Paper by Benjamin Timmermans et al: “There are many issues in the world that people do not agree on, such as Global Warming [Cook et al. 2013], Anti-Vaccination [Kata 2010] and Gun Control [Spitzer 2015]. Having opposing opinions on such topics can lead to heated discussions, making them appear controversial. Such opinions are often expressed through news articles and social media. There are increasing calls for methods to detect and monitor these online discussions on different topics. Existing methods focus on using sentiment analysis and Wikipedia for identifying controversy [Dori-Hacohen and Allan 2015]. The problem with this is that it relies on a well structured and existing debate, which may not always be the case. Take for instance news reporting during large disasters, in which case the structure of a discussion is not yet clear and may change rapidly. Adding to this is that there is currently no agreed upon definition as to what exactly defines controversy. It is only agreed that controversy arises when there is a large debate by people with opposing viewpoints, but we do not yet understand which are the characteristic aspects and how they can be measured. In this paper we use the collective intelligence of the crowd in order to gain a better understanding of controversy by evaluating the aspects that have impact on it….(More)”
See also http://crowdtruth.org/
