Computational Methods in Comparative Media Analysis: Operationalization of Conflict Narrative Research Using the Example of CNN and Al Jazeera
- Authors: Sokolov A.V.1
-
Affiliations:
- Issue: No 12 (2025)
- Pages: 103-120
- Section: Articles
- URL: https://journals.rcsi.science/2454-0749/article/view/372111
- DOI: https://doi.org/10.7256/2454-0749.2025.12.77328
- EDN: https://elibrary.ru/PXYKFT
- ID: 372111
Cite item
Full Text
Abstract
The subject of the research is the application of computational methods in the comparative analysis of media narratives that shape representations of armed conflicts in the global media landscape. The object of the study consists of news materials from the international media outlets CNN and Al Jazeera related to the Israeli-Palestinian conflict. The author analyzes aspects of the topic such as the operationalization of theoretical concepts in media analysis, the comparison of narrative strategies across different media, and the possibilities of scalable analysis of media discourse. Special attention is given to how media not only reflect events but also construct meaning models of conflict through framing, tonality, and attribution of agency. The article examines differences in thematic priorities, emotional coloring, and narrative structure in the materials from the two media systems that represent different political and institutional contexts. It discusses the limitation of traditional qualitative analysis methods when working with large text corpora and the necessity of integrating computational tools into media research. Thus, the study aims to identify persistent narrative differences and to form a reproducible analytical framework for comparative studies of media discourse on conflicts. The methodology of the research is based on a hybrid approach that combines natural language processing methods, thematic modeling, and interpretative analysis using large language models. The main findings of the conducted research reveal systematic differences in the narrative and discursive strategies of CNN and Al Jazeera when covering the same conflict. It has been established that Al Jazeera's materials are characterized by a consistently negative tonal background and an emphasis on the humanitarian dimension of the conflict, while CNN creates a more fragmented narrative alternating between negative and positive plots related to diplomatic events. The novelty of the research lies in the development and testing of a meta-model for comparative media analysis, which combines quantitative computational methods with qualitative interpretation of media texts. A significant contribution of the author is the operationalization of classic theories of media studies through specific NLP metrics and procedures, which enhances the reproducibility and transparency of the analysis. It has been shown that the integration of large language models expands the possibilities for semantic comparison of narratives without losing analytical depth. The conclusion is made regarding the continued influence of institutional factors in media systems on the formation of media reality even in the context of digitalization and automation of analysis.
References
Алекян М. В., Ерицян Д. Е. Применение метода автоматизированного сентимент-анализа для изучения специфики контента Telegram-каналов // Системные трансформации журналистики. СПб.: Изд-во СПбГУ, 2024. С. 5-6. Асланов И. А. Метафорический фрейминг в медиатекстах и коммуникации о депрессии: результаты контент-анализа и эксперимента // Вестник Московского университета. Серия 10: Журналистика. 2020. № 6. С. 3-22. doi: 10.30547/vestnik.journ.6.2020.322. EDN: HMPDAS. Дунас Д. В., Салихова Е. А., Толоконникова А. В., Бабына Д. А. Установление повестки дня и эффект фрейминга: о необходимости концептуального единства в медиаисследованиях "цифровой молодёжи" // Вестник Московского университета. Серия 10: Журналистика. 2022. № 4. С. 47-78. doi: 10.30547/vestnik.journ.4.2022.4778. EDN: SAKNBB. Дунас Д. В., Толоконникова А. В., Бабына Д. А., Бойко О. А., Сидоров Е. А. Повестка дня в социальных медиа и федеральных информагентствах: тематический разрыв и смысловое единство (на примере "цифровой молодёжи" России) // Журнал Сибирского федерального университета. Гуманитарные науки. 2025. Т. 18, № 1. С. 178-193. EDN: LDWPTK. Казаков А. А. Теория установления повестки дня vs. фрейминг: к вопросу о соотношении подходов // Полития: Анализ. Хроника. Прогноз. 