Examine How Content-unaware Attributes Influencing the Video Views of YouTuber

Chenrui Feng

doi:10.54097/q36r9p53

Authors

Chenrui Feng

DOI:

https://doi.org/10.54097/q36r9p53

Keywords:

Video views; YouTubers; linear regression model; model selection; diagnostic.

Abstract

YouTube is one of the most popular apps worldwide, and many people create channels to earn income as YouTubers. This research focuses on identifying content-unrelated attributes that impact video views and examining their influence. Initially, data cleaning is conducted to remove missing observations that are not useful for model fitting. Data exploration is performed to gain a basic understanding of the relationships between variables and the response, which may aid in variable selection and model construction. Linear regression models are then fitted to predict video views based on content-unrelated variables. In this paper, these models are compared to select the best one, followed by diagnostics using AIC, R-squared, and MSE. Additionally, the selected model is evaluated for its fit by checking linear assumptions, the presence of outliers, and the significance of predictors. Finally, potential drawbacks of the methods used in this research are discussed, along with consideration of future research directions.

Downloads

Download data is not yet available.

References

[1] Hruska J, Maresova P. Use of social media platforms among adults in the United States—Behavior on social media. Societies (Basel, Switzerland), 2020, 10(1): 27.

[2] Han B. How do YouTubers make money? A lesson learned from the most subscribed YouTuber channels. International Journal of Business Information Systems, 2020, 33(1): 132-143.

[3] Sukhee Han. Anatomizing Popular YouTube Channels of English-speaking Countries. International Journal of Internet, Broadcasting and Communication, 2020, 12(4), 42-47.

[4] Yildirim G, Kocaelli H A. Assessment of the content and quality of YouTube videos related zygomatic implants: A content–quality analysis. Clinical Implant Dentistry and Related Research, 2023, 25(3), 605-612.

[5] Al-Mamouri H, Baiee W R. Maximizing video popularity prediction: A holistic approach utilizing metadata and thumbnail analysis. AIP Conference Proceedings, 2024, 3097(1).

[6] Welbourne D J, Grant W J. Science communication on YouTube: Factors that affect channel and video popularity. Public Understanding of Science (Bristol, England), 2016, 25(6): 706-718.

[7] Halim Z, Hussain S, Hashim Ali R. Identifying content unaware features influencing popularity of videos on YouTube: A study based on seven regions. Expert Systems with Applications, 2022, 206: 117836.

[8] Nisa M U N, et al. Optimizing prediction of youtube video popularity using xgboost. Electronics (Basel), 2021, 10(23): 2962.

[9] Ladhari R, Massa E, Skandrani H. YouTube vloggers’ popularity and influence: The roles of homophily, emotional attachment, and expertise. Journal of Retailing and Consumer Services, 2020, 54: 102027.

[10] Baertl M. YouTube channels, uploads and views: A statistical analysis of the past 10 years. Convergence (London, England), 2018, 24(1): 16-32.