Sindhu Kiranmai Ernala

TL;DR: These data reinforce the need for ongoing collaborations integrating expertise from multiple fields to strengthen the ability to accurately identify and effectively engage individuals with mental illness online and move from noisy self-reports of schizophrenia on social media to more accurate identification of diagnoses by exploring a human-machine partnered approach.

TL;DR: Focusing on three commonly used proxy diagnostic signals derived from social media, it is found that predictive models built on these data, although offer strong internal validity, suffer from poor external validity when tested on mental health patients.

TL;DR: Signs of therapeutic outcomes following disclosures of schizophrenia diagnoses made on Twitter are found, including improved readability and coherence in language, future orientation, lower self preoccupation, and reduced discussion of symptoms and stigma perceptions.

TL;DR: Comparing data from ten self-reported Facebook use survey measures deployed in 15 countries against data from Facebook's server logs to describe factors associated with error in commonly used survey items from the literature concludes with recommendations on the most accurate ways to collect time-spent data via surveys.

TL;DR: Social media activity captures objective linguistic and behavioral markers of psychotic relapse in young individuals with recent onset psychosis and machine-learning models were capable of making personalized predictions of imminent relapse hospitalizations at the patient-specific level.