Algorithmia was on-hand at the second-annual DubHacks hackathon last month, the largest collegiate hackathon in the Pacific Northwest. Over 600 student developers and designers flocked to the University of Washington in Seattle campus to form teams, build projects, and create solutions to real-world problems.
The winner of the Best Use of the Algorithmia Platform was BSO’Meter, an iOS app by Rosie Zou, Jules Mazur, Daniel Tran, Kim Lister, Shaheen Sharifian that used Algorithmia to analyze statements made by politicians for factual correctness. We spoke with Rosie Zou about how their hack came together, inspiration, and what they’re planning to do next.
What was your team’s goal heading into DubHacks?
“Our main goal was really to just make something cool, learn, and have fun. Winning would be great, but to us it was completely optional. We came up with BSO’Meter because of the elections going on both in the U.S. and in Canada, and wanted to make an app that tells the user how much of a political statement is completely BS.
“At that time, we didn’t really plan out which specific frameworks or APIs we were going to use, but we did a lot of research on the necessary work for both frontend and backend, and we knew that we would, at the very least, require some sort of ‘smart’ text analysis.”
How did you utilize Algorithmia in BSO’Meter?
“Having worked with many APIs and libraries before, our biggest concern for the backend is that the API might be hard to integrate, or that the API and the app would require different versions of a language. These didn’t prove to be a problem at all when we used Algorithmia.
“The Python Client was very easy to install, and it was my first time calling an API using only five lines of code. We also loved how the output file was a Python string instead of the usual JSON files – no parsing, yay! Shoutouts to the simplicity and conciseness of Algorithmia’s APIs!”
What algorithms did your team use?
“We used four algorithms: Extract Text, Summarizer, Sentence Detection, and Sentiment Analysis. We wired our frontend and backend together with a web server. The user inputs a URL, we then use Algorithmia’s APIs on the backend to extract the text from the webpage, summarize the text, break down the summary into sentences, and assign each sentence with a sentiment score of 0 to 4 – 0 being very negative and 4 being very positive.
“We then take the average sentiment score of all sentences and use that value along with a Bayesian classification model that we developed, in order to analyze the text more accurately.
“We built the frontend in Xcode, using Swift 2.0, the backend programming was done in Python, and incorporated Algorithmia’s APIs. Our server was built on Tornado.”
What’s next for BSO’Meter?
“BSO’Meter is still largely a work in progress. We were very excited to have come up with a working demo during the hackathon, and we decided to continue the project afterwards. A lot of the features that we want to add to BSO’Meter would be made much easier by using Algorithmia’s APIs, including OCR, speech-to-text, and improvements on our Bayesian classification model.”
Learn More about BSO’Meter: