SavedAdd your journal

Journals / İstanbul Gelişim Üniversitesi Sağlık Bilimleri Dergisi / 2026 / Sayı: 29 Özel Sayı

Can Artificial Intelligence Reliably Detect Risky Eating Narratives? A Comparative Analysis of YouTube Extreme Diet Videos

Yapay Zekânın Riskli Yeme Anlatılarını Belirlemedeki Güvenilirliği: YouTube Radikal Diyet Videolarının Karşılaştırmalı Analizi

İrem Başören(ISTANBUL GELISIM UNIVERSITY)0009-0007-1095-6603
Hilal Aksoy(HACETTEPE UNIVERSITY, INSTITUTE OF INFORMATICS)0009-0008-2715-6597
Abdullah Furkan Korkmaz(GAZI UNIVERSITY, FACULTY OF SCIENCE, DEPARTMENT OF MATHEMATICS)0009-0006-6485-0567
Zehra Margot Çelik(Marmara University)0000-0002-4622-9252
Pages
37–53
Publication Date
2026-08-02
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

Interdisciplinary collaboration is required to ensure that AI-powered content analysis aligns with public health priorities.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Aim: This descriptive study was conducted to identify characteristics that are related to binge eating in YouTube videos that have been shared with the keywords “extreme diet” and “diet challenge” and to compare classifications made by expert dietitians with those generated by an artificial intelligence model.
📊
Key Findings & Data:Method: A total of 49 YouTube videos that met the inclusion criteria were analyzed.
💡
Conclusion & Impact:Interdisciplinary collaboration is required to ensure that AI-powered content analysis aligns with public health priorities.
🔬Design:Modeling & Simulation
📍Scope:2021–2026 Verileri
⚙️Variables:Beslenme · yapay zekâ · tıkınırcasına yeme bozukluğu

Abstract

Aim: This descriptive study was conducted to identify characteristics that are related to binge eating in YouTube videos that have been shared with the keywords “extreme diet” and “diet challenge” and to compare classifications made by expert dietitians with those generated by an artificial intelligence model. Method: A total of 49 YouTube videos that met the inclusion criteria were analyzed. The video characteristics were evaluated in relation to the view count, number of likes and comments, video duration, and time elapsed since upload . The quality of information provided in the video was assessed using the Modified DISCERN instrument, JAMA Benchmark Criteria, and Global Quality Score (GQS). A study-specific Binge Eating–Related Scoring System (BERS), consisting of 15 dichotomous items and based on video transcripts, was independently applied by both expert dietitians and the Gemini 3 Pro artificial intelligence model. In addition, 89,240 user comments were analyzed using R-based sentiment and emotion analysis techniques. Google Trends data for 2021–2026 were also evaluated. Statistical analyses were performed using SPSS 22.0. Results: The median number of views was 2,043,167 (IQR: 1,043,285–5,550,269). AI-based BERS scores showed significant positive correlations with the number of views (r=0.471), likes (r=0.453), comments (r=0.423), and video length (r=0.543) (p<0.05). A moderate positive correlation was found between expert-rated and AI-generated BERS scores (r=0.577, p<0.001). Higher binge eating–related scores were negatively correlated with educational quality scores (GQS). Sentiment analysis revealed that 41.3% of comments were positive, and the most frequently identified emotions were trust and joy. Google Trends indicated a peak in “extreme diet” searches in 2026. Conclusion: Highly engaging YouTube content often not only normalizes extreme eating behaviors but is also received positively by viewers. AI proved to be moderately reliable for identifying binge eating-related features, thus suggesting its potential as a scalable screening tool for monitoring harmful health trends. Interdisciplinary collaboration is required to ensure that AI-powered content analysis aligns with public health priorities.

