DEVELOPMENT OF CROWDSOURCING APPLICATION FOR WRITTEN EXAM GRADING

One method to solve a problem is using crowdsourcing method. Nowadays, there are many problems have been solved by crowdsourcing method and can be applied in various domain. One domain which can be applied by crowdsourcing is education domain. Implementation of crowdsourcing in education domain i...

Full description

Saved in:
Bibliographic Details
Main Author: Irfan Maulana, Muhamad
Format: Final Project
Language:Indonesia
Online Access:https://digilib.itb.ac.id/gdl/view/40113
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Institut Teknologi Bandung
Language: Indonesia
Description
Summary:One method to solve a problem is using crowdsourcing method. Nowadays, there are many problems have been solved by crowdsourcing method and can be applied in various domain. One domain which can be applied by crowdsourcing is education domain. Implementation of crowdsourcing in education domain is that can support teaching and learning process. One of them is in the written exam grading. Grading a written exam can be burdensome if you have a large number of examinees and a small number of examiners. However, crowdsourcing system which has existed for written exam grading still has lack in portability and features. Whereas, the potential to be improved still huge. With this research, a crowdsourcing application will be created that can support better written exam grading tasks. This crowdsourcing application will be developed based on the website. The crowdsourcing application will consider aspects in crowdsourcing such as task decomposition, quality management, task distribution, task integration, and rewarding system. Through this crowdsourcing application, an exam will be decomposed automatically into each exam question so that the grading of the written exam can be done by many people in parallel and the integrity of the grading is maintained. Then in the tests conducted, it was found that the effectiveness of the grading results through crowdsourcing application with the root mean square error metric of 0.889386 based on the question and 0.529188 based on the students when compared with the results of the grading from experts.