ANALISIS DATA PENDIDIKAN TINGGI MENGGUNAKAN PENDEKATAN DATA MINING

Gita Indah Marthasari

Abstract


ABSTRAK

Data mining untuk pendidikan menekankan pada pemanfaatan metode untuk menemukan pengetahuan dari data di lingkungan pendidikan. Bidang ini menggunakan mekanisme transformasi atau inovasi dari pendekatan yang diturunkan dari ilmu statistik, pembelajaran mesin, psikometrik, dan komputasi ilmiah. Penelitian ini mengusulkan sebuah analisis terhadap status keaktifan siswa menggunakan salah satu teknik data mining yaitu association rule mining (ARM). Teknik ARM bertujuan menemukan pola-pola yang merepresentasikan informasi bernilai tinggi bagi para pengambil keputusan di perguruan tinggi. Salah satu algoritma yang umum digunakan dalam ARM adalah Apriori. Algoritma Apriori digunakan untuk mencari aturan-aturan asosiasi yang menarik dari basis data dalam rangka mengekstraksi pengetahuan dari data profil dan data akademik siswa. Aturan-aturan yang ditemukan selanjutnya dianalisis sebagai bahan rekomendasi bagi para pengelola akademik untuk meningkatkan kualitas proses pengambilan keputusan. Selain itu, hasil analisis dapat menjadi acuan bagi arah kurikulum yang mampu memperbaiki kualitas pembelajaran siswa. Uji coba dilakukan dengan melakukan pengaturan terhadap parameter nilai minimal support dan minimal confidence. Berdasarkan hasil analisis diperoleh pengetahuan antara lain adanya hubungan kuat antara asal sekolah mahasiswa dan pekerjaan orang tua terhadap tingkat keaktifan. Selain itu, juga diperoleh pengetahuan tentang nilai minimal mahasiswa tiap semesternya untuk tetap aktif di semester selanjutnya.

Kata kunci : Data mining untuk pendidikan, Association Rule Mining, Algoritma apriori, Status keaktifan siswa.

 

ABSTRACT 

Educational data mining (EDM) concerns with developing methods for discovering knowledge from data that come from educational environments. EDM requires a transformation of existing or innovation of new approaches derived from statistics, machine learning, psychometrics, and scientific computing. In this paper, we propose an analysis of student activity status using one of data mining techniques that are association rule mining (ARM).ARM technique aims at discovering patterns that can provide valuable information for the decision maker in higher education.Apriori algorithm is one of many methods in ARM.We have used Apriori algorithm for finding interesting association rules from the transformed database which can be useful to extract knowledge of students’ profile and academic evaluation. The identified rules are analyzed to offer a helpful and constructive recommendation to the academic planners in higher institutions to enhance their decision-making process.We analyze the data by setting minimal support and minimal confidence value. Based on the experiment, we conclude that the student high school location and parent’s job have a strong correlation with student activity.Moreover, we also acquired a knowledge about student minimal grade point average in a semester to remain active in the next semester.

Keywords: Educational data mining, Association rule mining, Apriori algorithm, Students activity status

 


References


P. Baepler and C. J. Murdoch, “Academic Analytics and Data Mining in Higher Education,” Int. J. Scholarsh. Teach. Learn., vol. 4, no. 2, pp. 1–9, 2010.

G. Elakia, N. J. Aarthi, Elakia, Gayathri, Aarthi, and Naren J, “Application of Data Mining in Educational Database for Predicting Behavioural Patterns of the Students,” Elakia al,/(IJCSIT) Int. J. Comput. Sci. Inf. Technol., vol. 5, no. 3, pp. 4649–4652, 2014.

D. A. Alhammadi and M. S. Aksoy, “Data Mining in Education- An Experimental Study,” Int. J. Comput. Appl., vol. 62, no. 15, pp. 31–34, 2013.

K. Chandra, E., Nandhini and E. Chandra, “Knowledge mining from student data,” Eur. J. Sci. Res., vol. 47, no. 1, pp. 156–163, 2010.

E. J. M. Lauría, J. D. Baron, M. Devireddy, V. Sundararaju, and S. M. Jayaprakash, “Mining academic data to improve college student retention : An open source perspective,” Proc. 2nd Int. Conf. Learn. Anal. Knowl. - LAK ’12, no. May, pp. 139–142, 2012.

V. Kumar and A. Chadha, “Mining association rules in student’s assessment data,” Int. J. Comput. Sci. Issues, vol. 9, no. 5, pp. 211–216, 2012.

S. S. Aksenova, “Machine Learning with WEKA,” pp. 2–4, 2004.

S. Ahmed, R. Paul, A. Sayed, and L. Hoque, “Knowledge Discovery from Academic Data using Association Rule Mining,” no. December, pp. 22–23, 2014.

A. El-Halees, “Mining Students Data To Analyze Learning Behavior : a Case Study Educational Systems,” Work, no. February, 2008.

M. Manvar and M. Rao, “Predicting students performance in higher education: A Data Mining Approach,” Ijser.Org, vol. 5, no. 2, pp. 1024–1027, 2014.

S. Acharya and N. Madhu, “Discovery of students ’ academic patterns using data mining techniques,” Int. J. Comput. Sci. Eng., vol. 4, no. 6, pp. 1054–1062, 2012.

S. Kotsiantis and D. Kanellopoulos, “Association Rules Mining: A Recent Overview,” GESTS Int. Trans. Comput. Sci. Eng., vol. 32, no. 1, pp. 71–82, 2006.




DOI: https://doi.org/10.21107/simantec.v5i3.2386

Refbacks

  • There are currently no refbacks.


Copyright (c) 2016 Jurnal Simantec



Indexed By