Özet

Amaç: Bu tanımlayıcı çalışma, “extreme diet” ve “diet challenge” anahtar kelimeleri ile paylaşılan YouTube videolarında tıkınırcasına yeme ile ilişkili özelliklerin varlığını değerlendirmek ve uzman diyetisyenler tarafından yapılan sınıflandırmalar ile bir yapay zekâ modeli tarafından oluşturulan sınıflandırmaları karşılaştırmak amacıyla yapılmıştır. Yöntem: Dahil edilme kriterlerini karşılayan toplam 49 YouTube videosu analiz edilmiştir. Videoların görüntülenme sayısı, beğeni sayısı, yorum sayısı, süresi ve yüklenme tarihinden itibaren geçen süre kaydedilmiştir. Bilgi kalitesi Modifiye DISCERN aracı, JAMA (Journal of the American Medical Association) kriterleri ve Küresel Kalite Skoru (GQS) kullanılarak değerlendirilmiştir. Çalışmaya özgü 15 maddelik Tıkınırcasına Yeme ile İlişkili Puanlama Sistemi (BERS), uzman değerlendiriciler ve Gemini 3 Pro yapay zekâ modeli tarafından (video transkriptleri üzerinden) bağımsız olarak uygulanmıştır. Ayrıca 89.240 kullanıcı yorumu R programlama dili kullanılarak duygu ve duygu durumu analizi yöntemleriyle incelenmiştir. 2021–2026 yıllarına ait Google Trends verileri de değerlendirilmiştir. İstatistiksel analizler SPSS 22.0 programı ile gerçekleştirilmiştir. Bulgular: Medyan görüntülenme sayısı 2.043.167 (IQR: 1.043.285–5.550.269) olarak bulunmuştur. Yapay zekâ temelli BERS puanları ile görüntülenme (r=0,471), beğeni (r=0,453), yorum sayısı (r=0,423) ve video süresi (r=0,543) arasında istatistiksel olarak anlamlı pozitif ilişki saptanmıştır (p<0,05). Uzman ve yapay zekâ BERS puanları arasında orta düzeyde pozitif korelasyon belirlenmiştir (r=0,577, p<0,001). Tıkınırcasına yeme ile ilişkili daha yüksek puanların eğitimsel kalite (GQS) ile negatif ilişkili olduğu görülmüştür. Duygu analizinde yorumların %41,3’ünün pozitif olduğu; en sık belirlenen duyguların güven ve sevinç olduğu saptanmıştır. Google Trends verileri, 2026 yılında “extreme diet” aramalarında zirveye ulaşıldığını göstermiştir. Sonuç: Yüksek etkileşim alan YouTube içerikleri, aşırı yeme davranışlarını normalleştirebilmekte ve izleyiciler tarafından olumlu algılanabilmektedir. Yapay zekâ sistemi, tıkınırcasına yeme ile ilişkili özelliklerin belirlenmesinde orta düzeyde güvenilirlik göstermiş olup zararlı sağlık anlatılarının izlenmesinde ölçeklenebilir bir tarama aracı olarak potansiyel sunmaktadır. Yapay zekâ destekli içerik analizinin halk sağlığı öncelikleri ile uyumlu hale getirilmesi için disiplinler arası işbirliği gereklidir.

🔖

Cite This Article

Başören, İ., Aksoy, H., Korkmaz, A. F., Çelik, Z. M. (2026). Can Artificial Intelligence Reliably Detect Risky Eating Narratives? A Comparative Analysis of YouTube Extreme Diet Videos. İstanbul Gelişim Üniversitesi Sağlık Bilimleri Dergisi, Sayı: 29 Özel Sayı, 37–53. https://doi.org/10.38079/igusabder.1903214

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (39)

