Predicting like-ratio on YouTube videos using sentiment analysis on comments

Sammanfattning: Social media is huge today. It allows anyone with an internet connection to voice their opinion all over the world with a single click. Many of the biggest social media platforms such as Facebook and Twitter do not allow users to leave negative feedback on posts. YouTube is different, it allows users to leave negative feedback in the form of a dislike with the click of a button. Each video also has a comment field with comments regarding the video. With the data that YouTube videos provide and sentiment analysis, the research question for this paper is: Can the comments on a YouTube video be used to determine what ratio of the viewers liked or disliked the video using sentiment analysis?. The results from this work showed that there is a weak correlation between the percentage of likes and the percentage of positive comments on a video. Because the fluctuation in the data and results, it is not accurate enough to be applied to any comment field on the internet, but it could be used as an indication. Many areas of the method could be improved for better results.