Download presentation
Presentation is loading. Please wait.
1
Personalized Video Recommendation Based on Cross-Platform User Modeling
Zhengyu Deng, Jitao Sang, Changsheng Xu 1 Institute of Automation, Chinese Academy of Sciences 2 Chinese-Singapore Institute of Digital Media
2
Summary Cross-platform user modeling
The limitations of single platform Cold-start issue Data sparsity homogeneous Cross-platform user modeling A user has multiple accounts across web2.0, which reflect user interest from different perspectives We can utilize one platform to enrich another or generate a unified user profile by aggregating the distributed user info across different platform.
3
Framework --We use YouTube as the target platform where to perform the recommendation task, and Google+ as the auxiliary platform where user information is transferred. --Two strategies are designed to strengthen the understanding of user interest in the target platform: one is profile enrichment and the other is collaborative relationship transfer.
4
Approach Kernel-based similarity learning
--We assume that users who have similar profiles in Google+ are very likely to have similar profiles in YouTube. --We measure user similarity under different modalities using multiple kernel learning (MKL) scheme to integrate the multiple modalities
5
Experiments Quantitative results
Recommend only by YouTube Profile (S1); Recommend by Profile Enrichment (S2); Recommend by YouTube Profile with Collaborative Transfer (S3); Recommend by Profile Enrichment with Collaborative Transfer (S4).
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.