Crowdsourced Learning

The conventional education ecosystem in developing regions is plagued by the lack of good quality textbooks and educational resources, lack of skilled teachers and high variability across student skill and motivational levels [Crossley and Murby 1994; Glewwe et al. 2007]. This paper makes the case for establishing a crowdsourced learning ecosystem that leverages the collective intelligence of educators around the world to design a collaborative platform [Arias et al. 2000] to easily share, search, organize, rate and present educational materials for teachers and students around the world. The recent popularity of online learning platforms and Massive Open Online Courses (MOOCs) has made it possible for students to access high quality educational content from the comfort of their homes and enabled new forms of learning that were not possible before. Given the wealth of educational resources on the Web, this paper describes the vision of a crowdsourced learning platform that aims to integrate rich educational web content into an inquiry based framework using the 5E learning model [Bybee et al. 2006] for generating, sharing and rating web annotated lesson plans for school teachers and students. By sharing educational content across teachers, the crowdsourced learning platform should allow teachers to leverage content authored by other (potentially higher quality) teachers, rate the appropriateness of content and also provide feedback (in the form of votes/ratings) to promote high quality and relevant content as a function of student skill levels. Similarly, the platform should enable students to interact with their peers and the teachers to engage in discussions related to the course material (similar to existing forums in MOOCs [Mak et al. 2010]) and promote both a certain degree of peer learning as well as skill-based personalization. In essence, the goal of crowdsourced learning is to create an ecosystem that enables the collaboration amongst teachers and students of diverse backgrounds to improve the overall educational experience and lead to better learning outcomes for students. This paper specifically makes two important contributions: (a) Modeling learning outcomes in crowdsourced learning: We propose a mathematical framework that enables systematic modeling and comparison amongst different education paradigms. Our framework provides a means to quantify student learning under a given paradigm based on critical factors such as the student skill (or ability), quality of the reading material (or the teacher), etc. (b) Crowdsourced Learning Platform: We describe the design of YeSua, an initial prototype of our crowdsourced learning platform that uses an inquiry-based framework for generating annotated lesson plans for different subjects.