Web-based question-answering system for educational purpose

• Main Author: Chua, Xin Yi.
• Other Authors: Hui Siu Cheung
• Format: Final Year Project
• Language: English
• Published: 2012
• Subjects: DRNTU::Engineering::Computer science and engineering::Information systems::Information interfaces and presentation; DRNTU::Engineering::Computer science and engineering::Information systems::Information systems applications
• Online Access: http://hdl.handle.net/10356/50815
• Institution: Nanyang Technological University

There are many Questions-Answering (QA) systems readily available such as Yahoo! Answers and Answers that support a wide selection of categories including educational subjects. Such QA systems are not education-centered; they were found to not provide much support in the way users ask questions and also who their target audience is for the question. Educational QA sites such as Math Stack Exchange (MSE), Chegg Homework Help (Chegg), and Stackoverflow, allow users to ask and answer questions that are subject-centered, based on the editor tools available. However the editor tools available for posting contents are not enough to support user’s content postings. In addition, even though questions asked in such educational QA communities have a greater chance of having their target audience to answer, the support for asking questions can still be further improved by having an expert and tutoring community. In this study, the proposed QA system was implemented to support Math, Programming, and Science contents, with a main subject focus on Math. The QA systems: Yahoo! Answers, Chegg, Stackoverflow, MSE, and Askbot were reviewed and discussed based on their existing functionalities on the features that can be supported in the proposed system, Bingo. Techniques and editor tools were proposed to enhance feature support for educational subjects. An expert community was proposed to find a list of experts who posted questions according to their expertise in Subject(s) or Topic(s). The expert listing can allow users to gain credibility in the answers that the identified experts have posted. In addition, users can also sign up to be tutors, and allow other users to search for tutors, and directly ask appropriate tutors questions based on their expertise. In this way, the target audience for question answering can be the most credible. The performance of the Subject Expert Search, Topic Expert Search, and Question Tutor Search was evaluated, and a system evaluation was conducted based on the difficulty and usefulness of the features in Bingo. Finally, conclusions and recommendations for future work were discussed.