Crowd characterization for crowd management using social media data in city events

•Identify a set of factors that are relevant for pedestrian behavior analysis.•Derive information about these factors from social media data.•Explore methods for extracting information about these factors from social media data.•Perform 2 case-studies (i.e. Sail event 2015 and King’s Day event 2016 in Amsterdam) for analysing several properties of attendees, including demographics, city-role, crowd temporal distribution, social media post locations, Point of Interest (PoI.) preferences, and word use.•Perform an exploratory analysis in each case about these factors and correlate them with the corresponding event to check their accuracy and reliability.