Automatic Detection of Stigmatizing Uses of Psychiatric Terms on Twitter.

Psychiatry and people suffering from mental disorders have often been given a pejorative label that induces social rejection. Many studies have addressed discourse content about psychiatry on social media, suggesting that they convey stigmatizing representations of mental health disorders. In this paper, we focus for the first time on the use of psychiatric terms in tweets in French. We first describe the annotated dataset that we use. Then we propose several deep learning models to detect automatically (1) the different types of use of psychiatric terms (medical use, misuse or irrelevant use), and (2) the polarity of the tweet. We show that polarity detection can be improved when done in a multitask framework in combination with type of use detection. This confirms the observations made manually on several datasets, namely that the polarity of a tweet is correlated to the type of term use (misuses are mostly negative whereas medical uses are neutral). The results are interesting for both tasks and it allows to consider the possibility for performant automatic approaches in order to conduct real-time surveys on social media, larger and less expensive than existing manual ones.