Extracting Primary Emotions and Topics from the Al-Hayat Media Centre Magazine Publications, Using Topic Modelling and Lexicon-Based Approaches

Abstract

It is well recognized that ISIS have effectively utilized several channels to disseminate their propaganda. Producing a considerable amount of unstructured data, the Al-Hayat Media Centre had a cornerstone role in the implementation of the propaganda which targeted audiences of the Western world. Although there was a considerable effort by researchers to analyse the ISIS’s online propaganda, there are very few studies which try to relate the above-mentioned material with the emotions associated with it. In this paper, we study the influence of all known issues of the Islamic State magazines, published by the Al-Hayat Media Centre, used to disseminate propaganda, and introduced ideas to audiences outside Iraq and Syria. We perform a series of natural language processing techniques, such as Emotion and Polarity Analysis using a lexicon-based approach and topic modelling with Latent Dirichlet Allocation (LDA). We extract deep insights from the terrorist corpus, including the emotions that are dominant in the text, the combination of emotions (patterns) that the magazine authors attempt to evoke to the reader, the main topics of discussions and the overall ‘feel’ and theming of the propaganda. The combination of lexicon-based emotion analysis with the topic modelling further achieves a reduction in the ‘emotion noise’ that can be observed when applying the lexicon-based approach only, making clear which the dominant emotions are. The valuable findings discussed in this paper contribute to the existing Information Warfare literature as they provide a whole new perspective in the subject of ISIS’s propaganda. The method also aims to open an interdisciplinary discussion, with applications in politics, marketing, etc.

Deep parallel contextual analysis framework based emotion prediction in community wellness communications on social media

“…Document [ 2 ] built a social media emotional lexicon on top of HowNet, incorporating social media linguistic features and introduced a sliding window to compute a subjectivity tendency coefficient for emotional classification of social media texts. Document [ 3 ] developed a emotional lexicon based on topic modeling, characterized by language independence, fine granularity, and unlimited capacity. Although simpler, lexicon-based methods require substantial effort in lexicon construction, and their quality and coverage directly affect emotion prediction accuracy.…”

Behind Blue Skies: A Multimodal Automated Content Analysis of Islamic Extremist Propaganda on Instagram

“…For instance, Biswas and Deylami (2019) argue that the emotional framing of their mission increases the effectiveness of ISIS mobilization attempts. Other authors have started to examine the role of specific emotions in this context (Maragkos & Maravelakis, 2022), as emotions are known to motivate deeper information processing (Nabi, 2003) and play a motivating role in collective action (van Zomeren et al, 2008). Among others, these studies show that propaganda is more engaging when emotions such as anger (Lee & Colautti, 2022), or the elicitors of self-transcending emotions, are included (Frischlich, 2021).…”

“…Scholarship on Instagram as a propaganda tool is still relatively rare (Frischlich, 2022; but see Speckhard & Ellenberg, 2020). Second, we broadened prior work focusing on the textual and visual elements of propaganda (e.g., Maragkos & Maravelakis, 2022) by taking the entire logic of an Instagram campaign into account, thus including the hashtags employed to reach new audiences, the visual first impressions, and the text itself. Third, we sought to understand the mobilizing potential of Islamic extremist online propaganda by examining the collective action cues contained within the propaganda campaign.…”

“…Bouko et al (2022) show that Salafists express emotional hurt about the negative treatment of their ingroup, thereby potentially stirring up anger in their audience. A computational analysis of ISIS Al-Hayat Media Center magazines shows that similar emotions are evoked across languages: positive emotions of trust, joy, and anticipation are communicated together with negative emotions of fear and anger (Maragkos & Maravelakis, 2022). In the current study, we examined affect and emotions in Islamic extremist propaganda by studying three central affordances of Instagram: the hashtag, the image, and the text.…”