Suffering from online information overload? Blog-reading computers could one day help you sort out just the information you’re most interested in.
A system called BlogSum, developed by researchers at Concordia University, has successfully analyzed and made sense of large volumes of informally written online content like you find in the typical blog post. Using “discourse relations,” the system has been able to filter out irrelevant information and distill large amounts of online content into readable summaries.
“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,” said Leila Kosseim, one of the lead researchers at Concordia’s Computational Linguistics Laboratory (CLaC lab).
BlogSum promises many potential applications. It could, for example, let a business or organization ask a question and then analyze online blog discussions to see what people are saying. That could enable users to scour the web to determine consumer preferences or voter inclinations.
Such “natural language processing” could bring new levels of artificial intelligence to the field of linguistics.
“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,” Kosseim said.