YouTube is the largest video hosting platform. The site has emerged in 2005 and has achieved a continuous pattern of growth since its conception (Burgess & Green 2018). A high number of creators, viewers, subscribers and commentators act in this specific ecosystem which generates a huge amount of money. In this article, YouTube is considered as a bilateral network between the videos and the commentators. Analyzing a detailed data set focused on French YouTubers, we consider each comment as a link between a commentator and a video. The main objective of this paper is to understand the determinants of the creation of these links. This is to say, what can explain the choice of an agent to comment a specific video instead of another one, taking into account characteristics of commentators, videos, topics, channels as well as recommendations. This work is different from the classic NLP studies, using text mining techniques to analyze the contents of the comments and the kind of information they diffuse.