Mohammed Ehsan Hoque

Minh Tran, Taylan Sen, Kurtis Haut et al.

Despite a revolution in the pervasiveness of video cameras in our daily lives, one of the most meaningful forms of nonverbal affective communication, interpersonal eye gaze, i.e. eye gaze relative to a conversation partner, is not available from common video. We introduce the Interpersonal-Calibrating Eye-gaze Encoder (ICE), which automatically extracts interpersonal gaze from video recordings without specialized hardware and without prior knowledge of participant locations. Leveraging the intuition that individuals spend a large portion of a conversation looking at each other enables the ICE dynamic clustering algorithm to extract interpersonal gaze. We validate ICE in both video chat using an objective metric with an infrared gaze tracker (F1=0.846, N=8), as well as in face-to-face communication with expert-rated evaluations of eye contact (r= 0.37, N=170). We then use ICE to analyze behavior in two different, yet important affective communication domains: interrogation-based deception detection, and communication skill assessment in speed dating. We find that honest witnesses break interpersonal gaze contact and look down more often than deceptive witnesses when answering questions (p=0.004, d=0.79). In predicting expert communication skill ratings in speed dating videos, we demonstrate that interpersonal gaze alone has more predictive power than facial expressions.

Md Iftekhar Tanveer, Md Kamrul Hasan, Daniel Gildea et al.

Automated prediction of public speaking performance enables novel systems for tutoring public speaking skills. We use the largest open repository---TED Talks---to predict the ratings provided by the online viewers. The dataset contains over 2200 talk transcripts and the associated meta information including over 5.5 million ratings from spontaneous visitors to the website. We carefully removed the bias present in the dataset (e.g., the speakers' reputations, popularity gained by publicity, etc.) by modeling the data generating process using a causal diagram. We use a word sequence based recurrent architecture and a dependency tree based recursive architecture as the neural networks for predicting the TED talk ratings. Our neural network models can predict the ratings with an average F-score of 0.77 which largely outperforms the competitive baseline method.

Tayan Sen, Md Kamrul Hasan, Zach Teicher et al.

We developed an online framework that can automatically pair two crowd-sourced participants, prompt them to follow a research protocol, and record their audio and video on a remote server. The framework comprises two web applications: an Automatic Quality Gatekeeper for ensuring only high quality crowd-sourced participants are recruited for the study, and a Session Controller which directs participants to play a research protocol, such as an interrogation game. This framework was used to run a research study for analyzing facial expressions during honest and deceptive communication using a novel interrogation protocol. The protocol gathers two sets of nonverbal facial cues in participants: features expressed during questions relating to the interrogation topic and features expressed during control questions. The framework and protocol were used to gather 151 dyadic conversations (1.3 million video frames). Interrogators who were lied to expressed the smile-related lip corner puller cue more often than interrogators who were being told the truth, suggesting that facial cues from interrogators may be useful in evaluating the honesty of witnesses in some contexts. Overall, these results demonstrate that this framework is capable of gathering high quality data which can identify statistically significant results in a communication study.

Rasoul Shafipour, Raiyan Abdul Baten, Md Kamrul Hasan et al.

In this study, we explore peer-interaction effects in online networks on speaking skill development. In particular, we present an evidence for gradual buildup of skills in a small-group setting that has not been reported in the literature. We introduce a novel dataset of six online communities consisting of 158 participants focusing on improving their speaking skills. They video-record speeches for 5 prompts in 10 days and exchange comments and performance-ratings with their peers. We ask (i) whether the participants' ratings are affected by their interaction patterns with peers, and (ii) whether there is any gradual buildup of speaking skills in the communities towards homogeneity. To analyze the data, we employ tools from the emerging field of Graph Signal Processing (GSP). GSP enjoys a distinction from Social Network Analysis in that the latter is concerned primarily with the connection structures of graphs, while the former studies signals on top of graphs. We study the performance ratings of the participants as graph signals atop underlying interaction topologies. Total variation analysis of the graph signals show that the participants' rating differences decrease with time (slope=-0.04, p<0.01), while average ratings increase (slope=0.07, p<0.05)--thereby gradually building up the ratings towards community-wide homogeneity. We provide evidence for peer-influence through a prediction formulation. Our consensus-based prediction model outperforms baseline network-agnostic regression models by about 23% in predicting performance ratings. This, in turn, shows that participants' ratings are affected by their peers' ratings and the associated interaction patterns, corroborating previous findings. Then, we formulate a consensus-based diffusion model that captures these observations of peer-influence from our analyses.