With hundreds of articles published every day, it is hard to keep track of the main issues in the media. However, the unsupervised learning may help to identify the most relevant information.
Why should we read news sites if we can automatically extract the most important information?
During the talk, I will present how to identify and summarise the most important topics appearing on news sites. I will cover theoretical and practical aspects of LexRank and other unsupervised methods that may be used to identify key topics in media on a particular day.