Invited Talk 3: Computational Modeling in Human-Computer Interaction
Nikola Banović · 2019
The proliferation of personal, mobile, and wearable devices and smart environments outfitted with precision sensors enabled tracking and collecting staggering amounts of human behavior traces data about people and their environments. For example, fitness trackers count each step we take, web search engines process and store each Internet search we make, social media sites record each personal connection we establish and each message we post, map and navigation applications record each place we visit. This offers a new source of data to study human behavior at scale and create future User Interfaces that can automatically reason about and act in response to people's behaviors. However, it is not immediately obvious how to: 1) explore such large amounts of heterogeneous and unlabeled data stored in behavior logs to understand people's behaviors, and 2) leverage it to build future User Interfaces. One promising solution, that addresses both challenges above, is computational modeling, which mathematically encodes a complex system (such as cognition, behaviors, and environments in which behavior is situated) to explore the system and act in response to modeled behaviors through simulation and prediction. In this talk, I will present a methodology that formalizes people's behaviors in a mathematical explanation encoded as a computational model. I illustrate the applications of computational models of human behavior in domains of Computational Interaction, Behavior Data Analytics, and Behavior-Aware User Interfaces. I conclude with a vision for modeling the human accurately across domains as a theoretical foundation for work in Human-Computer Interaction in which computational models enable us to study, describe, and understand complex human behaviors and support design, optimization, and evaluation of user interfaces.