Related Experiment Video
Updated: Apr 30, 2026
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
Leveraging Language Embeddings from EMA Surveys to Predict Perceived Social Isolation among Stroke Survivors
IEEE Journal of Biomedical and Health Informatics
|April 28, 2026
Summary
This study introduces a new method using language embeddings to predict perceived social isolation (PSI) in stroke survivors from Ecological Momentary Assessment (EMA) data, improving early intervention accuracy.
Area of Science:
- Neuroscience
- Psychology
- Computer Science
Background:
- Perceived social isolation (PSI) negatively impacts stroke survivors' emotional well-being.
- Ecological Momentary Assessment (EMA) is used to identify PSI precursors.
- Current prediction methods using handcrafted features lack semantic depth.
Purpose of the Study:
- To develop a novel approach for predicting PSI in stroke survivors.
- To leverage language embeddings for analyzing structured EMA data.
- To enhance real-time monitoring of psychosocial outcomes.
Main Methods:
- Collected 11,802 EMA surveys from 218 stroke survivors.
- Extracted language embeddings from EMA data using a pre-trained model.
- Trained an autoencoder on embeddings for PSI prediction.
Main Results:
- Achieved a weighted F1 score of 0.84 and AUPRC of 0.92 for PSI prediction.
- Outperformed traditional handcrafted feature methods.
- Demonstrated optimized prediction using only three selected questions.
Conclusions:
- The proposed language embedding approach accurately predicts PSI in stroke survivors.
- This method offers an efficient tool for real-time psychosocial monitoring.
- Potential for improved early intervention and personalized care in stroke recovery.
