Tweets to Treasure Better Trend Analysis

Too bad that rarely happens anymore.

Thanks to social networks like Twitter, a worldwide broadcast of your every move and mood is just 140-characters away. We've come a long way since 2008, when many of today's most tweet-happy users (myself included) complained about their fears of being followed and argued that the minutia of someone else's life isn’t interesting enough to distract their attention.

Nope, we've learned that Twitter really is the gateway to deeper, more meaningful communication — and allows people to more deeply connect, share resources, share online opportunities and collaborate.

And now researchers at the University of Missouri claim they've found a way to make Twitter even more useful for those who believe there's actually a lot of treasure in those tweets.

Context Counts

Every marketer who studies social media wants to understand how to use it to the best advantage. Everyone knows that trending topics on Twitter show the quantity of tweets associated with a specific event. However, University of Missouri (UM) researchers note, trends only show the highest volume keywords and hashtags, and may not give qualitative information about the tweets themselves.

That's why UM researchers have developed and validated a software program that analyzes event-based tweets and measures the context of tweets rather than just the quantity. Using data associated with the Super Bowl and World Series, researchers at UM have developed and validated a software program that analyzes event-based tweets and measures the context of tweets rather than just the quantity.

The study, “Sifting signal from noise: a new perspective on the meaning of tweets about the ‘big game,’" was published in the journal, New Media and Strategy, and was funded by a grant from the National Science Foundation.

Sean Goggins, assistant professor in the School of Information Science and Learning Technologies at UM, and Ian Graves, a doctoral student in the Computer Science and IT Department at the College of Engineering at UM, developed a software program and method that they claim will help Twitter analysts gain better insight into human behavior associated with trends and events.

Goggins said it takes Twitter analysis to the next level. “When analyzing tweets that are connected to an action or event, looking for specific words at the beginning of the tweets gives us a better indication of what is occurring, rather than only looking at hashtags,” he explained.

So What Did They Do?

Graves developed software that analyzes tweets based on the words found within the tweets. As they explained, by programming a “bag of words” or tags they felt would be associated with the Super Bowl and World Series, the software analyzed the words and their placement within the 140 character tweets.

"The software is able to detect more nuanced occurrences within the tweet, like action happening on the baseball field in between batters at the plate or plays in the game," Graves said.

Bottom line: Marketers who just look at the volume of tweets around a topic are not getting the insight they need about what’s truly happening. It's just part of the picture. "By focusing on the words within the tweet, we have the potential to find a truer signal in a very noisy environment," Graves said.