Relative difficulty estimation in community answering services

Abstract

Given a question on a crowd sourced Q&A platform, we tried to gauge the difficulty of the question. Earlier, we tried various NLP based techniques for this purpose. Now, we tried various graph models in order to model our intuition of how difficulty is associated with questions, the answerers, the asker and how over time the difficulty of one’s questions change. We used various ranking techniques in order to compute the difficulty values of the questions in our graph model.