TweetSafe is a task that is encaptured in SafeYou+ project, which is an extension of the existing SafeYou project. SafeYou+ aims to address the identified needs among EU institutions, education providers, national anti-doping organizations, sports authorities etc, in order to promote all healthy aspects of sports and exercise. The project’s goal is to identify, collect, analyze and extract useful information and features about doping cases, prohibited substances for athletes of various sports and events. Our team's (Informatics Department, Aristotle University of Thessaloniki, Greece) contribution to the project (WP4, A23-A24) can be summarized as follows: We support data collection & integration, design and implementation of data collection processes from external sources, with an emphasis on social networks. We also provide analysis of technical specifications and methods of classifying them, in order to facilitate their efficient modeling. We develop pre-processing & data modeling tools, design techniques for removing noise from data (data cleansing) and use of suitable models of representation of information sources (endogenous, internal and external).
214K
214.498 distinct tweets
3841
3841 distinct Youtube comments
79K
78636 distinct users
142K
141.879 distinct words