Very interesting idea, but not sure Twitter sentiment analysis tells us anything. Most Twitter users don't tweet, and most college-age people are not active Twitter users. Instagram would provide more comprehensive data.
Even then, you have to make a variety of (sometimes shaky) assumptions:
1. The data set is a representative sample
2. Sentiment of social media posts is a good proxy for happiness
3. Machine analysis is sentiment is reliable (i.e. doesn't fail when it encounters sarcasm, which is common on Twitter)
Twitter probably wasn't the best place to start, but it's my first data science project. I need more examples of where students actively talk about their universities, like StudentRoom forums (https://www.thestudentroom.co.uk/) or indeed Instagram.
Gonna be tweaking the approach over time, trying out other models and frameworks.
Wondering if you RateMyProf could be a component of your happiness ranking.
ie. look at the average rate my prof rating per school. There's of course room for bias, but schools with higher professor satisfaction may correlate with overall student happiness.
Thanks, I'll look at this as a data source, cause bias on social is huge, students (and people in general) tend to post on socials when they have something to say, and more often than not it's to rant rather than praise.
One way to improve this is to look at the confession pages and the meme page data of the universities.
Though getting all this data will be cumbersome.
Even then, you have to make a variety of (sometimes shaky) assumptions:
1. The data set is a representative sample
2. Sentiment of social media posts is a good proxy for happiness
3. Machine analysis is sentiment is reliable (i.e. doesn't fail when it encounters sarcasm, which is common on Twitter)