2015. № 1(76). С. 103-113. EDN: XRAJFZ. Соколов А. В. Контекстуализация панарабистского нарратива "Аль-Джазира": тематическая классификация, фрейминг и анализ тональности новостного контента // Журналист. Социальные коммуникации. 2024. № 4(56). С. 97-110. EDN: RHIQQQ. Blei D. M., Ng A. Y., Jordan M. I. Latent Dirichlet Allocation // Journal of Machine Learning Research. 2003. Vol. 3. P. 993-1022. Bojić L., Zagovora O., Zelenkauskaite A. et al. Comparing Large Language Models and Human Annotators in Latent Content Analysis of Sentiment, Political Leaning, Emotional Intensity and Sarcasm // Scientific Reports. 2025. Vol. 15. Article 11477. doi: 10.1038/s41598-025-96508-3. EDN: HRTTTY. Burggraaff C., Trilling D. Through a Different Gate: An Automated Content Analysis of How Online News and Print News Differ // Journalism. 2020. Vol. 21, № 1. P. 112-129. doi: 10.1177/1464884917716699. EDN: LONYBA. Chew R., Bollenbacher J., Wenger M., Speer J., Kim A. LLM-Assisted Content Analysis: Using Large Language Models to Support Deductive Coding // arXiv. 2023. doi: 10.48550/arXiv.2306.14924. Damanhoury K. E., Saleh F. Is It the Same Fight? Comparative Analysis of CNN and Al Jazeera America's Online Coverage of the 2014 Gaza War // Journal of Arab & Muslim Media Research. 2017. Vol. 10, № 1. P. 85-103. doi: 10.1386/jammr.10.1.85_1. Dunivin Z. O. A Computational Qualitative Approach to Large-Scale Characterization of Cultural Identities on Social Media // SocArXiv. 2025. doi: 10.31235/osf.io/5wvhx_v1. Elmasry M. H. Images of the Israel-Gaza War on Instagram: A Content Analysis of Western Broadcast News Posts // Journalism & Mass Communication Quarterly. 2024. Vol. 102, № 3. P. 695-721. doi: 10.1177/10776990241287155. EDN: MZSMIL. Entman R. M. Framing: Toward Clarification of a Fractured Paradigm // Journal of Communication. 1993. Vol. 43, № 4. P. 51-58. doi: 10.1111/j.1460-2466.1993.tb01304.x. Herman E. S., Chomsky N. Manufacturing Consent: The Political Economy of the Mass Media. New York: Pantheon Books, 2002. 412 p. Hossain A., Abdul Wahab J., Khan M. S. R. A. A Computer-Based Text Analysis of Al Jazeera, BBC, and CNN News Shares on Facebook: Framing Analysis on Covid-19 Issues // SAGE Open. 2022. Vol. 12(1). doi: 10.1177/21582440211068497. Hutto C. J., Gilbert E. VADER: A Parsimonious Rule-Based Model for Sentiment Analysis of Social Media Text // Proceedings of the International AAAI Conference on Weblogs and Social Media. 2014. Vol. 8(1). P. 216-225. doi: 10.1609/icwsm.v8i1.14550. Kim H., Jang S. M., Kim S.-H., Wan A. Evaluating Sampling Methods for Content Analysis of Twitter Data // Social Media + Society. 2018. Vol. 4(2). doi: 10.1177/2056305118772836. Kommers S. et al. Computational Hermeneutics: Evaluating Generative AI as a Cultural Technology // SSRN. 2025. doi: 10.2139/ssrn.5409144. McCombs M., Llamas J. P., Lopez-Escobar E., Rey F. Candidate Images in Spanish Elections: Second-Level Agenda-Setting Effects // Journalism & Mass Communication Quarterly. 1997. Vol. 74. P. 703-717. doi: 10.1177/107769909707400404. Mohr J. W., Wagner-Pacifici R., Breiger R. L. Toward a Computational Hermeneutics // Big Data & Society. 2015. Vol. 2, № 2. doi: 10.1177/2053951715613809. Pavelko R. L., Grabe M. E. Sampling, Content Analysis // The International Encyclopedia of Communication Research Methods. Wiley-Blackwell, 2017. P. 1-10. doi: 10.1002/9781118901731.iecrm0223. Picca D., Schnyder A., Romele A. Computational Hermeneutics of Emotion: A Comparative Study of Emotional Landscapes in Dostoevsky's "em"Crime and Punishment"/em" // Humanities and Social Sciences Communications. 2024. Vol. 11. Article 1428. doi: 10.1057/s41599-024-03955-w. EDN: EGTGVZ. Schroeder H., Aubin Le Quéré M., Randazzo C., Mimno D., Schoenebeck S. Large Language Models in Qualitative Research: Uses, Tensions, and Intentions // Proceedings of the CHI Conference on Human Factors in Computing Systems. 2025. P. 1-15. Seib P. The Al Jazeera Effect: How the New Global Media Are Reshaping World Politics. Washington, DC: Potomac Books, 2008. 240 p. Taher H. A., Alabid N., Hasan B. M. Integration Named Entity Recognition and Latent Dirichlet Allocation to Enhance Topic Modeling // Annals of Emerging Technologies in Computing. 2025. Vol. 9, № 2. P. 20-30. doi: 10.33166/AETiC.2025.02.002. EDN: SMQIZU. van Atteveldt W., Welbers K., Van der Velden M. A. C. G. Studying Political Decision Making With Automatic Text Analysis // Oxford Research Encyclopedia of Politics. Oxford University Press, 2019. P. 1-11. doi: 10.1093/acrefore/9780190228637.013.957.
Supplementary files

