Recommendation Domain with Search Query Representation
• RUEL: Retrieval-Augmented User Representation with Edge Browser Logs for Sequential Recommendation