Exploring the relationship between YouTube video optimisation practices and video rankings for online marketing: a machine learning approach

YouTube plays a vital role in allowing firms to engage with customers and digitally market their products. Many firms operating on major e-commerce platforms (e.g., eBay and Amazon) rely on advertising their products on YouTube by creating video content providing product information. Hence, there is an increasing need for research to examine the various aspects of YouTube videos for better ranking and views. This research develops a framework through machine learning to predict if a particular video will rank in the top 10 on a YouTube search. This research investigates factors affecting video rankings via a post-model agnostic technique called Shapley Additive Explanations (SHAP) and sentiment analysis. The results show that video content creators should optimise video titles and descriptions with the keywords of interest. Creators should consider the sentiment of the description and strive for a positive tone. Finally, creators should solicit views and likes to obtain better rankings.