An assumption commonly unchallenged in Social Media is that its open nature leads to a representative view of the world. There are (at least) two issues with this assumption. The rst issue is that such representativeness may be harmful and may contradict social principles, e.g. non-discrimination against women or minorities. The second issue is that algorithms that work on such representation may be harmful and may introduce bias misrepresenting people or peoples preferences. In this talk we want to overview the issue of bias occurring in the Social Web. We will consider a case study of liquid feedback, a direct democracy platform of the German pirate party as well as models of (non)discriminating systems. As a conclusion of this talk we stipulate the need of Social Media systems to bias their working according to social norms and to publish the bias they introduce.