More about HKUST
A Deep Architecture for Depression Detection using Posting, Behavior, and Living Environment Data
Speaker: Professor Arbee L.P. Chen Chair Professor of Computer Science and Information Engineering Asia University, Taiwan Title: A Deep Architecture for Depression Detection using Posting, Behavior, and Living Environment Data Date: Friday, 8 September 2017 Time: 11:00am to 12 noon Venue: Room 5619 (via lift nos. 31/32), HKUST Abstract: The World Health Organization (WHO) predicts that depression disorders will be widespread in the next 20 years. According to the research, 40% of the patients with depression have suicidal thoughts and 10%~15% die by suicide. Early depression detection and prevention therefore becomes an important issue. In this talk, I will present our approach to predict the depression label of an individual by analyzing his/her living environment, behavior, and the posting contents in the social media. The proposed method employs Recurrent Neural Networks to compute the posts representation of each individual. The representations are then combined with other content-based, behavior and living environment features to predict the depression label of the individual with Deep Neural Networks. The experiment results on a real dataset show that the performance of our approach significantly outperforms the other baselines. **************************** Biography: Arbee L.P. Chen received a Ph.D. degree in computer engineering from the University of Southern California, USA, and is currently Chair Professor of Computer Science and Vice President at Asia University, Taiwan. He also holds joint faculty positions at National Tsing Hua University and Academia Sinica, Taiwan. Dr. Chen was a Professor of the Department of Computer Science, National Tsing Hua University; a Member of Technical Staff at Bell Communications Research, USA; and a Research Scientist at Unisys, USA. Dr. Chen organized IEEE Data Engineering Conference in Taiwan, and continuously serves in various capacities for international conferences and journals. He was invited to deliver a speech in the NSF-sponsored Inaugural International Symposium on Music Information Retrieval and the IEEE Shannon Lecture Series, USA, and the Institute for Advanced Study of Hong Kong University of Science and Technology, Hong Kong. Dr. Chen's current research interests include big data analytics, top-k queries, and multimedia information retrieval. He has published more than 250 papers in renowned international journals and conference proceedings, and was a visiting scholar at Tsinghua University, China, Kyoto University, Japan, King's College London, UK, Stanford University, Boston University, Harvard University, USA, and Hong Kong University of Science and Technology, Hong Kong.