Behind the Stars: Uncovering Hidden Adjustments in Letterboxd Film Ratings

• Caio Santana Trigueiro UFMG
• Lucas Dayrell UFMG
• Arthur Buzelin UFMG
• Guilherme H. G. Evangelista UFMG
• Caio Souza Grossi UFMG
• Virgilio A. F. de Almeida UFMG
• Wagner Meira Jr. UFMG

DOI: https://doi.org/10.5753/webmedia.2025.16181

Abstract

Letterboxd’s movie ratings influence millions, yet its scoring algorithm is opaque. We investigate the discrepancy between the platform’s displayed score and the true user rating average, which we define as Δ. Analyzing a corpus of 1,737 Brazilian films and over 1.3 million ratings, we uncover the factors driving this distortion. Our analysis reveals a systematic algorithmic compression that pulls extreme scores toward the mean, with a strong negative correlation (−0.903) between a film’s true rating and its Δ. Using K-Means, we identify four distinct rating distribution profiles (e.g., Polarized, Highly-Rated) and demonstrate that these profiles, along with genre, are significant predictors of the score adjustment. Niche genres like documentaries and musicals, which often exhibit polarized or extremely high ratings, are penalized most heavily. Furthermore, we find that popularity acts as a stabilizer; as a film’s rating count increases, the magnitude of Δ decreases. Taken together, these results indicate that Letterboxd employs a normalization mechanism that mitigates the influence of outlier patterns, potentially fostering more representative aggregate scores and enhancing comparability across films. This study proposes greater transparency in these algorithms that shape cultural consumption.

Keywords: Letterboxd, rating systems, algorithmic transparency, film recommendation, user behavior, score normalization, social platforms

References

Alberto Acerbi, John Burns, Unal Cabuk, Jakub Kryczka, Bethany Trapp, John Joseph Valletta, and Alex Mesoudi. 2023. Sentiment Analysis of the Twitter Response to Netflix’s *Our Planet* Documentary. Conservation Biology 37, 4 (2023), e14060. DOI: 10.1111/cobi.14060

Aditya Bhardwaj, Chirla Rushil Reddy, and Palak Arora. 2023. Movie Recommendation System Using SVD (Letterboxd). International Journal of Advanced Research in Computer and Communication Engineering 12, 10 (2023). DOI: 10.17148/IJARCCE.2023.121013

Yinchang Chen and Zhe Dai. 2022. Mining of Movie Box Office and Movie Review Topics Using Social Network Big Data. Frontiers in Psychology 13 (2022), 903380. DOI: 10.3389/fpsyg.2022.903380

Alfonso Crisci, Valentina Grasso, Paolo Nesi, Gianni Pantaleo, Irene Paoli, and Imad Zaza. 2018. Predicting TV Programme Audience by Using TwitterBased Metrics. Multimedia Tools and Applications 77, 10 (2018), 12203–12232. DOI: 10.1007/s11042-017-4880-x

Rafael M. D’Addio, Marcos A. Domingues, and Marcelo G. Manzato. 2017. Exploiting Feature Extraction Techniques on Users’ Reviews for Movies Recommendation. Journal of the Brazilian Computer Society 23 (2017), 7. DOI: 10.1186/s13173-017-0057-8

Kacy Kim, Sukki Yoon, and Yung Kyun Choi. 2019. The effects of eWOM volume and valence on product sales – an empirical examination of the movie industry. International Journal of Advertising 38, 3 (2019), 471–488. DOI: 10.1080/02650487.2018.1535225 arXiv: [link]

Vassilis Kostakos. 2009. Is the Crowd’s Wisdom Biased? A Quantitative Analysis of Three Online Communities. In 2009 International Conference on Computational Science and Engineering. IEEE, 251–255. DOI: 10.1109/cse.2009.491

BoYang Lu, Jia Li, YuZhong Chen, and Hao Xu. 2017. Evaluation of the Television Dramas Ranking Using the Bayes’ Theorem. In Proceedings of the 3rd Annual International Conference on Social Science and Contemporary Humanity Development (SSCHD 2017) (Advances in Social Science, Education and Humanities Research, Vol. 90). Atlantis Press, 155–157. DOI: 10.2991/sschd-17.2017.31

Washington Luiz, Felipe Viegas, Rafael Alencar, Fernando Mourão, Thiago Salles, Dárlinton Carvalho, Marcos Andre Gonçalves, and Leonardo Rocha. 2018. A Feature-Oriented Sentiment Rating for Mobile App Reviews. In Proceedings of the 2018 World Wide Web Conference (Lyon, France) (WWW ’18). InternationalWorld Wide Web Conferences Steering Committee, Republic and Canton of Geneva, CHE, 1909–1918. DOI: 10.1145/3178876.3186168

Laura Ridenour and Wooseob Jeong. 2016. Leveraging the Power of Social Reading and Big Data: An Analysis of CoRead Clusters of Books on Goodreads. In iConference 2016 Proceedings. [link]

Kunhao Yang, Itsuki Fujisaki, and Kazuhiro Ueda. 2023. Social Influence Makes Outlier Opinions in Online Reviews Offer More Helpful Information. Scientific Reports 13 (2023), 9625. DOI: 10.1038/s41598-023-35953-4

Víctor Yeste and Ángeles CalduchLosa. 2022. Exploratory Twitter Hashtag Analysis of Movie Premieres in the USA. In Desafíos Audiovisuales de la Tecnología y los Contenidos en la Cultura Digital. McGraw–Hill Interamericana de España S.L., 169–187.