Mohammed

Md Kamrul Hasan, Wasifur Rahman, Amir Zadeh et al.

Humor is a unique and creative communicative behavior displayed during social interactions. It is produced in a multimodal manner, through the usage of words (text), gestures (vision) and prosodic cues (acoustic). Understanding humor from these three modalities falls within boundaries of multimodal language; a recent research trend in natural language processing that models natural language as it happens in face-to-face communication. Although humor detection is an established research area in NLP, in a multimodal context it is an understudied area. This paper presents a diverse multimodal dataset, called UR-FUNNY, to open the door to understanding multimodal language used in expressing humor. The dataset and accompanying studies, present a framework in multimodal humor detection for the natural language processing community. UR-FUNNY is publicly available for research.

Ru Zhao, Vivian Li, Hugo Barbosa et al.

This paper presents a description and evaluation of the ROC Speak system, a platform that allows ubiquitous access to communication skills training. ROC Speak (available at rocspeak.com) enables anyone to go to a website, record a video, and receive feedback on smile intensity, body movement, volume modulation, filler word usage, unique word usage, word cloud of the spoken words, in addition to overall assessment and subjective comments by peers. Peer comments are automatically ranked and sorted for usefulness and sentiment (i.e., positive vs. negative). We evaluated the system with a diverse group of 56 online participants for a 10-day period. Participants submitted responses to career oriented prompts every other day. The participants were randomly split into two groups: 1) treatment - full feedback from the ROC Speak system; 2) control - written feedback from online peers. When judged by peers (p<.001) and independent raters (p<.05), participants from the treatment group demonstrated statistically significant improvement in overall speaking skills rating while the control group did not. Furthermore, in terms of speaking attributes, treatment group showed an improvement in friendliness (p<.001), vocal variety (p<.05) and articulation (p<.01).

Iftekhar Naim, M. Iftekhar Tanveer, Daniel Gildea et al.

We present a computational framework for automatically quantifying verbal and nonverbal behaviors in the context of job interviews. The proposed framework is trained by analyzing the videos of 138 interview sessions with 69 internship-seeking undergraduates at the Massachusetts Institute of Technology (MIT). Our automated analysis includes facial expressions (e.g., smiles, head gestures, facial tracking points), language (e.g., word counts, topic modeling), and prosodic information (e.g., pitch, intonation, and pauses) of the interviewees. The ground truth labels are derived by taking a weighted average over the ratings of 9 independent judges. Our framework can automatically predict the ratings for interview traits such as excitement, friendliness, and engagement with correlation coefficients of 0.75 or higher, and can quantify the relative importance of prosody, language, and facial expressions. By analyzing the relative feature weights learned by the regression models, our framework recommends to speak more fluently, use less filler words, speak as "we" (vs. "I"), use more unique words, and smile more. We also find that the students who were rated highly while answering the first interview question were also rated highly overall (i.e., first impression matters). Finally, our MIT Interview dataset will be made available to other researchers to further validate and expand our findings.