Online Invited Seminar Talk
Monitoring Psychological Processes Underpinning Mental Disorders using Social Media Data
Laboratory of Digital and Computational Demography
Online Invited Seminar Talk via Zoom, September 30, 2020
Lucia Lushi Chen, visitor at the Digital and Computational Demography Laboratory at MPIDR gave an Online Seminar Talk about the use of social media data to monitor mental illness symptoms instead of predicting a mental health status.
Social media data has rich information about people’s emotions, moods, and life events. If a person seeks health care support for long-term health conditions such as depression, social media data may be useful to provide extra information about the person between clinical visits. Existing studies have mainly focused on using this "clinical whitespace" data to produce a prediction on mental status. This approach carries with it concerns around data privacy, stigmatization, model biases, and validity of ground truth labels. In her dissertation, Lucia Lushi Chen proposes to use social media data to monitor mental illness symptoms instead of predicting a mental health status. The five data-driven empirical studies in this thesis demonstrate that a computational approach can identify symptoms of affective disorder and suicidal ideation manifested in social media. Her thesis contributes to methods for connecting complex social media behavior to transdiagnostic symptoms. It is an important step for clinical workers and psychologists to explore the possibilities of using social media data to compensate "whitespace" in clinical visits.
Lucia Lushi Chen is a Ph.D. student at the University of Edinburgh, School of Informatics. Her research project involves using digital data to track the affective, cognitive, and behavioral changes of users, identifying the associations between digital signals and symptoms of mental disorders. She is interested in early symptom detection as a human-centered approach to assist interventions and early prevention of mental disorders or harmful behaviors. Along the way, she cares about ethical research practices, model bias and fairness. Her work involves understanding model biases and examining the ‘noise’ in social media signals. She is also passionate to communicate her research and machine learning methods on her YouTube channel: ML_made_simple