Full Publications
Algorithmic Composition
MM 2022   Structure-Enhanced Pop Music Generation via Harmony-Aware Learning
Xueyao Zhang, Jinchao Zhang, Yao Qiu, Li Wang, Jie Zhou
Proceedings of the 30th ACM International Conference on Multimedia (Acceptance Rate: 690/2473=27.9%)
Preprint / Code / Demo
TL;DR: We propose to learn harmony for generating form- and texture- enhanced pop music.
Fake News Detection
ACL 2022   Zoom Out and Observe: News Environment Perception for Fake News Detection
Qiang Sheng, Juan Cao, Xueyao Zhang, Rundong Li, Danding Wang, and Yongchun Zhu
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics
PDF / Poster / Code / Chinese Video / Chinese Blog
TL;DR: For the first time, we propose to perceive signals from the news environment for fake news detection.
CIKM 2021   Integrating Pattern- and Fact-based Fake News Detection via Model Preference Learning
Qiang Sheng*, Xueyao Zhang*, Juan Cao, and Lei Zhong (*: Equal Contribution)
Proceedings of the 30th ACM International Conference on Information and Knowledge Management (Acceptance Rate: 271/1251=21.7%)
PDF / Poster / Code / Chinese Blog
TL;DR: We propose a graph-based model preference learning framework to separately handle the pattern and fact indicators in fake news detection.
ACL 2021   Article Reranking by Memory-enhanced Key Sentence Matching for Detecting Previously Fact-checked Claims
Qiang Sheng, Juan Cao, Xueyao Zhang, Xirong Li, and Lei Zhong
Proceedings of the Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Acceptance Rate: 571/2327=24.5%)
PDF / Poster / Code / Chinese Blog
TL;DR: We detect previously fact-checked claims by matching them against the key sentences in fact-checking articles.
WWW 2021   Mining Dual Emotion for Fake News Detection
Xueyao Zhang, Juan Cao, Xirong Li, Qiang Sheng, Lei Zhong, and Kai Shu
Proceedings of the 30th Web Conference (Acceptance Rate: 357/1736=20.6%)
PDF / Code / Slides / Video / Chinese Video
TL;DR: We leverage both publisher emotion and social emotion for fake news detection.