32464 lrg
AI Modeling of Character Strengths to Predict Educational and Holistic Outcomes of Human Flourishing
TWCF Number
32464
Project Duration
September 1 / 2024
- August 31 / 2027
Core Funding Area
Big Questions
Priority
Discovery
Region
North America
Amount Awarded
$945,850

* A Grant DOI (digital object identifier) is a unique, open, global, persistent and machine-actionable identifier for a grant.

Director
Adam Green
Institution Georgetown University

A project led by Adam Green at Georgetown University’s Lab for Relational Cognition aims to leverage advanced artificial intelligence (AI) modeling to identify and assess the presence of character strengths in written language, specifically in college admissions statements and other similar forms of personal writing, and to then empirically link the identified character strengths with flourishing-related outcomes among American and Ghanaian university students. 

The project operates across three studies. Ten strengths will be explored: creativity, curiosity, persistence, kindness, citizenship, self-regulation, hope, and spirituality/purpose.

Study 1 employs a novel big data approach, utilizing a massive-scale dataset of college applicants from 24 diverse institutions. Large language models (LLMs) will be trained on existing data from personal statement essays as well as selected academic achievement and formative engagement outcomes. Models that best reflect each character strength and that most robustly relate those character strengths to achievement and formative engagement outcomes. This study will also consider whether these models can reduce known measurement biases (i.e., associated with race and socioeconomic status) that subsequently impact equity of opportunity for underrepresented populations in college admissions.

Study 2 takes a person-centered longitudinal approach, allowing the team to expand the types of personal writings and the outcomes that are investigated in relation to text-based assessments of character strengths. Additionally, Study 2 aims to assess character strengths and flourishing-related outcomes during a period of significant transition and growth for a young person: the initial years after graduation.

Recognizing that character strengths are value judgments that are culturally embedded, Study 3 will be a pilot proof of concept study into AI modeling of character strengths and outcomes that are valued in Ghana. This pilot study will be done in partnership with Ashesi University, a primarily English-language university in Accra that is also an academic partner of Arizona State University.

Disclaimer
Opinions expressed on this page, or any media linked to it, do not necessarily reflect the views of Templeton World Charity Foundation, Inc. Templeton World Charity Foundation, Inc. does not control the content of external links.
Person doing research
Projects &
Resources
Explore the projects we’ve funded. We’ve awarded hundreds of grants to researchers and institutions worldwide.

Projects & Resources