Computer Science Crowd Education: Turning Stack Overflow into an Educational Tool
Science Without Borders Project
In the field of Computing, online communities of practice such as Stack Overflow have great potential for educational purposes. Michael Staton suggested technology firms now consider Stack Overflow to be “the new Computer Science Department where people go to learn”.
A recent survey conducted among Irish lectures and students revealed how more than 75% of lecturers have already used Stack Overflow, 82% admit to have learned something from it, half of them think SO could be used in teaching Computing, 30% thinks Stack Overflow explains concepts better than a University textbook, 35% of students think that SO always or often explains concepts better than their lecturers.
However, Stack Overflow has not been designed as a learning environment.
The main problems are the lack of structure of the Stack Overflow dataset, the fragmented nature of its content and the lack of guidance for a learner. Moreover, the content is not always intended for explanatory and didactic purposes but rather for professional practitioners, and the content may be incomplete and not sound enough. Stack Overflow has been criticized for favouring quick rather than good answers and encouraging bad learning habits.
The project aims to turn Stack Overflow into an educational resource by addressing its deficiencies, by distilling the best material from its rich repository and by organizing it into a web-based intelligent and dynamic learning environment. The project has a practical social aim. It will be based on open data and therefore open to learners and lecturers all around the world, with the potential of representing the largest educational gym for teaching computing.
The structure of concepts that are supposed to guide the learner has to be mined rather than imposed; it must emerge from the richness of the SO repository.
In order to give a structure to Stack Overflow repository, various techniques could be pursuit by the PhD candidate. Our proposal is to employ state-of-the-art text-mining techniques coupled with social network analysis and computational trust. The Stack Overflow repository will be mined to extract the most interesting questions for learning purposes.
Science Without Borders