Home > Seminars > Morteza Dehghani - Computation and Morality: Integrating Diverse Data to Study Moral Behavior in the Wild

Morteza Dehghani - Computation and Morality: Integrating Diverse Data to Study Moral Behavior in the Wild

Start:

12/5/2019 at 3:30PM

End:

12/5/2019 at 4:45PM

Location:

131 DeBartolo

Host:

College of Engineering close button
headerbottom

Tim Weninger

Tim Weninger

VIEW FULL PROFILE Email: tweninge@nd.edu
Phone: 574-631-6770
Website: http://www.nd.edu/~tweninge/
Office: 353 Fitzpatrick Hall

Affiliations

College of Engineering Associate Professor
Network science, data science, machine learning, databases, and information retrieval.
Click for more information about Tim
574-631-6770
Add to calendar:
iCal vCal

My research combines observational studies of psychological processes encoded in social discourse with behavioral experimentation to study the relationship between human values and environmental and psychological factors, and to predict real-world behaviors. In this talk, I will discuss four major lines of research related to this framework: first, I will present preliminary results in a project in which we examine individuals' Facebook updates in combination with their self-reported moral concerns to predict individual moral concerns from language. Next, I will discuss a project in which we demonstrate how moralization on social networks shapes real-world violence, and how hourly counts of moral tweets during the Baltimore 2015 protests predicts count of arrests as reported by the Baltimore Police Department. Then, I will discuss our work at the intersection of morality and hate, and demonstrate that the prevalence of hate groups in a particular region can be predicted based on group-based moral values held in that region. Lastly, I will discuss a project in which we exposed English, Mandarin, and Farsi native speakers to native language translations of the same moral stories during fMRI scanning, and demonstrate that using distributed representations of these stories, we can identify the specific story a participant was reading from the neural data. I will conclude by discussing how methodological developments at the intersection of NLP and psychology can have transformational effects on the study of morality, improving the ecological validity of a field that has relied almost exclusively on self-reported answers to preset questionnaires.

Seminar Speaker:

Morteza Dehghani

Morteza Dehghani

University of Southern California

Morteza is an Assistant Professor of psychology, computer science and the Brain and Creativity Institute (BCI) at University of Southern California. His research spans the boundary between psychology and artificial intelligence. His work investigates properties of cognition by using documents of the social discourse, such as narratives, social media, transcriptions of speeches and news articles, in conjunction to behavioral studies. Morteza's research interests include theory-based natural language processing with direct applications to moral decision-making, group dynamics, and intergroup conflict and negotiation. He received his BS and MS from UCLA, and PhD from Northwestern. Morteza is a recipient of the NSF CAREER Award, in addition to the Young Investigator award from the Air Force Office of Scientific Research.