S
Shuangyong Song
Researcher at Alibaba Group
Publications - 51
Citations - 371
Shuangyong Song is an academic researcher from Alibaba Group. The author has contributed to research in topics: Microblogging & Computer science. The author has an hindex of 9, co-authored 39 publications receiving 303 citations. Previous affiliations of Shuangyong Song include Fujitsu & Chinese Academy of Sciences.
Papers
More filters
Proceedings ArticleDOI
Modelling Domain Relationships for Transfer Learning on Retrieval-based Question Answering Systems in E-commerce
TL;DR: In this article, the authors proposed a transfer learning framework for paraphrase identification and natural language inference, which can effectively and efficiently adapt the shared knowledge learned from a resource-rich source domain to a resource poor target domain.
Journal ArticleDOI
A new temporal and social PMF-based method to predict users' interests in micro-blogging
TL;DR: The proposed model provides a unified way to fuse the time information and the social network structure to predict users' future interests accurately and demonstrates the efficiency and effectiveness of the proposed model.
Journal ArticleDOI
A Temporal-Topic Model for Friend Recommendations in Chinese Microblogging Systems
TL;DR: A temporal-topic model is proposed to analyze users' possible behaviors and predict their potential friends in microblogging and the experimental results of friend recommendations on Sina Weibo have demonstrated the effectiveness of the model.
Book ChapterDOI
A spatio-temporal framework for related topic search in micro-blogging
TL;DR: A novel framework that mines the associations among topic trends in twitter by considering both temporal and location information is proposed and the experimental results show that the method can find the related topics effectively and accurately.
Proceedings ArticleDOI
Detecting Concept-level Emotion Cause in Microblogging
Shuangyong Song,Yao Meng +1 more
TL;DR: Experimental results on a dataset from Sina Weibo show CECM can better detect emotion causes than baseline methods.