Requests are at the core of many social media systems such as question & answer sites and online philanthropy commu- nities. While the success of such requests is critical to the success of the community, the factors that lead community members to satisfy a request are largely unknown. Success of a request depends on factors like who is asking, how they are asking, when are they asking, and most critically what is being requested, ranging from small favors to substantial monetary donations. We present a case study of altruistic re- quests in an online community where all requests ask for the very same contribution and do not offer anything tangible in return, allowing us to disentangle what is requested from tex- tual and social factors. Drawing from social psychology liter- ature, we extract high-level social features from text that op- erationalize social relations between recipient and donor and demonstrate that these extracted relations are predictive of success. More specifically, we find that clearly communicat- ing need through the narrative is essential and that linguistic indications of gratitude, evidentiality, and generalized reci- procity, as well as high status of the asker further increase the likelihood of success. Building on this understanding, we de- velop a model that can predict the success of unseen requests, significantly improving over several baselines. We link these findings to research in psychology on helping behavior, pro- viding a basis for further analysis of success in social media systems.