  1. Kircaburun K, Harris A, Calado F, Griffiths MD. The psychology of mukbang watching: A scoping review of the academic and non-academic literature. Int J Ment Health Addict. 2020;19(4):1190-1213.
  2. Kiss A, Tompa O, Lakner Z, Unger-Plasek B, Temesi Á, Soós S. Conveying sport nutrition information in YouTube videos: A qualitative content analysis of dietary advice and ways of communication. Curr Dev Nutr. 2025;9(9):107525.
  3. Kiss A, Soós S, Temesi Á, Unger-Plasek B, Lakner Z, Tompa O. Evaluation of the reliability and educational quality of YouTube videos on sport nutrition topics. J Int Soc Sports Nutr. 2023;20(1):2278632.
  4. Lim MSC, Molenaar A, Brennan L, Reid M, McCaffrey T. Young adults' use of different social media platforms for health information: Insights from web-based conversations. J Med Internet Res. 2022;24(1):e23656.
  5. Sanzari CM, Gorrell S, Anderson L, et al. The impact of social media use on body image and disordered eating behaviors: Content matters more than duration of exposure. Eat Behav. 2023;49:101722.
  6. Rounsefell K, Gibson S, McLean S, et al. Social media, body image and food choices in healthy young adults: A mixed methods systematic review. Nutr Diet. 2020;77(1):19-40.
  7. Moffitt L, Thomas MS. Influence of social media on dietary habits and nutritional choices in adolescents: A systematic review of the evidence. Int J Nutr Food Sci. 2025;14(4):211-225.
  8. Liu L, Yang J, Tan F, Luo H, Chen Y, Zhao X. Web-based video platforms as sources of information on body image dissatisfaction in adolescents: Content and quality analysis of a cross-sectional study. JMIR Form Res. 2025;9:e71652.
  9. Giel KE, Bulik CM, Fernandez-Aranda F, et al. Binge eating disorder. Nat Rev Dis Primers. 2022;8(1):16.
  10. Dane A, Bhatia K. The social media diet: A scoping review to investigate the association between social media, body image and eating disorders amongst young people. PLoS Glob Public Health. 2023;3(3):e0001091.
  11. Chiu MC, Penders B. “Maybe a long fast is good for you”: Health conceptualisations in YouTube diet videos. Front Commun. 2021;6:625906.
  12. Wu Y, Kemps E, Prichard I. Mind your figure! Watch, but don’t eat: A content analysis of eating and appearance-related messages in eating videos on social media. Body Image. 2025;52:101883.
  13. Akçay E, Bahadır B. Are YouTube videos a useful source of information on avoidant/ restrictive food intake disorder? Arch Curr Med Res. 2025;6(1):51-60.
  14. Ferrey A, Ashworth G, Cabling M, Rundblad G, Ismail K. A thematic analysis of YouTube comments on a television documentary titled ‘Diabulimia: The World's most dangerous eating disorder’. Diabet Med. 2023;40(5):e15025.
  15. Suresh A, Pallempati LL, Saxena P, Ansari A, Bassi R, Bhandari A. Exploring YouTube videos about anorexia nervosa on the basis of reliability, popularity, and contributions of healthcare professionals: A cross-sectional study. Cureus. 2023;15(11):e48095.
  16. Gimenez-Perez G, Robert-Vila N, Tomé-Guerreiro M, Castells I, Mauricio D. Are YouTube videos useful for patient self-education in type 2 diabetes? Health Informatics J. 2020;26(1):45-55.
  17. Megaly M, Khalil C, Tadros B, Tawadros M. Evaluation of educational value of YouTube videos for patients with coeliac disease. Int J Celiac Dis. 2016;4(3):102-104.
  18. Du RC, Zhang Y, Wang MH, Lu NH, Hu Y. TikTok and Bilibili as sources of information on Helicobacter pylori in China: A content and quality analysis. Helicobacter. 2023;28(5):e13007.
  19. Silberg WM, Lundberg GD, Musacchio RA. Assessing, controlling, and assuring the quality of medical information on the Internet: Caveat lector et viewor—Let the reader and viewer beware. JAMA. 1997;277(15):1244-1245.
