摘要：Disinformation does not always take the form of a fake news item, it also appears in much less evident formats which are subtly filtered into public opinion, thus making its detection more difficult. A method is proposed in this paper to address the study of “widespread” disinformation by combining social science methods with artificial intelligence and text mining. The case study chosen was the expression “right of self-determination” as a generator of disinformation within the context of the Catalan independence process. The main work hypothesis was that the (intentional or unintentional) confusion around the meaning and scope of this right has become widely extended within the population, generating negative emotions which favour social polarisation. The method utilised had three stages: (1) Description of the disinformation elements surrounding the term with the help of experts; (2) Detection of these elements within a corpus of tweets; (3) Identification of the emotions expressed in the corpus. The results show that the disinformation described by experts clearly dominates the conversation about “self-determination” on Twitter and is associated with a highly negative emotional load in which contempt, hatred, and frustration prevail.
