Outcome Based Predictive Analysis of Automated Question Paper using Data Mining by Simranjeet Kour Bindra
Abstract
In recent years, data mining became very popular in providing useful application in diverse fields. Large amount of data elements are stored in the database. Various data mining algorithms are used to classify the data elements and perform different operations for finding best solution based on relational parameters. This research incorporates architecture for an automated question paper based on Revised Blooms taxonomy. The entire examination process is a vital component for direct assessment of an individual learning. So, preparing a complete test paper and the setting it according to instruction is relatively necessary. Currently, the convention technique of making question paper has been handbook. In current scenario the question paper generation is a manual approach leading to unproductive most of the time owing to bias, repetition and security concerns. The work proposed presents an automatic procedure of question paper generation capable of being modified, streamlined, synchronized and secured. Several tasks done by the proposed system are automatic leading to reduced storing space, bias and security issues. Earlier, the question paper was generated by academic teacher manually and was very time consuming, man power was required and sometimes the question paper lacked accuracy. Outcome Based Education (OBE) predicts the student ability to acquire concepts of a particular course, program and be able to apply the acquired knowledge in future. The information related to student learning was collected for question paper generation and assessment using OBE. This information can be used to predict student’s ability, advancements in education system, betterment in teaching method, future interest of student etc. Various data mining algorithms like oneR, ZeroR, J48, Naive Bayes, IBk are used for prediction of the Course Outcome. The research includes comparative study based on parameters like time, detection accuracy, classification error etc. for assessing the performance of the predictive model generated using classification algorithm.
