Educational Data Classification Framework for Community Pedagogical Content Management using Data Mining
Journal Title: International Journal of Advanced Computer Science & Applications - Year 2019, Vol 10, Issue 1
Abstract
Recent years witness the significant surge in awareness and exploitation of social media especially community Question and Answer (Q&A) websites by academicians and professionals. These sites are, large repositories of vast data, pawing ways to new avenues for research through applications of data mining and data analysis by investigation of trending topics and the topics of most attention of users. Educational Data Mining (EDM) techniques can be used to unveil potential of Community Q&A websites. Conventional Educational Data Mining approaches are concerned with generation of data through systematic ways and mined it for knowledge discovery to improve educational processes. This paper gives a novel idea to explore already generated data through millions of users having variety of expertise in their particular domains across a common platform like StackOverFlow (SO), a community Q&A website where users post questions and receive answers about particular problems. This study presents an EDM framework to classify community data into Software Engineering subjects. The framework classifies the SO posts according to the academic courses along with their best solutions to accommodate learners. Moreover, it gives teachers, instructors, educators and other EDM stakeholders an insight to pay more attention and focus on commonly occurring subject related problems and to design and manage of their courses delivery and teaching accordingly. The data mining framework performs preprocessing of data using NLP techniques and apply machine learning algorithms to classify data. Amongst all, SVM gives better performs with 72.06% accuracy. Evaluation measures like precision, recall and F-1 score also used to evaluate the best performing classifier.
Authors and Affiliations
Husnain Mushtaq, Imran Siddique, Dr. Babur Hayat Malik, Muhammad Ahmed, Umair Muneer Butt, Rana M. Tahir Ghafoor, Hafiz Zubair, Umer Farooq
Keywords
Related Articles
- EP ID EP448839
- DOI 10.14569/IJACSA.2019.0100144
- Views 94
- Downloads 0
Virtual Identity Approaches Evaluation for Anonymous Communication in Cloud Environments
Since the era’s of Cloud computing beginning, the Identity Management is considered as a permanent challenge especially for the hybrid IT environments that permit for many users’ applications to share the same data cente...
MCMC Particle Filter Using New Data Association Technique with Viterbi Filtered Gate Method for Multi-Target Tracking in Heavy Clutter
Improving data association technique in dense clutter environment for multi-target tracking used in Markov chain Monte Carlo based particle filter (MCMC-PF) are discussed in this paper. A new method named Viterbi f...
Exon_Intron Separation Using Amino Acids Groups Frenquency Repartition as Coding Technique
This paper presents a new coding technique based on amino acids repartition in chromosome. The signal generated with this coding technique constitutes, after treatment, a new way to separate between exons and introns in...
Improvement in Classification Algorithms through Model Stacking with the Consideration of their Correlation
In this research we analyzed the performance of some well-known classification algorithms in terms of their accuracy and proposed a methodology for model stacking on the basis of their correlation which improves the accu...
SYNTHETIC TEMPLATE: EFFECTIVE TOOL FOR TARGET CLASSIFICATION AND MACHINE VISION
A process for replacing a voluminous image dictionary, which characterizes a certain target of interest in a constrained zone of effectiveness representing controlled states including scale and view angle, with a synthet...