Wesley Ramos dos Santos

Wesley Ramos dos Santos, Ivandre Paraboni

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.

Wesley Ramos dos Santos, Ivandre Paraboni

Fundamental Big Five personality traits (e.g., Extraversion) and their facets (e.g., Activity) are known to correlate with a broad range of linguistic features and, accordingly, the recognition of personality traits from text is a well-known Natural Language Processing task. Labelling text data with facets information, however, may require the use of lengthy personality inventories, and perhaps for that reason existing computational models of this kind are usually limited to the recognition of the fundamental traits. Based on these observations, this paper investigates the issue of personality facets recognition from text labelled only with information available from a shorter personality inventory. In doing so, we provide a low-cost model for the recognition of certain personality facets, and present reference results for further studies in this field.