conflab-shot

About

An important but under-explored problem in computer science is the automated analysis of conversational dynamics in large unstructured social gatherings such as networking or mingling events. Research has shown that attending such events contributes greatly to career and personal success. While much progress has been made in the analysis of small pre-arranged conversations, scaling up robustly presents a number of fundamentally different challenges. Unlike analysing small pre-arranged conversations, during mingling, sensor data is seriously contaminated: audio by background chatter; video by people occluding each other; and proximity by noisy radio reflections due to the high density of human bodies. Moreover, determining who is talking with whom is difficult because groups can split and merge at will. A fundamentally different approach is needed to handle both the complexity of the social situation as well as the uncertainty of the sensor data which has not been addressed by state-of-the-art techniques. By exploiting people's non-verbal behaviour, I will develop novel learning methods to estimate the quality of conversational interactions in mingling events. Motivated by findings in social and behavioural psychology demonstrating links between body movements and conversational events, I propose a fresh perspective to solve this by relying more heavily on sensors that can capture body motion. Novel representations of jointly coordinated behaviour will be developed to detect conversational events using multi-sensor streams. By departing from current graph-based representations of groups, I propose to both predict and detect the evolution of conversation partners by combining each individual's intrinsic motivations with the emergent behaviour of their conversational group. With my expertise in developing computational methods for both small and large group social behaviour analysis, I am well-positioned to bridge this gap. Solving this problem will provide the breakthrough necessary to significantly advance a number of other domains from human-robot interaction to organisational psychology.