Extracting and Analysing Metaphors in Migration Media Discourse: towards a Metaphor Annotation Scheme

Proceedings of the 13th Conference on Language Resources and Evaluation (LREC 2022), pages 237–243 Marseille, 20-25 June 2022 © European Language Resources Association (ELRA), licensed under CC-BY-NC-4.0 237 Automatic Detection of Stigmatizing Uses of Psychiatric Terms on Twitter V´eronique Moriceau, Farah Benamara, Abdelmoumene Boumadane IRIT, Universit´e de Toulouse, CNRS, Toulouse INP, UT3, Toulouse, France {firstname.lastname}@irit.fr Abstract 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. Keywords: mental health, opinion analysis, social media 1. Introduction Mental health stigma finds its roots in the history of psychiatry, in its connection to madness representa- tions. People suffering from mental disorders have of- ten been given a pejorative label that induces social re- jection with multiple negative impacts such as difficul- ties for professional integration, access to housing or interpersonal relationships (Giordana, 2010; Crisp et al., 2000; Lampropoulos et al., 2018). Difficulties con- cern also the treatment itself, including delay in initial medical consultation, difficulty in accepting the illness, tenuous therapeutic alliance, etc. (Giordana, 2010). Many studies analyzing newspaper articles pointed out a major diversion from the use of psychiatric terms (Athanasopoulou and V¨alim¨aki, 2014; Magliano et al., 2011). A French survey conducted by the OBSoCo (L’Observatoire Soci´et´e et Consomma- tion) (L’OBSoCo, 2015) noticed that the French terms for schizophrenic and schizophrenia are particularly used in the context of violent news items and are of- ten employed metaphorically with a negative connota- tion (e.g. A policewoman stabbed by a man oscillating between schizophrenia and radicalization). With the raise of the internet and social media, it be- comes important to analyze how psychiatric terms are employed by general people to act effectively against stigma. Indeed, from the internet users’ point of view, Berry et al. (2017) showed that tweeting about mental health helps reducing isolation, fighting stigmatization and raising awareness of mental health by improving knowledge, promoting free expression and strengthen- ing coping and empowerment strategies. In this paper, we focus for the first time on …

Content truncated to 500 words