C-SoDA Speaker Series - Yu-Ru Lin (Computing & Information, Pittsburgh)

"Spatio-Temporal Learning for Forecasting Human-Societal Activity"
When Apr 10, 2019
from 12:15 PM to 01:30 PM
Where B001 Sparks Databasement
Contact Name
Contact Phone 814-267-2720
Attendees All interested members of the PSU community are welcome to attend.
Add event to calendar vCal
iCal

Yu-Ru Lin

Abstract:

The relationships between individual behavior and broader-scale societal structures have been central to a range of human phenomena, from job and migration decisions to political participation to the experience of a specific health-related event. Recent progress in predictive analytics along with big data offers a powerful way to explore those relationships but often gives rise to the "black box" problem with little insight into what goes on in the algorithmically learned relationships. In this talk, I will present a spatiotemporal learning approach that leverages a deep learning framework with relevant social theories to help examine the relationship between human-societal activity and their social and geographical contexts, with applications including predicting political protest and opioid overdose events. Our approach is not only capable of forecasting the occurrence of future events, but also provides theory-relevant interpretations -- it allows for interpreting what features, from which places, have significant contributions on the forecasting model, as well as how they make those contributions. I will discuss the results and implications of our recent studies based on the proposed approach.

 

Bio:

Yu-Ru Lin is an associate professor at School of Computing and InformationUniversity of Pittsburgh. She is interested in studying social and political networks, as well as computational and visualization methods for understanding network data. Her work has focused on large-scale community dynamics, high-dimensional (rich-context) social information summarization and representation. She has been using massive social media data and anonymized cellphone records to understand the collective responses with respect to political events and under exogenous shocks such as emergencies. She leads the PITT Computational Social Dynamics Lab (PICSO LAB).

She is a computer scientist by training, and a computational social scientist working on questions like: "how would a society be informed?" "how do people share information, ideas and opinions in various contexts?" These questions have led her to explore analytical and computational techniques for mining heterogeneous, multi-relational, and semistructured data that can advance our understanding about structures in networked societies. She was a postdoctoral research fellow at the Institute for Quantitative Social ScienceHarvard University and College of Computer and Information ScienceNortheastern University.

For more information visit http://www.yurulin.com.

Further details

A light lunch will be available starting at noon. All interested members of the Penn State community are welcome to attend.

Directions to the Databasement in Sparks can be found here.