Instagram Reels Engagement Drivers: Machine Learning Insights into Celebrities and Brands

Abstract

The paper explores the major motivators of user interaction on Instagram Reels, a rising short video form in digital marketing. Despite the central role played by Reels in content strategies, there is still minimal empirical research on which specific features are relevant in driving the engagement. To fill this gap, we analyzed 438 Instagram Reels of global celebrities and brands in the period from January to March 2024. A combination of exploratory data analysis with a Random Forest regression model was applied in a specific way so that it could estimate the importance of the features and find the most significant predictors of the engagement rate. These were the ranked features, which then were the input of a K-Means clustering analysis which indicated patterns of content that were linked to different degrees of audience response. The results indicate that celebrity and brand presence is the most influential factor (22.10% importance), followed by content type (19.03%), age representation (16.27%), and human activity (16.16%). In contrast to common assumptions, the findings show that neutral emotional tone generates the highest engagement, while positive tone yields the lowest, suggesting that authenticity and subtle emotional expression may be more effective than overt positivity in short-form video contexts. The combination of machine learning methods and traditional engagement theory within the study gives practical recommendations to the marketer and will create a clear, reproducible map of research on short-form video analytics in the future.

Keywords

• Instagram Reels
• Digital marketing
• Engagement Rate
• Machine Learning
• Social Media Marketing

Ethical Statement

The study entitled “Instagram Reels Engagement Drivers: Machine Learning Insights into Celebrities and Brands” was conducted in accordance with scientific research principles, ethical standards, and citation guidelines. No manipulation, fabrication, or falsification was performed on the collected data. Furthermore, this study has not been submitted to any other academic publication venue for evaluation. Ethical committee approval was not required for this research. Statement of Contribution Rate of Researchers: The first author contributed 60%, and the second author contributed 40%. Declaration of Conflict: There are no potential conflicts of interest in this study. Funding: No funding was received from any institution or organization for this study. Statement of Use for Artificial Intelligence and Its Types: Artificial intelligence and its various types were not used in the writing of this article. Data Sharing Statement: We declare that, upon reasonable request for the purpose of verifying the findings, we can share the data of this study according to the conditions specified in the relevant section of the "ethical principles and publication policy". Notes: This article was presented as a poster at the European Academy of Marketing (EMAC) Spring Conference 2025, held in Pozuelo, Spain, from 27-30 May 2025.

Instagram Reels Etkileşimini Artıran Faktörler: Ünlüler ve Markalar Hakkında Makine Öğrenmesi İçgörüleri

Abstract

Bu çalışma, dijital pazarlamada yükselen kısa video formatlarından biri olan Instagram Reels üzerinde kullanıcı etkileşimini yönlendiren temel faktörleri incelemektedir. Reels içerik stratejilerinde merkezi bir rol oynamasına rağmen, etkileşimi hangi spesifik özelliklerin yönlendirdiğine dair ampirik araştırmalar hâlen sınırlıdır. Bu boşluğu doldurmak amacıyla, Ocak–Mart 2024 döneminde küresel ölçekte tanınan ünlüler ve markalar tarafından paylaşılan 438 Instagram Reels içeriği analiz edilmiştir. Özelliklerin önemini tahmin edebilmek ve etkileşim oranının en güçlü belirleyicilerini ortaya koyabilmek için keşifsel veri analizi ile Random Forest regresyon modeli birlikte kullanılmıştır. Elde edilen özellik önem sıralamaları, farklı düzeylerde izleyici tepkisiyle ilişkilendirilen içerik örüntülerini belirlemek amacıyla K-Means kümeleme analizine girdi olarak kullanılmıştır. Sonuçlar, ünlü ve marka varlığının en etkili faktör olduğunu (%22,10 önem düzeyi), bunu içerik türü (%19,03), yaş temsili (%16,27) ve insan aktivitesi (%16,16) değişkenlerinin izlediğini göstermektedir. Yaygın varsayımların aksine, bulgular nötr duygusal tonun en yüksek etkileşimi sağladığını, olumlu tonun ise en düşük etkileşim düzeyine sahip olduğunu ortaya koymaktadır. Bu durum, kısa video bağlamında özgünlük ve daha örtük duygusal ifadenin, açık ve yoğun pozitiflikten daha etkili olabileceğini düşündürmektedir. Makine öğrenmesi yöntemlerinin geleneksel etkileşim teorileriyle birlikte kullanılması, pazarlamacılara yönelik pratik öneriler sunmakta ve gelecekte kısa video analitiği alanındaki araştırmalar için açık ve tekrarlanabilir bir çerçeve ortaya koymaktadır.

