Text Mining Makes Sense of Social Media
September 21, 2012
Text mining is taking a curious turn toward social media, according to “Mining the Blogosphere: Researchers Develop Tools That Make Sense of Social Media” on Science Daily. We learn in the article that several Concordia computer scientists are helping computers get closer to “reading” an online blog and understanding it. The system they created, called BlogSum, allows organizations to pose questions and then find out how a large number of people online would respond by examining real-life self-expression.
Leila Kosseim, associate professor in Concordia’s Faculty of Engineering and Computer Science and one of the lead researchers on the project, explains:
“Huge quantities of electronic texts have become easily available on the Internet, but people can be overwhelmed, and they need help to find the real content hiding in the mass of information.”
Kosseim also comments:
“The field of natural language processing is starting to become fundamental to computer science, with many everyday applications — making search engines find more relevant documents or making smart phones even smarter.”
When tested against similar technology or even human subjects, BlogSum was ranked superior. The vast number of possibilities available with this technology are overwhelming, from marketing research on consumer preferences to voter intentions in upcoming elections. We look forward to seeing it advance the world of search.
Andrea Hayden, September 21, 2012