报告人：Xiaohua Tony Hu, Drexel University
时间：9 月 6 日（星期二）上午 10:00-11:00
地点：张江校区软件楼 105 会议室
联系人：王晓阳 xywangcs@fudan.edu.cn
Abstract:
Various social media applications have generated lot of data, provided many challenges as well as opportunities to dig into user behaviors, discover helpful knowledge, offer information service, and so on. In this talk, I will discuss big data analysis in three social media applications: (1) Language model smoothing on social networks: we propose to tackle the Achilles Heel of social networks by smoothing the language model via influence propagation. We formulate a socialized factor graph model, which utilizes both the textual correlations between document pairs and the socialized augmentation networks behind the documents, such as user relationships and social interactions. These factors are modeled as attributes and dependencies among documents and their corresponding users, (2) Video Popularity Prediction by Sentiment Propagation via Implicit Network: we present a Dual Sentimental Hawkes Process (DSHP) to deal with all the challenging issues in existing approaches. DSHP lifts "Linear Correlation" assumption, reveals deeper factors that reflect a video's popularity; and it is topology free, (3) Topic Propagation with Semi-Supervised Dirichlet Hawkes Process: propose a novel model – Semi-Supervised Dirichlet Hawkes Process (SDHP) to detect and track topics from Twitter.
Boi：
Xiaohua Tony Hu is a professor at the College of Computing and Informatics, Drexel University, also a lecture professor at the Central China Normal University, China. He is also serving as the founding Co-Director of the NSF Center (I/U CRC) on Visual and Decision Informatics (NSF CVDI), and IEEE Computer Society Big Data Steering Committee Chair. His’s current research interests are in data/text/web mining, big data, bioinformatics/biomedicine. He has published more than 270 peer-reviewed research papers in various journals, conferences and books, graduated 15 Ph.D. students from 2006 to 2016 and is currently supervising 14 Ph.D. students.
