Best Practices in Automating Affect Recognition

Prof. Rosalind Picard, Massachusetts Institute of Technology

AI researchers have traditionally framed affect recognition as a pattern recognition problem, often ignoring context. What are some of the pitfalls posed by this framing and how might we avoid them, and improve results? This talk will give an overview with some suggestions for best practices.

What Text Analysis Cannot Tell Us: The Importance of Observation in Understanding Creative Teams

Prof. Page Moreau, University of Wisconsin-Madison

Facial expressions, physical settings, body posture, gestures, and spatial dynamics can convey crucial information that may be missed in a sentiment analysis. This talk will discuss the ways in which visual and contextual information can offer a deeper understanding of the meaning of the spoken words in creative settings. To illustrate this point, several short case studies will be presented along with a conceptual framework designed to highlight the role of visual information.

Towards an artificial intuition: Conversational markers of (anti)social dynamics

Prof. Cristian Danescu-Niculescu-Mizil, Cornell University

Can conversational dynamics—the nature of the back and forth between people—predict outcomes of social interactions? This talk will describe efforts on developing an artificial intuition about ongoing conversations, by modeling the subtle pragmatic and rhetorical choices of the participants. The resulting framework distills emerging conversational patterns that can point to the nature of the social relation between interlocutors, as well as to the future trajectory of this relation. For example, I will discuss how interactional dynamics can be used to foretell whether an online conversation will stay on track or eventually derail into personal attacks, providing community moderators several hours of prior notice before an anti-social event is likely to occur. The data and code are available through the Cornell Conversational Analysis Toolkit (ConvoKit): http://convokit.cornell.edu

This talk includes joint work with Jonathan P. Chang, Lucas Dixon, Liye Fu, Yiqing Hua, Dan Jurafsky, Lillian Lee, Jure Leskovec, Vlad Niculae, Chris Potts, Arthur Spirling, Dario Taraborelli, Nithum Thain, and Justine Zhang.

AI-assisted human creativity

Prof. Devi Parikh, Georgia Teach / Facebook AI Research

In this talk, I will present several projects where we explore how AI can inspire human creativity. These projects cover a variety of domains, including sketches, thematic typography, dance movements, and generative art. I will also talk about some of our work on generating a visual abstraction that summarizes how your day was.