Towards an Online Emotional Support Agent: Identifying Emotional Support Strategies via Crowdsourcing

In this paper, an empirical study conducted with Amazon Mechanical Turk workers is presented that aims to make a correspondence between messages about stressful situations, which were shared via Twitter, and 5 different types of supportive replies to them. Around 10.00 tweets were collected and analyzed in the terms previously described. We performed statistical tests to determine possible correlations between causes of stress and supportive response strategies. We are about to use these findings to improve a previously implemented algorithm that automatically generates supportive messages to stressed users. This algorithm is the core of an agent, in the form of a chatbot, that would be able to interact with such stressed users as if it would belong to their social networks.