Google award to aid positive empathy project
With a grant from Google, a University of Illinois at Chicago psychologist will lead a project to identify the features of personal stories that trigger empathy and determine if empathy causes stories to go viral.
Sylvia Morelli, UIC assistant professor of psychology, earned the prestigious award through the annual Google Faculty Research Awards program, which supports world-class research in computer science and related topics, such as machine learning, machine perception, natural language processing and quantum computing.
Google received more than 1,000 proposals from 46 countries and over 360 universities. After expert reviews and committee discussions, 152 projects were chosen for funding in the recently announced 2017 round cohort.
The $50,000 award will fund a graduate student for one year and provides both faculty and students the opportunity to work directly with Google researchers and engineers.
Morelli’s project, “Predicting empathy for others’ stories with machine learning,” builds on current work in her lab, where researchers have already collected more than 700 stories in which people describe the best and worst events of their lives.
“As a next step, we will ask 1,000 online participants to read these personal stories and rate how much empathy they feel for the storyteller,” said Morelli, who directs the Empathy and Social Connection Lab at UIC.
Morelli’s team will then see if the characteristics of the reader — such as age, gender, race, and personality — predict how much empathy the reader feels.
In addition, the research team will test if the vividness of the story, intensity of the storyteller’s emotions, or details of the storyteller’s circumstances predict readers’ empathy.
In the project’s second phase, the researchers will find first-person narratives from websites like Humans of New York, Story Corps and Upworthy, and investigate whether readers’ empathy makes stories go viral. Using a machine learning algorithm, they will determine which psychological and linguistic features of the story predict readers’ empathy and how frequently a story is shared and liked on websites.
“We hope the results of our studies can be used to help people communicate more effectively and create content that others care about,” Morelli said.