Inspiration
We were inspired by both dating websites and LinkedIn. It's good to know the history of prospective partners; and in the same lens it's best for employers to know who they're trusting with company resources.
What it does
This Twitter Sentiment Analyzer makes use of the tweet history of data samples to determine what sentiments are generally expressed on that social media platform.
How we built it
We identified potential job candidates with Twitter handles using an API from PDL, used an open source Twitter scraper and then used Python NLTK to rate the positivity and negativity of each handle's tweets.
Challenges we ran into
We ran into some data limitation. Not all Twitter handles were up-to-date, which caused issues for our data compiler. Even the Twitter API was hard to access; we had to find a backdoor API to actually retrieve the information we wanted from the website.
Accomplishments that we're proud of
We're proud of the simplicity of our script. 32 lines gives us a fleshed-out output file that gives us all the information we would need to make conclusions about the social media presence of our candidates.
What we learned
We learned that a lot of the information we give to the internet can be easily traced back to us. We should be careful of what we post when our names are often associated with what we're saying!
What's next for Twitter sentiment analyzer
This project could be expounded on in a number of directions. More variables could be added to our analysis, which could help both employers and employees find better matches, which ideally contributes to a happier, healthier, and more productive work environment and culture.
Log in or sign up for Devpost to join the conversation.