Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Social Proof00:52

Social Proof

32.4K
Social proof is a form of persuasion based on comparison and conformity. People compare their behavior and actions to what others are doing and will change to conform to do what their peers do.
32.4K
Social Traps01:41

Social Traps

27.0K
Social traps are negative situations where people get caught in a direction or relationship that later proves to be unpleasant, with no easy way to back out of or avoid. The concept was orignally introduced by John Platt who applied psychology to Garrett Hardin's "Tragedy of the Commons", where in New England herd owners could let their cattle graze in the common ground. This situation seems like a good idea, but an individual could have an advantage. If they owned...
27.0K
The Sense of Self: Reflected Self-Appraisal and Social Comparison02:57

The Sense of Self: Reflected Self-Appraisal and Social Comparison

56.2K
According to Charles Cooley, we base our image on what we think other people see (Cooley 1902). We imagine how we must appear to others, then react to this speculation. We don certain clothes, prepare our hair in a particular manner, wear makeup, use cologne, and the like—all with the notion that our presentation of ourselves is going to affect how others perceive us. We expect a certain reaction, and, if lucky, we get the one we desire and feel good about it. But more than that, Cooley...
56.2K
Social Scripts02:10

Social Scripts

10.3K
People tend to know what behavior is expected of them in specific, familiar settings. A script is a person’s knowledge about the sequence of events expected in a specific setting (Schank & Abelson, 1977). Essentially, scripts are a particular kind of schema, one containing default values for the features within an event. In the restaurant example, the script's features include the props (e.g., tables, menu, food, and money), the roles to be played (e.g., customer and waiter),...
10.3K
Social Facilitation01:04

Social Facilitation

36.6K
Not all intergroup interactions lead to negative outcomes. Sometimes, being in a group situation can improve performance. Social facilitation occurs when an individual performs better when an audience is watching than when the individual performs the behavior alone. This typically occurs when people are performing a task for which they are skilled.
36.6K
Social Loafing01:37

Social Loafing

39.7K
Another way in which a group presence can affect performance is social loafing—the exertion of less effort by a person working together with a group. Social loafing occurs when our individual performance cannot be evaluated separately from the group. Thus, group performance declines on easy tasks (Karau & Williams, 1993). Essentially individual group members loaf and let other group members pick up the slack. Because each individual’s efforts cannot be evaluated,...
39.7K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Measurement-Based Care Benchmarks and Bipolar Classification in ABCD Youth.

medRxiv : the preprint server for health sciences·2026
Same author

An AI-based chatbot to support health-related social needs among pediatric primary care population: Protocol for a pilot randomized controlled trial.

PloS one·2026
Same author

Toward trustworthy chatbots: a protocol for red teaming for health related conversations.

Scientific reports·2026
Same author

Toward Trustworthy Chatbots: A Protocol for Red Teaming for Health Related Conversations.

medRxiv : the preprint server for health sciences·2025
Same author

An AI-Based Chatbot to Support Health-Related Social Needs among Pediatric Primary Care Population: Protocol for a Pilot Randomized Controlled Trial.

medRxiv : the preprint server for health sciences·2025
Same author

Digital Health Technologies for Screening and Identifying Unmet Social Needs: Scoping Review.

Journal of medical Internet research·2025

Related Experiment Video

Updated: Feb 13, 2026

The Social Dimension of Stress: Experimental Manipulations of Social Support and Social Identity in the Trier Social Stress Test
11:13

The Social Dimension of Stress: Experimental Manipulations of Social Support and Social Identity in the Trier Social Stress Test

Published on: November 19, 2015

14.5K

Socially Grounded Exemplars Improve Synthetic Conversations for Health-Related Social Needs Navigation.

Syed-Amad Hussain1,2, Daniel I Jackson1,2, Samanvith Thotapalli3

  • 1Abigail Wexner Research Institute at Nationwide Children's Hospital.

Medrxiv : the Preprint Server for Health Sciences
|February 12, 2026
PubMed
Summary

Generating realistic synthetic data for conversational agents is crucial for addressing Health-Related Social Needs (HRSNs). Socially Grounded Exemplars (SGEs) improve data authenticity, outperforming traditional demographic methods and enhancing privacy in healthcare applications.

More Related Videos

Integrating Computerized Linguistic and Social Network Analyses to Capture Addiction Recovery Capital in an Online Community
08:53

Integrating Computerized Linguistic and Social Network Analyses to Capture Addiction Recovery Capital in an Online Community

Published on: May 31, 2019

5.8K
Assessment of Social Interaction Behaviors
06:41

Assessment of Social Interaction Behaviors

Published on: February 25, 2011

95.4K

Related Experiment Videos

Last Updated: Feb 13, 2026

The Social Dimension of Stress: Experimental Manipulations of Social Support and Social Identity in the Trier Social Stress Test
11:13

The Social Dimension of Stress: Experimental Manipulations of Social Support and Social Identity in the Trier Social Stress Test

Published on: November 19, 2015

14.5K
Integrating Computerized Linguistic and Social Network Analyses to Capture Addiction Recovery Capital in an Online Community
08:53

Integrating Computerized Linguistic and Social Network Analyses to Capture Addiction Recovery Capital in an Online Community

Published on: May 31, 2019

5.8K
Assessment of Social Interaction Behaviors
06:41

Assessment of Social Interaction Behaviors

Published on: February 25, 2011

95.4K

Area of Science:

  • Artificial Intelligence
  • Natural Language Processing
  • Health Informatics

Background:

  • Health-Related Social Needs (HRSNs) significantly impact patient health outcomes.
  • Conversational agents show promise for scalable support but face challenges with privacy and specialized training data.
  • Current synthetic data generation methods using personas often produce generic or stereotyped outputs due to reliance on coarse demographic attributes.

Purpose of the Study:

  • To introduce Socially Grounded Exemplars (SGEs) for generating more realistic and nuanced synthetic personas for conversational AI.
  • To develop and evaluate a two-stage pipeline using GPT-4o for generating SGEs and grounding synthetic dialogue.
  • To assess the effectiveness of SGEs in improving the diversity and authenticity of synthetic healthcare dialogues compared to traditional methods.

Main Methods:

  • Implemented a two-stage pipeline utilizing GPT-4o to generate Socially Grounded Exemplars (SGEs) from abstract persona attributes.
  • Employed SGEs to ground synthetic dialogue generation, exploring various prompting strategies including implicit name-based cueing.
  • Evaluated synthetic data quality using automatic metrics (Vendi Score) and blinded preference ratings from community behavioral health specialists (CBHS).

Main Results:

  • GPT-4o demonstrated high acceptability (85%) in generating SGEs.
  • Dynamic SGEs significantly enhanced lexical diversity in generated conversations (Vendi Score: 289.41 vs. 252.36).
  • The model combining dynamic SGEs with implicit name-based cueing received the highest preference ratings from CBHS (Bradley-Terry Score: 0.753), surpassing SGE-only and explicit demographic models.

Conclusions:

  • Socially Grounded Exemplars (SGEs) effectively leverage LLM knowledge to create diverse synthetic data, overcoming limitations of rigid demographic ontologies.
  • Implicit cueing, such as names, generates more authentic and less stereotyped representations than explicit demographic labeling.
  • This framework facilitates the creation of privacy-preserving conversational datasets for sensitive healthcare applications, supporting agent evaluation and development.