Zhentao Xu
Inferring Social Media Users' Mental Health Status from Multimodal Information
Authors: Zhentao Xu,Veronica Perez-Rosas ,Rada Mihalcea
Conference: 2018 International Conference on Multimodal Interaction (ICMI) (submitted)
Abstract: A continuously growing number of people is suffering from mental disorders such as depression and anxiety. In the United States only, one in every four adults suffers from a mental health condition, which makes mental health a pressing concern. In this paper, we explore the use of multimodal cues present in social media posts to predict a user's mental health status. Specifically, we focus on identifying social media posts that indicate either a mental health condition or its onset. We collect posts from Flickr and apply a multimodal approach that consists of jointly analyzing image, language, and post cues and their relation to mental health. We conduct several experiments aiming to discriminate between (1) healthy users and users affected by a mental health illness; and (2) healthy users and users prone to mental illness. Our experimental results indicate that using multiple modalities can improve the performance of this classification task as compared to the use of one modality at a time, and can provide important cues into a user's mental status.
A pneu shape display: Physical buttons with programmable touch response
Authors: Alex Russomanno, Zhentao Xu, Sile O'Modhrain, Brent Gillespie
Conference: 2017 IEEE World Haptics Conference (WHC), Best Demonstration Award
Abstract: By the nature of their physicality, conventional push-buttons provide raised edges and click feel that support localization and confirm actuation, even in the absence of vision. Though touchscreens augmented with modulated traction forces can render certain haptic cues, these cues are not enough to support many of the types of user interaction available through push-buttons. In this paper we introduce pneumatic actuators suitable for overlay on touchscreens that render programmable raised features and click-feel. We present two user studies to feature our programmable raised button technology. The first demonstrates possibilities for interaction even beyond conventional push-buttons and the second demonstrates improved lane keeping in a simulated driving task while operating a interface.