The aim of this project is to compare and contrast speeches and statements at the official level of the two governments on the island.
This can be easily visualized through a word-cloud where the size of each word relates to how commonly it is used.
We managed to download statements and speeches from both sides, through the official PIO websites (follow the links for Gc and Tc).
To do this we go through a ton of text files containing statements since 2003 for Gc ones and 2008 for Tc ones. This is carried out semi-automatically through Processing and some manual control. We also apply filters so that words such as ‘say’ and ‘said’ are counted as the same word. Bellow you can see a first draft after processing some of the statements in Greek.
We got the technical part down, but there’s still quite a bit of work to do to get it being informative. If you want to help us make sense of all this data, we’d love your input.