This paper by Daniel Gayo-Avello
looked at election predictions using twitter and found that predictive power of Twitter regarding elections has been greatly exaggerated.
There are many flaws, including assumptions that all tweets are trustworthy, while political statements are full of propaganda and humour.
The previous work does not account for demographics. Tweeters are overwhelmingly younger and this will bias any results. The biggest problem is the lack of a single actual election prediction -
all analysis on elections so far has been done after the fact.
"I have not found a single paper predicting a future result," says Gayo-Avello.
Predicting X from Twitter is a popular fad within the Twitter research subculture. It seems both appealing and relatively easy. Among such kind of studies, electoral prediction is maybe the most attractive, and at this moment there is a growing body of literature on such a topic.
This is not only an interesting research problem but, above all, it is extremely difficult. However, most of the authors seem to be more interested in claiming positive results than in providing sound and reproducible methods.
It is also especially worrisome that many recent papers seem to only acknowledge those studies supporting the idea of Twitter predicting elections, instead of conducting a balanced literature review showing both sides of the matter.
After reading many of such papers I have decided to write such a survey myself. Hence, in this paper, every study relevant to the matter of electoral prediction using social media is commented.
From this review it can be concluded that the predictive power of Twitter regarding elections has been greatly exaggerated, and that hard research problems still lie ahead.