Twitter Tweets Chart The Social Whirl
Data mining Twitter tweets may produce a gold mine for two University of Cincinnati computer science students.
William Clifton and Alex Padgett have developed a web-based application called The Tweetographer that allows users to learn about events in their cities or neighborhoods. The app works by collecting tweets sent by large numbers of Twitter users and extracting information about events parties, concerts, games, etc. happening nearby. Its like a real-time events guide.
The Tweetographer was the senior project for the pair, who are graduating during the 2011-12 academic year, Padgett in December and Clifton in June.
We wanted to explore data mining, which is an important area of research in Computer Science, in the context of social media, Padgett said. Although the concept will work with many social media platforms, Twitter was the most accessible. Everything is out there in public domain, a giant pool of untapped data, tagged with latitude and longitude. Its very precise and lends itself to so many uses.
That broad utility created some difficulty for the developers as they tried to formulate a focused project.
We realized that we could do all sorts of things with this data. We could add all sorts of functions, but we worked really hard to avoid feature creep and decided to focus on events, Clifton said.
The Tweetographer, in practice, answers a common question for socially active people: Whats happening? Since people who use Twitter often tweet about where they are going or what they want to do, The Tweetographer answers that question by listening in to the chatter. A user can get a sense of not only what is going on, but how popular various events are.
The application is so effective that it was initially overwhelmed the volume of data streaming in through millions of tweets in some large cities.
Eventually we were able to come up with a solution for this with a kind of queuing system that let us handle a stream of that magnitude, Clifton said.
Another obstacle was making sense of all the available data. Although Twitter offers upwards of 140 million tweets a day, they are not posted in a uniform format.
So many people type in their own shorthand, Padgett said.
The solution, according to Clifton, was to create a thesaurus of multiple Twitter synonyms.
Do you know how many ways people type Tuesday? Clifton said.
All of the technical obstacles needed to be overcome on a tight deadline just six months from assignment to presentation.
If we had a couple of years, we could come up with something a lot more sophisticated, Padgett said. Everyone is their own worst critic, and we had very high standards. We wanted to show an elegant, simple solution.
The Tweetographer got an enthusiastic reception at its unveiling.
It blew peoples minds, Clifton said. One skeptic, in particular, wanted to test us. He said, If I tweet right now, it will show up, and we said yes. He tweeted, and it popped up onscreen right away.
The future of The Tweetographer is yet to be written. Padgett and Clifton are making plans beyond graduation, yet still actively working on improving and evolving this project. Clifton thinks the engine developed for The Tweetographer has other useful applications, such as predicting election outcomes, or compiling product reviews.
So much is out there, Clifton said.
Related Stories
Creating community on campus
December 2, 2024
In 2021, the Association for Women of Color in Engineering (AWOCE) was formed at the University of Cincinnati with the mission of providing an inclusive space and voice for women-identifying engineers of color. Since then, the student group has built a strong foundation, and it's membership and impact continue to grow.
Narcan vending machines help communities save fentanyl users'...
December 2, 2024
United Press International, Yahoo News and MSN highlighted research from the University of Cincinnati's Daniel Arendt in a story on the rise of harm reduction vending machines across the country.
Card transaction fees are a growing monthly expense business...
December 2, 2024
Susan Stephan, director of the master of legal studies program at UC Law, spoke with The New York Times for a story about the growing burden of credit and debit card fees for consumers and small businesses.