Keywords

• Instagram Reels
• Dijital Pazarlama
• Etkileşim Oranı
• Makine Öğrenmesi
• Sosyal Medya Pazarlaması

Ethical Statement

“Instagram Reels Etkileşimini Artıran Faktörler: Ünlüler ve Markalar Hakkında Makine Öğrenmesi İçgörüleri” başlıklı çalışmanın yazım sürecinde bilimsel kurallara, etik ve alıntı kurallarına uyulmuş; toplanan veriler üzerinde herhangi bir tahrifat yapılmamış ve bu çalışma herhangi başka bir akademik yayın ortamına değerlendirme için gönderilmemiştir. Bu araştırma da etik kurul kararı zorunluluğu bulunmamaktadır. Araştırmacıların Katkı Oranı Beyanı: 1.yazar: % 60, ikinci yazar % 40 oranında katkı sağlamıştır. Çatışma Beyanı: Çalışmada herhangi bir potansiyel çıkar çatışması söz konusu değildir. Finansman: Bu çalışma için herhangi bir kurum veya kuruluştan destek alınmamıştır. Yapay Zeka ve Türleri Kullanım Beyanı: Bu makalenin yazımında yapay zeka ve türleri kullanılmamıştır. Veri Paylaşım Beyanı: Bu çalışmanın verilerini bulguların doğrulanması amacıyla makul bir talep üzerine “etik ilkeler ve yayın politikası”nın ilgili kısmında belirtilen şartlara göre paylaşabileceğimizi beyan ederiz. Not: Bu makale, 27-30 Mayıs 2025 tarihleri arasında İspanya'nın Pozuelo kentinde düzenlenen Avrupa Pazarlama Akademisi (EMAC) Bahar Konferansı 2025'te poster olarak sunulmuştur.

References

1. Aldhamiri, A., Carlson, J., Vilches-Montero, S., Rahman, S. M., & Gudergan, S. P. (2024). What drives higher active customer engagement in luxury brands’ social media? Measurement and contingencies. Journal of Retailing and Consumer Services, 79, 103804.
2. Alhabash, S., & Ma, M. (2017). A tale of four platforms: Motivations and uses of Facebook, Twitter, Instagram, and Snapchat among college students? Social Media + Society, 3(1), 2056305117691544. https://doi.org/10.1177/2056305117691544
3. Al Kurdi, B., Alshurideh, M. T., Hamadneh, S., Kalra, D., Marwaha, S., & Alzoubi, H. M. (2024, February). Machine learning applications in social media marketing: innovating customer engagement and brand building. In 2024 2nd international conference on cyber resilience (ICCR) (pp. 1-7). IEEE.
4. Andariesta, D. T., & Wasesa, M. (2023). Machine learning models to predict the engagement level of Twitter posts: Indonesian e-commerce case study. Procedia Computer Science, 227, 823-832.
5. Asan, K., & Zwiegelaar, J. (2025). Digital leisure use and psychological well-being among recreation management students: The mediating role of social media engagement. Journal of Hospitality, Leisure, Sport & Tourism Education, 37, 100570.
6. Berger, J., & Milkman, K. L. (2012). What makes online content viral? Journal of Marketing Research, 49(2), 192– 205. https://doi.org/10.1509/jmr.10.0353
7. De Vries, L., Gensler, S., & Leeflang, P. S. H. (2012). Popularity of brand posts on brand fan pages: An investigation of the effects of social media marketing. Journal of Interactive Marketing, 26(2), 83–91.
8. Gunawardena, C. N. (1995). Social presence theory and implications for interaction and collaborative learning in computer conferences. International journal of educational telecommunications, 1(2), 147-166.

