Finding Prerequisite Relations using the Wikipedia Clickstream

Mohsen Sayyadiharikandeh, Jonathan Gordon, José Luis Ambite, Kristina Lerman

Abstract: The increased availability of online learning resources in the form of courses, videos, and tutorials has created new opportunities for independent learners, but it has also increased the difficulty of planning a course of study. Where should the learner start? What should the learner know before tackling a new course? Manually identifying these prerequisite relations between learning resources or concepts is expensive in terms of time and expertise, and it is particularly difficult to do so for new or rapidly changing areas of knowledge. To address this challenge, we present a new method for identifying prerequisite relations based on naturally occurring data, namely the navigation patterns of users on the Wikipedia online encyclopedia. Our supervised learning approach shows that the navigation network structure can be used to identify dependencies among concepts in several domains.