Prompt-based mental health screening from social media text
Open Access
- 21 July 2024
- conference paper
- Published by Sociedade Brasileira de Computação
- p. 186-192
Abstract
This article presents a method for prompt-based mental health screening from a large and noisy dataset of social media text. Our method uses GPT 3.5. prompting to distinguish publications that may be more relevant to the task, and then uses a straightforward bag-of-words text classifier to predict actual user labels. Results are found to be on pair with a BERT mixture of experts classifier, and incurring only a fraction of its training costs.Keywords
All Related Versions
This publication has 18 references indexed in Scilit:
- Mental Health Prediction from Social Media Text Using Mixture of ExpertsIEEE Latin America Transactions, 2023
- SetembroBR: a social media corpus for depression and anxiety disorder predictionLanguage Resources and Evaluation, 2023
- Overview of eRisk 2022: Early Risk Prediction on the Internet2022
- Ensemble Hybrid Learning Methods for Automated Depression DetectionIEEE Transactions on Computational Social Systems, 2022
- User profiling and satisfaction inference in public information access servicesJournal of Intelligent Information Systems, 2021
- Morality Classification in Natural Language TextIEEE Transactions on Affective Computing, 2020
- Twitter Moral Stance Classification Using Long Short-Term Memory Networks2020
- τ-SS3: A text classifier with dynamic n-grams for early risk detection over text streamsPattern Recognition Letters, 2020
- SenseMood: Depression Detection on Social Media2020
- Fine-grained analysis of language varieties and demographicsNatural Language Engineering, 2020