Better youtube recommendations
- More autonomy when choosing what to watch
- Very customizable
- Recommendations for two or more people
- You can install it locally for completely private recommendations
- Sharing and browsing information bubbles
- Less clickbait
You can install it on your computer following the instructions below, or just use it online. You can try it out as the default user, but to have personalized recommendations you will need to follow these steps:
- Export your data from youtube (instructions here)
- Choose your username, in the panel on the left. Note that anyone who knows your username can use your account, so if you don't want that, choose a hard to guess one.
- Upload the zip file with your youtube takeout, with the
Choose Filebutton. - Click refresh button below
- You will be able to use the system the next day.
You can save some cluster of videos for later using controls on the top. Note that on default your clusters will be publicly visible, along with your username. If you want to create a private cluster, start its name with _, for example _music.
You can also browse clusters that the other users saved.
How does it work?
- For every video you have liked on youtube, its recommended videos are collected.
- This way, we create a graph, where two videos are connected if one recomends the other.
- Now we divide this graph into clusters (groups of videos around common theme). For example we can have a
folk rockcluster, or ascience podcastscluster or atravel vlogscluster. - Small clusters are a part of larger clusters. For example
folk rockandboomer rockare inside ofrockcluster, androckis insidemusic. - This forms a tree, with big branches (like
music), splitting into smaller and smaller branches and twigs. - Now, to choose what to watch you can start at the trunk, and "climb" this tree, by choosing which branch to go into.
- Note, that some clusters are too big to be clearly labeled, but by looking at the videos in them, you can usually get a general idea about this cluster's theme.
How are the clusters found?
- When a group of videos is densely connected, it's assumed do be a cluster. When two clusters are well connected, they are joined into a bigger cluster. The exact method we use is here.
Why rely on youtube recommendations instead of providing our own and having more control over them?
- Creating a recommender system from scratch is much harder than you may think at first. In addition to having accurate recommendations, you also have to defend against attacks, like click farms trying to boost some content, or intelligence agencies spreading misinformation. You also have to detect illegal or NSFL stuff, and filter it out. See this to get a sense of how hard this is.
- Another critical problem is the network effect. To build a good recommender system, we need data from a lot of users. To have a lot of users, we need a good recommender system.
- For these reasons, it's better to start with an existing recomender system as a "bottom layer", and then build any new features we want, on top of it.
mkdir -p ~/.yourtube ; curl -s https://raw.githubusercontent.com/filyp/yourtube/master/docker-compose-release.yml > ~/.yourtube/yourtube.yml ; docker-compose -f ~/.yourtube/yourtube.yml run yourtube poetry run yourtube-install- Login to your YouTube account
- Click on your profile picture in the top right corner of the web page
- Make sure your preferred language is English
- Click on "Your data in YouTube" in the displayed drop down
- Click on "More" in the "Your YouTube dashboard" card
- Click on "Download YouTube data"
- Under "Create a New Export", make sure "YouTube and YouTube Music" is selected
- Click "Next step"
- Select your preferred method of delivery (Email, Dropbox, etc.) and click on "Create Export"
- Download the .zip file
- Unzip the file
sudo chown -R $USER:$USER ~/.yourtube
mkdir ~/.yourtube/data/takeouts/default
mv __PATH_TO_YOUR_TAKEOUT__/Takeout .yourtube/data/takeouts/defaultTo add other users, do the same, but replace default with the username you want to use.
Now run:
docker-compose -f ~/.yourtube/yourtube.yml run yourtube poetry run yourtube-scrapeIt will collect recommendations from the videos in your playlists and from your liked videos, which can take up to an hour.
docker-compose -f ~/.yourtube/yourtube.yml down ; docker-compose -f ~/.yourtube/yourtube.yml up -dYourTube shuld be now available at: http://localhost:8866/