A data scientist took a look at YouTube to see whats working and whats not.
“The main goal of the analysis is to find interesting facts and patterns by exploring the data and by using effective visualizations.
Some of the questions the analysis will answer:
- What is the average/minimum/maximum view count for 2019’s trending videos?
- Which videos appeared on the trending list the most (because some videos might appear on the trending list for more than one day)?
- What are the most common words in the titles/descriptions/tags of trending videos?
- What are the title lengths of the trending videos? What is the average/minimum/maximum title length?
- Which channels have more trending videos than others?
- What are the top categories of trending videos? Are “Entertainment” videos more trending than “Gaming” videos?
- How many views/comments/likes trending videos have when first appearing on the trending list?
- How many days are between publishing a video and its first appearance on the trending list?
- How long are the descriptions/tags of trending videos?
- What are the most used colors in the thumbnails of trending videos?
- What are the most common objects in the thumbnails of trending videos? (Running AI object detection algorithm on all thumbnails)
The analysis covers much more topics as you will see soon.”