SSP Forum: Johannes Eichstaedt on AI-based language analysis

Monday, March 7, 2022
Zoom meeting
Photo of Johannes Eichstaedt

The
Symbolic Systems Forum
presents

AI-based Language Analyses for Science, Public Health and Public Policy 

Johannes Eichstaedt
Psychology Department

Monday, March 7, 2022
12:15-1:15 pm
Everyone is welcome to join from PC, Mac, Linux, iOS or Android (requires logging in to a Zoom account): https://stanford.zoom.us/j/99713091022?pwd=b0hna3VRUkFWWHl0TUEwcTRQYktwQT09
(Only students enrolled in SYMSYS 280 may attend in person, provided in-person instruction resumes before this date.)

ABSTRACT:

The content shared on social media is the largest data set on human thoughts, emotions, and behaviors in history. We use Natural Language Processing and machine learning to leverage this data for social good and psychological science. I will demonstrate how Facebook data can be used to predict depression of patients before it appears in their medical records, and how Twitter can predict the heart disease of communities better than standard risk factors. Finally, if we have time, I will talk about our new work to equip transformer-based language models with personality. Across these studies, I show that large-scale language analyses with AI can augment clinical practice, guide prevention, and inform public policy.

A NOTE ON THE RECORDING OF EVENTS:

If a decision has been made in advance to record an event and to make it available for later public viewing, the event announcement will usually state this. In many cases, however, decisions to record, and/or to make a recording available publicly, are not finalized before an event is announced. Availability decisions for recordings are often subject to what speakers prefer after an event has concluded, among other considerations that may include usage rights for material used in an event, as well as the need for, and practicality of, editing. When recordings are made publicly available, they will be linked within the original event announcement on the Symsys website in the days or weeks following an event. Unfortunately, we cannot follow up on individual requests for more information about whether and when a recording may become available if it is not yet posted publicly.