How can computational linguistics help the implementation of evidence-based interventions?
Road Home Program
1645 West Jackson Blvd., Suite 302
Although Evidence-Based Programs (EBPs) can reduce a number of behavioral problems in a variety of contexts, their public health impact has not kept up with its potential. Poor implementation explains significant reductions in effect sizes when are translated to real-world settings.
Many sources of disconnect between the program as designed and as implemented can be measured, including provider’s fidelity to the program content, and the quality with which providers deliver the material. In this talk, we present computational methods developed from natural language processing, machine learning, and behavioral science to monitor implementation in an efficient, scalable, non-obtrusive, and automatic manner.
The goal, therefore, is to demonstrate that computational linguistics has the potential to improve the implementation of future generation behavioral interventions.