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. It’s 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. It’s 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: “What’s 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 people’s 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.
Greg Hand | EurekAlert!
Rapid increase in the volume of video transmissions: Work is in progress on a new intelligent video platform
23.06.2020 | Alpen-Adria-Universität Klagenfurt
More focus and comfort at telephone workstations
20.02.2020 | Fraunhofer-Institut für Digitale Medientechnologie IDMT
New insight into the spin behavior in an exotic state of matter puts us closer to next-generation spintronic devices
Aside from the deep understanding of the natural world that quantum physics theory offers, scientists worldwide are working tirelessly to bring forth a...
Kiel physics team observed extremely fast electronic changes in real time in a special material class
In physics, they are currently the subject of intensive research; in electronics, they could enable completely new functions. So-called topological materials...
Solar cells based on perovskite compounds could soon make electricity generation from sunlight even more efficient and cheaper. The laboratory efficiency of these perovskite solar cells already exceeds that of the well-known silicon solar cells. An international team led by Stefan Weber from the Max Planck Institute for Polymer Research (MPI-P) in Mainz has found microscopic structures in perovskite crystals that can guide the charge transport in the solar cell. Clever alignment of these "electron highways" could make perovskite solar cells even more powerful.
Solar cells convert sunlight into electricity. During this process, the electrons of the material inside the cell absorb the energy of the light....
Empa researchers have succeeded in applying aerogels to microelectronics: Aerogels based on cellulose nanofibers can effectively shield electromagnetic radiation over a wide frequency range – and they are unrivalled in terms of weight.
Electric motors and electronic devices generate electromagnetic fields that sometimes have to be shielded in order not to affect neighboring electronic...
A promising operating mode for the plasma of a future power plant has been developed at the ASDEX Upgrade fusion device at Max Planck Institute for Plasma...
07.07.2020 | Event News
02.07.2020 | Event News
19.05.2020 | Event News
10.07.2020 | Life Sciences
10.07.2020 | Materials Sciences
10.07.2020 | Life Sciences