|
Title:
|
ON THE PREDICTABILITY OF ELECTIONS USING SOCIAL MEDIA DATA |
|
Author(s):
|
Panagiotis T. Metaxas |
|
ISBN:
|
978-989-8533-01-2 |
|
Editors:
|
Bebo White, Pedro Isaías and Flávia Maria Santoro |
|
Year:
|
2011 |
|
Edition:
|
Single |
|
Keywords:
|
Social Network Analysis, Data Mining, Elections, Web 2.0, Social Media, Twitter. |
|
Type:
|
Reflection Paper |
|
First Page:
|
597 |
|
Last Page:
|
600 |
|
Language:
|
English |
|
Cover:
|
|
|
Full Contents:
|
click to dowload 
|
|
Paper Abstract:
|
Predictions using data from social networks and Web searches have attracted a lot of attention lately. By following what people are blogging about or what they are searching about can give us some intuition on the collective psyche and lead us to understand what is currently happening in society before it has actually happened. Sometimes people refer to this phenomenon as the wisdom of the crowd, that is, taking into account the opinions of the society as a whole, instead of the opinions of the expert. One would expect that, following the previous research literature, and given the high utilization that the Web and online social networks have in the US, Twitter volume should have been able to predict consistently the outcomes of the US Congressional elections. But is it so? In this reflection paper we examine the instances and methods that have been used in the past in the claims of electoral results predictions and discuss their predictive power. We then argue that Social Media cannot predict elections and we will give a range of reasons inherent in the use of Social Media that undercut the predictability of elections. |
|
|
|
|
|
|
