The idea for the project is to do data-to-text in a particular area of sports: professional cycling.

Raw data and the stats for the race will be extracted from Twitter and Strava. Additionally to get written descriptions of a cycling race, magazines and blogs can be used. However the first part of the race is not televised, team car tweets would be essential to gather that information.

Major Goals -

• Choose a particular race, e.g. the 2015 Tour de France.
• Find tweets from the cycling teams during each stage of the race.
• Find Strava data from the cyclists during each stage of the race.
• Eventually, work on aligning the text and the data.