Flood observations classification using the ‘Relevancer’

How do you know which text messages are relevant and which are not? The Centre of Language Studies of Radboud University and FloodTags developed a tool that classifies text messages using a K-means algorithm. The tool is named "Relevancer". On the basis of initial user input (annotating clusters of content in several rounds of user input), Relevancer estimates the relevance of the text messages and classifies the observations on the basis of the words and language that is used.