  20. Bernard A, Langille M, Hughes S, Rose C, Leddin D, Van Zanten SV. A systematic review of patient inflammatory bowel disease information resources on the World Wide Web. Am J Gastroenterol. 2007;102(9):2070-2077.
  21. Ooms JJ. A simple and robust JSON parser and generator for R. CRAN website. https://cran.r-project.org/web/packages/jsonlite/. Published 2022. Accessed January 28, 2026.
  22. Silge J, Robinson D. tidytext: Text mining using tidy data principles. CRAN website. https://cran.r-project.org/web/packages/tidytext/. Published 2022. Accessed December 4, 2022.
  23. Wickham H, François R, Henry L, Müller K. dplyr: A grammar of data manipulation. CRAN website. https://cran.r-project.org/web/packages/dplyr/. Published 2022. Accessed December 4, 2022.
  24. Wickham H. stringr: Simple, consistent wrappers for common string operations. CRAN website. https://cran.r-project.org/web/packages/stringr/. Published 2022. Accessed December 4, 2022.
  25. Wickham H, Winston C, Henry L, et al. ggplot2: Create elegant data visualisations using the grammar of graphics. CRAN website. https://rdrr.io/cran/ggplot2/. Published 2022. Accessed January 28, 2026.
  26. Fellows I. wordcloud: Word clouds. CRAN website. https://cran.r-project.org/web/packages/wordcloud/. Published 2018. Accessed December 4, 2022.
  27. Neuwirth E. RColorBrewer: ColorBrewer palettes. CRAN website. https://cran.r-project.org/web/packages/RColorBrewer/. Published 2022. Accessed December 4, 2022.
  28. Baykan GB, Batıgün AD. Reliability and validity of the Binge Eating Scale-Turkish form. Turk J Clin Psychiatry. 2024;27:230-238.
  29. Ferhatoglu MF, Kartal A, Ekici U, Gurkan A. Evaluation of the reliability, utility, and quality of the information in sleeve gastrectomy videos shared on open access video sharing platform YouTube. Obes Surg. 2019;29(5):1477-1484.
  30. Tan D, Huang Y, Liu M, Li Z, Wu X, Huang C. Identification of online health information using large pretrained language models: Mixed methods study. J Med Internet Res. 2025;27:e70733.
  31. Benítez-Andrades JA, Alija-Pérez JM, Vidal ME, Pastor-Vargas R, García-Ordás MT. Traditional machine learning models and BERT-based automatic classification of tweets about eating disorders: Algorithm development and validation study. JMIR Med Inform. 2022;10(2):e34492.
  32. Dopelt K, Houminer-Klepar N. The impact of social media on disordered eating: Insights from Israel. Nutrients. 2025;17(1):180.
  33. Osman W, Mohamed F, Elhassan M, Shoufan A. Is YouTube a reliable source of health-related information? A systematic review. BMC Med Educ. 2022;22(1):382.
  34. Dünki A, Öztürk Ö. Assessment of informational quality and credibility of YouTube content on osteosarcoma. J Baltalimanı. 2025;1(2):53-57.
  35. Lin J, Portingale J, Krug I. Virtual feasts and their impact: A pilot study on the influence of mukbang videos on eating behaviours, body image, and emotional wellbeing. Body Image. 2025;56:102004.
  36. Ataguba G, Kalu I, Chan G, Orji R. Food mukbang on social media: Towards an AI-driven persuasive interventions for living healthy on social media. AI Soc. 2025;40:3295-3316.
  37. Roorda BA, Molnar M, Cassin SE. “What I eat in a day”: The effect of social media’s diet messaging on body image and dieting intentions. Dietetics. 2026;5(1):8.
  38. Fiuza A, Rodgers RF. The effects of brief diet and anti-diet social media videos on body image and eating concerns among young women. Eat Behav. 2023;51:101811.
  39. Serifler S, Gul F. Evaluating tonsillectomy-related YouTube videos via a human expert review and the ChatGPT-4: A multi-method quality analysis. BMC Med Educ. 2025;25(1):1157.