Ramíırez-Cifuentes, DianaMayans Yern, MarcFreire, Ana2019-03-052018Ramírez-Cifuentes D, Mayans M, Freire A. Early risk detection of anorexia on social media. In: Bodrunova S, editor. Internet Science. 5th International Conference, INSCI 2018, Proceedings; 2018 Oct 24-26; St. Petersburg, Russia. Cham: Springer; 2018. p. 3-14. (LNCS; no. 11193. LNISA; no. 11193). DOI: 10.1007/978-3-030-01437-7_197830300143600302-9743http://hdl.handle.net/10230/36745Comunicació presentada a: INSCI 2018 celebrada del 24 al 26 d'octubre de 2018 a Sant Petersburg, Rússia.This paper proposes an approach for the early detection of anorexia nervosa (AN) on social media. We present a machine learning approach that processes the texts written by social media users. This method relies on a set of features based on domain-specific vocabulary, topics, psychological processes, and linguistic information extracted from the users’ writings. This approach penalizes the delay in detecting positive cases in order to classify the users in risk as early as possible. Identifying anorexia early, along with an appropriate treatment, improves the speed of recovery and the likelihood of staying free of the illness. The results of this work showed that our proposal is suitable for the early detection of AN symptoms.application/pdfeng© Springer The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-030-01437-7_1info:eu-repo/semantics/conferenceObjecthttp://dx.doi.org/10.1007/978-3-030-01437-7_1Early risk detectionEating disordersSocial mediaAnorexiaMachine learninginfo:eu-repo/semantics/openAccess