Time: 15:16 (Greece)
As a continuation of our previous work on prediction election (cf. Deliverable 2.3), our collaborator Adam Tsakalidis (now PhD candidate with the University of Warwick) has applied the SocialSensor election result prediction approach to make a forecast on the result of the Greek Elections 2015 (Jan 25). In our previous effort (with Euro-elections), our forecasts were impressively close to the actual results, hence we were interested in finding out whether such accurate predictions could be repeated.
Obviously, once again, such results should be read with great caution as they stem from a highly experimental setting (even if it was already tested once) and are only the beginning of some very interesting research that will continue.
Here are the results (given the existing situation and last polls, these seem quite unlikely)....
More details are available on Adam's blog post.
Disclaimer: In case it was not clear from the above, those results were produced by means of automatic data analysis methods and they do not reflect any political bias of the researchers. In addition, they should not be considered as reliable vote estimates but rather a research experiment.