Prompt-based mental health screening from social media text
This work addresses mental health screening from social media, offering a cost-effective alternative to complex models, but it is incremental as it adapts existing methods rather than introducing a new paradigm.
The authors tackled mental health screening from noisy social media text by using GPT-3.5 prompting to filter relevant posts and a bag-of-words classifier for predictions, achieving results comparable to a BERT mixture of experts classifier with significantly lower training costs.
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.