文章基本信息

标题：Educational Data Classification Framework for Community Pedagogical Content Management using Data Mining
本地全文：下载
作者：Husnain Mushtaq ; Imran Siddique ; Dr. Babur Hayat Malik 等
期刊名称：International Journal of Advanced Computer Science and Applications(IJACSA)
印刷版ISSN：2158-107X
电子版ISSN：2156-5570
出版年度：2019
卷号：10
期号：1
页码：329-338
DOI：10.14569/IJACSA.2019.0100144
出版社：Science and Information Society (SAI)
摘要：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.
关键词：Text mining; educational data mining; social learning; course design and delivery; technology supported learning; crowdsourced educational data mining