Comparação da Cobertura Jornalística Entre Portais de Notícias e YouTube: Um Estudo de Caso do Conflito entre Israel e Palestina

• Victor Martins UFMG
• Jussara M. Almeida UFMG
• Marcos Gonçalves UFMG

DOI: https://doi.org/10.5753/webmedia.2025.16193

Resumo

This study systematically investigates how the journalistic coverage of the same event can vary depending on the dissemination platform and the communication vehicle. The research focuses on the coverage of the Israel-Palestine conflict, analyzing content from official news portals and the YouTube channels of major mass-reach media organizations. To this end, we employed Natural Language Processing (NLP) techniques to comparatively characterize both the texts published on the portals and the video transcripts aired on the respective YouTube channels. For sentiment analysis, we utilized the TextBlob and VADER algorithms. Furthermore, we applied text similarity methods, such as the Longest Common Subsequence (LCS) technique and the SBERT (Sentence-BERT) model, to measure the degree of resemblance between headlines and correlated content. This helped to identify when seemingly similar texts actually converge or diverge in their focus. Using BERTopic, it was observed that, despite the existence of similar headlines between portals and videos, the associated texts frequently address distinct themes or emphasize varied aspects of the conflict. This methodological combination allowed us to demonstrate that the journalistic narrative is not uniform and can be significantly influenced by the dissemination platform, even when the base event is the same.

Palavras-chave: platform dissemination, Israel-Palestine conflict, natural language processing, topic modeling, text similarity

Referências

Kholoud Khalil Aldous, Jisun An, and Bernard J. Jansen. 2023. What really matters?: characterising and predicting user engagement of news postings using multiple platforms, sentiments and topics. Behaviour and Information Technology 42, 5 (2023), 545–568.

Artur Alvarez, Luisa Belchior, and Wesley Bischoff. 2025. Israel e Hamas chegam a acordo por cessar-fogo na guerra em Gaza, anuncia Catar. [link] Acesso em 13 fev. 2025.

Alberto Apostolico and Concettina Guerra. 1987. The longest common subsequence problem revisited. Algorithmica 2 (1987), 315–336.

Raffi Berg. 2024. What we know about the Gaza ceasefire deal. BBC News (2024). [link] Acesso em 02 de fevereiro de 2025.

Muriël de Groot, Mohammad Aliannejadi, and Marcel R. Haas. 2022. Experiments on Generalizability of BERTopic on Multi-Domain Short Text. arXiv:2212.08459

Ramit Debnath, Pengyu Zhang, Tianzhu Qin, R. Michael Alvarez, and Shaun D. Fitzgerald. 2024. Deciphering public attention to geoengineering and climate issues using machine learning and dynamic analysis. arXiv:2405.07010

Aline Dias, Richardy Tanure, Jussara Almeida, Helen Lima, and Carlos Ferreira. 2024. Análise da Percepção do Uso de Cigarros Eletrônicos no Brasil por meio de Comentários no YouTube. In Proceedings of the 30th Brazilian Symposium on Multimedia and the Web. 45–53.

Nimrod Dvir, Elaine Friedman, Suraj Commuri, Fan Yang, and Jennifer Romano. 2023. Words That Stick: Predicting Decision Making and Synonym Engagement Using Cognitive Biases and Computational Linguistics.

Yousra El-Ghawi, Abeer Marzouk, and Aya Khamis. 2024. LexiconLadies at FIGNEWS 2024 Shared Task: Identifying Keywords for Bias Annotation Guidelines of Facebook News Headlines on the Israel-Palestine 2023 War. In Proceedings of The Second Arabic Natural Language Processing Conference. 561–566.

Nikolaos Alexandros Goudis. 2024. Beyond the lens: An analysis of CNN, Al Jazeera and protothema.gr news photographs of the 2023 Israel-Palestine war. Univerzita Karlova, Fakulta sociálních věd, Praga, Tchéquia.

Kyeo Re Lee Jang Hyun Kim Haein Lee, Seon Hong Lee. 2023. ESG Discourse Analysis Through BERTopic: Comparing News Articles and Academic Papers. Computers, Materials & Continua 75, 3 (2023), 6023–6037.

Simon Hofmann, Christoph Sommermann, Mathias Kraus, Patrick Zschech, and Julian Rosenberger. 2024. Hate Speech and Sentiment of YouTube Video Comments From Public and Private Sources Covering the Israel-Palestine Conflict. 19th International Conference on Wirtschaftsinformatik (2024).

C.J. Hutto and Eric Gilbert. 2014. VADER: A Parsimonious Rule-based Model for Sentiment Analysis of Social Media Text. In Proceedings of the International AAAI Conference on Web and Social Media, Vol. 8. AAAI, 216–225.

Ian Kloo, Iain J. Cruickshank, and Kathleen M. Carley. 2024. A Cross-Platform Topic Analysis of the Nazi Narrative on Twitter and Telegram during the 2022 Russian Invasion of Ukraine. Proceedings of the International AAAI Conference on Web and Social Media 18, 1 (May 2024), 839–850.

Xinhang Li, Zhaopeng Qiu, Jiacheng Jiang, Yong Zhang, Chunxiao Xing, and Xian Wu. 2023. Conditional Cross-Platform User Engagement Prediction. ACM Trans. Inf. Syst. 42, 1, Article 6 (Aug. 2023), 28 pages.

Alexander Liu, Siqi Wu, and Paul Resnick. 2024. How to Train Your YouTube Recommender to Avoid Unwanted Videos.

Yankai Liu. 2024. A Corpus-Based Critical Discourse Analysis of News Reports on the 2023 Israel-Hamas War. Journal of Linguistics and Communication Studies 3, 3 (Aug. 2024), 70–84.

Steven Loria. 2014. TextBlob: Simplified Text Processing. [link] Versão usada: 0.15.3. Acesso em 15 de fevereiro de 2025..

The Observer. 2024. The Observer view: Shaky ceasefire is no victory for Netanyahu amid suffering of Gaza and hostages. [link] Acesso em 13 fev. 2025.

Karl Pearson. 1895. Notes on regression and inheritance in the case of two parents. Proceedings of the Royal Society of London 58 (1895), 240–242.

Limor Peer and Thomas B. Ksiazek and. 2011. YouTube and the challenge to Journalism. Journalism Studies 12, 1 (2011), 45–63.

Iury Pereira, Juan Avelar, Cláudio Silva, and Daniel Barbosa. 2024. Análise de Sentimentos em Vídeos do Youtube sobre Polarização Política: Uma Abordagem Híbrida Baseada em Reconhecimento de Entidades. In Anais do XIII Brazilian Workshop on Social Network Analysis and Mining. 221–227.

Iryna Reimers, Nils e Gurevych. 2019. Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). Association for Computational Linguistics, Hong Kong, China, 3982–3992.

Maud Reveilhac. 2024. YouTube as an information source on politics and current affairs: Supply- and demand-side perspectives. First Monday 29 (07 2024).

David Tewksbury and Jason Rittenberg. 2012. News on the Internet: Information and Citizenship in the 21st Century.