|
Activity Number:
|
389
- Words and Insights via Text Analysis
|
|
Type:
|
Invited
|
|
Date/Time:
|
Thursday, August 12, 2021 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Text Analysis Interest Group
|
|
Abstract #316724
|
|
|
Title:
|
Measuring the Impact of Behavior Change Interventions Using Free-Text
|
|
Author(s):
|
Michael Baiocchi* and Jordan Rodu
|
|
Companies:
|
Stanford University and University of Virginia
|
|
Keywords:
|
behavior;
causal inference;
measurement
|
|
Abstract:
|
Free-text is a flexible, and more authentic, modality for measuring behavior change. To assess the causal effect of behavior change we have gone back to the fundamentals of causal inference and rebuilt a framework for taking in free-text and isolating causal effects. We will start by describing our applied work in developing free-text based outcome measurements in both randomized controlled trials, as well as in observational studies. We will then abstract the key insights and discuss a generalized statistical framework for developing free-text based measurements.
|
Authors who are presenting talks have a * after their name.
