Automatic Depressive Symptom Detection on Social Media Using the BDI-II
Automatic depression detection from social media has been widely explored as a complementary approach to mental health assessment; however, most existing work has focused on binary user-level classification, paying limited attention to how individual depressive symptoms are linguistically manifested in online discourse. This study addresses this limitation through symptom-level depression detection grounded in the 21 items of the BDI-II. The evaluation considers general-purpose transformer models, architectures adapted to the mental health domain, and approaches based on embeddings leveraging large language models across multiple editions of the eRisk benchmark. Results indicate that embedding-based approaches such as GPT-4+SVM and LLaMA+SVM, provide competitive performance with lower computational cost, while domain-adapted models consistently outperform general-purpose transformers. Symptom-level analysis reveals that affective symptoms are more reliably detected, whereas cognitively complex, behavioral, or sensitive symptoms remain underrepresented in social media text.
Palabras clave: Depression, Beck Depression Inventory, Social Media
Publicación: Congreso
1788258017132
1 de setembro de 2026
/research/publications/automatic-depressive-symptom-detection-on-social-media-using-the-bdi-ii
Automatic depression detection from social media has been widely explored as a complementary approach to mental health assessment; however, most existing work has focused on binary user-level classification, paying limited attention to how individual depressive symptoms are linguistically manifested in online discourse. This study addresses this limitation through symptom-level depression detection grounded in the 21 items of the BDI-II. The evaluation considers general-purpose transformer models, architectures adapted to the mental health domain, and approaches based on embeddings leveraging large language models across multiple editions of the eRisk benchmark. Results indicate that embedding-based approaches such as GPT-4+SVM and LLaMA+SVM, provide competitive performance with lower computational cost, while domain-adapted models consistently outperform general-purpose transformers. Symptom-level analysis reveals that affective symptoms are more reliably detected, whereas cognitively complex, behavioral, or sensitive symptoms remain underrepresented in social media text. - Cielo Aholiva Higuera-Gutiérrez, Irvin Hussein López-Nava, Manuel Montes-y-Gómez, Mario Ezra Aragón , and David E. Losada - 10.1007/978-3-032-28393-1_26 - 978-3-032-28392-4
publications_gl