SMHD-GER: A Large-Scale Benchmark Dataset for Automatic Mental Health Detection from Social Media in German

AbstractMental health problems are a challenge to our modern society, and their prevalence is predicted to increase worldwide. Recently, a surge of research has demonstrated the potential of automated detection of mental health conditions (MHC) through social media posts, with the ultimate goal of enabling early intervention and monitoring population-level health outcomes in real-time. Progress in this area of research is highly dependent on the availability of high-quality datasets and benchmark corpora. However, the publicly available datasets for understanding and modelling MHC are largely confined to the English language. In this paper, we introduce SMHD-GER (Self-Reported Mental Health Diagnoses for German), a large-scale, carefully constructed dataset for MHC detection built on high-precision patterns and the approach proposed for English. We provide benchmark models for this dataset to facilitate further research and conduct extensive experiments. These models leverage engineered (psycho-)linguistic features as well as BERT-German. We also examine nuanced patterns of linguistic markers characteristics of specific MHC.