Multimodal Foundation Model-Driven User Interest Modeling and Behavior Analysis on Short Video Platforms

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhao, Yushang, Peng, Yike, Zhang, Li, Sun, Qianyi, Zhang, Zhihui, Zhuang, Yingying
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909771614912512
author Zhao, Yushang
Peng, Yike
Zhang, Li
Sun, Qianyi
Zhang, Zhihui
Zhuang, Yingying
author_facet Zhao, Yushang
Peng, Yike
Zhang, Li
Sun, Qianyi
Zhang, Zhihui
Zhuang, Yingying
contents With the rapid expansion of user bases on short video platforms, personalized recommendation systems are playing an increasingly critical role in enhancing user experience and optimizing content distribution. Traditional interest modeling methods often rely on unimodal data, such as click logs or text labels, which limits their ability to fully capture user preferences in a complex multimodal content environment. To address this challenge, this paper proposes a multimodal foundation model-based framework for user interest modeling and behavior analysis. By integrating video frames, textual descriptions, and background music into a unified semantic space using cross-modal alignment strategies, the framework constructs fine-grained user interest vectors. Additionally, we introduce a behavior-driven feature embedding mechanism that incorporates viewing, liking, and commenting sequences to model dynamic interest evolution, thereby improving both the timeliness and accuracy of recommendations. In the experimental phase, we conduct extensive evaluations using both public and proprietary short video datasets, comparing our approach against multiple mainstream recommendation algorithms and modeling techniques. Results demonstrate significant improvements in behavior prediction accuracy, interest modeling for cold-start users, and recommendation click-through rates. Moreover, we incorporate interpretability mechanisms using attention weights and feature visualization to reveal the model's decision basis under multimodal inputs and trace interest shifts, thereby enhancing the transparency and controllability of the recommendation system.
format Preprint
id arxiv_https___arxiv_org_abs_2509_04751
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Multimodal Foundation Model-Driven User Interest Modeling and Behavior Analysis on Short Video Platforms
Zhao, Yushang
Peng, Yike
Zhang, Li
Sun, Qianyi
Zhang, Zhihui
Zhuang, Yingying
Information Retrieval
Machine Learning
With the rapid expansion of user bases on short video platforms, personalized recommendation systems are playing an increasingly critical role in enhancing user experience and optimizing content distribution. Traditional interest modeling methods often rely on unimodal data, such as click logs or text labels, which limits their ability to fully capture user preferences in a complex multimodal content environment. To address this challenge, this paper proposes a multimodal foundation model-based framework for user interest modeling and behavior analysis. By integrating video frames, textual descriptions, and background music into a unified semantic space using cross-modal alignment strategies, the framework constructs fine-grained user interest vectors. Additionally, we introduce a behavior-driven feature embedding mechanism that incorporates viewing, liking, and commenting sequences to model dynamic interest evolution, thereby improving both the timeliness and accuracy of recommendations. In the experimental phase, we conduct extensive evaluations using both public and proprietary short video datasets, comparing our approach against multiple mainstream recommendation algorithms and modeling techniques. Results demonstrate significant improvements in behavior prediction accuracy, interest modeling for cold-start users, and recommendation click-through rates. Moreover, we incorporate interpretability mechanisms using attention weights and feature visualization to reveal the model's decision basis under multimodal inputs and trace interest shifts, thereby enhancing the transparency and controllability of the recommendation system.
title Multimodal Foundation Model-Driven User Interest Modeling and Behavior Analysis on Short Video Platforms
topic Information Retrieval
Machine Learning
url https://arxiv.org/abs/2509.04751