PhD Thesis Proposal: Nikola Banovic, "Method for Exploring and Understanding Complex Human Routine Behaviors from Large Behavior Logs"
Speaker
Nikola Banovic
HCII PhD candidate
When
-
Where
Gates Hillman Center 6115
Description
Committee:
Anind Dey (HCII) (Co-chair)
Jennifer Mankoff (HCII) (Co-chair)
Aniket Kittur (HCII)
Eric Horvitz (Microsoft)
Abstract:
User interfaces that learn about people’s behaviors by observing them and interacting with them enable a future in which technology helps people to be productive, comfortable, healthy, and safe. However, despite current advances in Artificial Intelligence that make such interfaces possible, it remains challenging to ensure that models that power those interfaces are free of biases that may negatively impact people. Thus, to make user interfaces that have a positive impact on people requires technology that can accurately model people’s behaviors. In this work, we focus on behaviors in the domain of human routines that people enact as sequences of actions they perform in specific situations, which we call behavior instances.
Jennifer Mankoff (HCII) (Co-chair)
Aniket Kittur (HCII)
Eric Horvitz (Microsoft)
Abstract:
User interfaces that learn about people’s behaviors by observing them and interacting with them enable a future in which technology helps people to be productive, comfortable, healthy, and safe. However, despite current advances in Artificial Intelligence that make such interfaces possible, it remains challenging to ensure that models that power those interfaces are free of biases that may negatively impact people. Thus, to make user interfaces that have a positive impact on people requires technology that can accurately model people’s behaviors. In this work, we focus on behaviors in the domain of human routines that people enact as sequences of actions they perform in specific situations, which we call behavior instances.
We propose a probabilistic, generative model of human routine behaviors, that can describe, reason about, and act in response to people’s behaviors. We ground our model in a holistic definition of human routines to constrain the patterns it extracts from the data to those that match routine behaviors. We train the model by estimating the likelihood that people will perform certain actions in different situations in a way that matches their demonstrated preference for those actions and situations in behavior logs. We leverage this computational model of routines to create visual analytics tools to aid stakeholders, such as domain experts and end users, in exploring, making sense of, and generating new insights about human behavior stored in large behavior logs in a principled way.
Host
Queenie Kravitz