Article « The mediums and the messages: exploring the language of Islamic State media through sentiment analysis » de Logan Macnair & Richard Frank, publié le 8 mars 2018. Résumé : « This study applies the method of sentiment analysis to the online media released by the Islamic State (IS) in order to distinguish the ways in which IS uses language within their media, and potential ways in which this language differs across various online platforms.
The data used for this sentiment analysis consist of transcripts of IS-produced videos, the text of IS-produced online periodical magazines, and social media posts from IS-affiliated Twitter accounts. It was found that the language and discourse utilised by IS in their online media is of a predominantly negative nature, with the language of videos containing the highest concentration of negative sentiment. The words and phrases with the most extreme sentiment values are used as a starting point for the identification of specific narratives that exist within online IS media. The dominant narratives discovered with the aid of sentiment analysis were: 1) the demonstrated strength of the IS, 2) the humiliation of IS enemies, 3) continuous victory, and 4) religious righteousness. Beyond the identification of IS narratives, this study serves to further explore the utility of the sentiment analysis method by applying it to mediums and data that it has not traditionally been applied to, specifically, videos and magazines. »