9. Han, J., Kamber, M., & Pei, J. (2011). Data Mining: Concepts and Techniques (3rd ed.). Morgan Kaufmann.
10. Horton, D., & Wohl, R. R. (1956). Mass communication and para-social interaction: Observations on intimacy at a distance. Psychiatry, 19(3), 215–229. https://doi.org/10.1080/00332747.1956.11023049
11. Jin, X. L., Yin, M., Zhou, Z., & Yu, X. (2021). The differential effects of trusting beliefs on social media users’ willingness to adopt and share health knowledge. Information Processing & Management, 58(1), 102413.
12. Johnson, B. K., & Ranzini, G. (2018). Click here to look clever: Self-presentation via selective sharing of music and film on social media. Computers in Human Behavior, 82, 148-158.
13. Jolliffe, I. T., & Cadima, J. (2016). Principal component analysis: A review and recent developments. Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, 374(2065), 20150202. https://doi.org/10.1098/rsta.2015.0202
14. Kietzmann, J. H., Hermkens, K., McCarthy, I. P., & Silvestre, B. S. (2011). Social media? Get serious! Understanding the functional building blocks of social media. Business Horizons, 54(3), 241-251.
15. Kramer, A. D. I., Guillory, J. E., & Hancock, J. T. (2014). Experimental evidence of massive-scale emotional contagion through social networks. Proceedings of the National Academy of Sciences, 111(24), 8788–8790.
16. Krisprimandoyo, D. A., Sufa, S. A., Wardani, D. T., & Widiyanto, S. (2024). Exploring the relationship between social media engagement, customer reviews, and brand perceptions: A comprehensive study in retail industry. International Journal of Business, Law, and Education, 5(2), 1584-1591.
17. Liadeli, G., Sotgiu, F., & Verlegh, P. W. (2023). A meta-analysis of the effects of brands’ owned social media on social media engagement and sales. Journal of Marketing, 87(3), 406-427.
18. Lipsman, A., Mudd, G., Rich, M., & Bruich, S. (2012). The power of "like": How brands reach (and influence) fans through social-media marketing. Journal of Advertising Research, 52(1), 40–52.
19. Lou, C., & Xie, Q. (2021). Something social, something entertaining? How digital content marketing augments consumer experience and brand loyalty. International Journal of Advertising, 40(3), 376-402.
20. Meng, K. S., & Leung, L. (2021). Factors influencing TikTok engagement behaviors in China: An examination of gratifications sought, narcissism, and the Big Five personality traits. Telecommunications Policy, 45(7), 102172.
21. Menon, D. (2022). Factors influencing Instagram Reels usage behaviours: An examination of motives, contextual age and narcissism. Telematics and Informatics Reports, 5, 100007.
22. Moran, G., Muzellec, L., & Johnson, D. (2020). Message content features and social media engagement: Evidence from the media industry. Journal of Product & Brand Management, 29(5), 533–545.
23. Omar, B., & Dequan, W. (2020). Watch, share or create: The influence of personality traits and user motivation on TikTok mobile video usage. International Association of Online Engineering, 121-137.
24. Onofrei, G., Filieri, R., & Kennedy, L. (2022). Social media interactions, purchase intention, and behavioural engagement: The mediating role of source and content factors. Journal of Business Research, 142, 100-112.
25. Qin, Y. S. (2020). Fostering brand–consumer interactions in social media: the role of social media uses and gratifications. Journal of Research in Interactive Marketing, 14(3), 337-354.
26. Reddy, D., Singh, A., Chopra, R., & Patel, R. (2021). Leveraging machine learning algorithms and natural language processing for AI-Enhanced social media marketing analytics. Journal of AI ML Research, 10(8).
27. Reimer, T. (2023). Environmental factors to maximize social media engagement: A comprehensive framework. Journal of Retailing and Consumer Services, 75, 103458.
28. Schivinski, B. (2021). Eliciting brand-related social media engagement: A conditional inference tree framework. Journal of Business Research, 130, 594-602.
29. Shao, G. (2009). Understanding the appeal of user‐generated media: a uses and gratification perspective. Internet research, 19(1), 7-25.
30. Sichach, M. (2023). Uses and Gratifications Theory-Background, History and Limitations. History and Limitations (November 17, 2023).
31. Tafesse, W., & Wien, A. (2018). Using message strategy to drive consumer behavioral engagement on social media. Journal of Consumer Marketing, 35(3), 241-253.
32. Tajfel, H. (1974). Social identity and intergroup behaviour. Social Science Information, 13(2), 65-93.
33. Trunfio, M., & Rossi, S. (2021). Conceptualising and measuring social media engagement: A systematic literature review. Italian Journal of Marketing, 2021(3), 267-292.
34. Voorveld, H. A., Van Noort, G., Muntinga, D. G., & Bronner, F. (2018). Engagement with social media and social media advertising: The differentiating role of platform type. Journal of advertising, 47(1), 38-54.
35. Wallach, K. A., Pham, H., Koschmann, A., & Arwade, G. (2025). Analyzing the impact of faces on consumer engagement in social media videos: a machine learning approach. Journal of Consumer Marketing, 42(3), 318- 335.
36. Wibowo, A., Chen, S. C., Wiangin, U., Ma, Y., & Ruangkanjanases, A. (2020). Customer behavior as an outcome of social media marketing: The role of social media marketing activity and customer experience. Sustainability, 13(1), 189.
37. Wies, S., Bleier, A., & Edeling, A. (2023). Finding goldilocks influencers: How follower count drives social media engagement. Journal of Marketing, 87(3), 383-405.