[Talk Summary 7] Modeling Human Commucation Dynamics
Professor Louis-Philippe Morency from CMU presented the talk "Modeling Human Communication Dynamics" on October, 21, 2016. at CS department, University of Pittsburgh.
He started the talk with an introduction about his research that focuses on creating computational technologies to analyze, recognize and predict human subtle communicative behaviors in social context. Speaking of human communicative behaviors, he indicated three main aspects, namely, verbal, vocal and visual aspects.
There are four challenges in modeling human communication dynamics as stated by prof. Morency, which are behavioral, multimodal, interpersonal, and societal dynamics. He suggested that the model can broadly apply to healthcare, education, and online multimedia.
In the three main parts of the talk, he performed his group's recent achievements, mutlimodal machine learning, and predicting listener behaviors. Firstly, he gave a demo about a healthcare decision support system using Multisense, analysis of face-to-face human interactions, and Simsensei Kiosk, an implemented virtual human interviewer. He introduced some language processing techniques and psychological distress indicators. Secondly, he stated the four major steps that need to be solved in multimodal machine learning:
One promising result showed in this talk is that participants felt more rapport when interacting with the WoZ system than they did in face-to-face interviews. If there are more evidence to support this conclusion, I think we can move toward a step to apply computer technologies to help patient having issues with depression, anxiety, or post-traumatic stress disorder (PTSD).
10/21/2016
5317 Sennott Square
University of Pittsburgh
He started the talk with an introduction about his research that focuses on creating computational technologies to analyze, recognize and predict human subtle communicative behaviors in social context. Speaking of human communicative behaviors, he indicated three main aspects, namely, verbal, vocal and visual aspects.
There are four challenges in modeling human communication dynamics as stated by prof. Morency, which are behavioral, multimodal, interpersonal, and societal dynamics. He suggested that the model can broadly apply to healthcare, education, and online multimedia.
In the three main parts of the talk, he performed his group's recent achievements, mutlimodal machine learning, and predicting listener behaviors. Firstly, he gave a demo about a healthcare decision support system using Multisense, analysis of face-to-face human interactions, and Simsensei Kiosk, an implemented virtual human interviewer. He introduced some language processing techniques and psychological distress indicators. Secondly, he stated the four major steps that need to be solved in multimodal machine learning:
- Behavior Dynamics: Structure
- Mulitmodal dynamics: Representation
- Multimodal dynamics: Synchrony
- Interpersonal Dynamics: Interpretation
One promising result showed in this talk is that participants felt more rapport when interacting with the WoZ system than they did in face-to-face interviews. If there are more evidence to support this conclusion, I think we can move toward a step to apply computer technologies to help patient having issues with depression, anxiety, or post-traumatic stress disorder (PTSD).
10/21/2016
5317 Sennott Square
University of Pittsburgh
Comments
Post a Comment