The development of science and technology is very rapidly, resulting in employees having to change their working systems in based on demand that exist today. In an increasingly complex modern life, humans will tend to experience emotion when humans are less able to adapt their desires to the reality, both the reality inside and outside themselves. All kinds of emotional
forms are basically caused by a lack of understanding of human beings on their own limitations. Emotional behavior of employees occur at PO Pambudi Jaya is mainly part of Programmer staff. Programmers alwayswork with high pressure and tight schedules. Programmers always had been relationship with other employees and where is often misunderstandings from it. Whereas a programmer always have problem with their emotional, especially if the Programmer is under high pressure and other employees are trying to ask about the problem. In this study the application of data mining using the decision tree method and J48 algorithm to determine the emotional behavior of the programmer in response to problems. The data mining analysis process in this study uses WEKA 3.9.3 data mining application software. The J48 algorithm classification results in classifying data achieve accuracy above 80% with educational attributes are attributes that have the highest Gain value.
Emotional Programmer's Behavior to Respond Problems by Using a Decision Tree
[1] Zohar, D., & I. Marshall. (2000). Spiritual Intelligence the Ultimate
Intelligence. Great Britain: Bloomsbury Publishing.
[2] Wright, T. A. (2004). The Role of “Happiness” in Organizational
Research: Past, Present and Future Directions. Research in
Occupational Stress and Well Being, 221-264.
[3] Zapf, D. (2002). Emotion Work and Psychological Well-being
Review of the Literature and Some Conceptual Considerations.
Human Resource Management Review, 12, 237-268.
[4] Fineman, S. (2003). Understanding Emotion at Work. London: Sage
Publication.
[5] Lee, S., Hooshyar, D., Ji, H., Nam, K., & Lim, H. (2017). Mining
biometric data to predict programmer expertise and task difficulty.
Cluster Computing, 1-11.
[6] Utama,T.D., Sihwi, S.W., & Doewes, A. (2014). Implementasi
Algoritma Iterative Dichotomiser 3 pada Penyeleksian Program
Mahasiswa Wirausaha UNS. Jurnal Itsmart, 74-82.
[7] Andri, Kunang, Y.N., & Murniati, S. (2013), Implementasi Teknik
Data Mining untuk Memprediksi Tingkat Kelulusan Mahasiswa pada
Universitas Bina Darma Palembang. Seminar Nasional Informatika,
A56-A63.
[8] Ningrat, R.W. & Santoso, B. (2012). Pemilihan Diet Nutrien bagi
Penderita Hipertensi Menggunakan Metode Klasifikasi Decision Tree
(Studi Kasus: RSUD Syarifah Ambami Rato Ebu Bangkalan). Jurnal
Teknik ITS, A536-A539.
[9] Andriani, A. (2013). Sistem Pendukung Keputusan Berbasis Decision
Tree dalam Pemberian Beasiswa Studi Kasus : AMIK “BSI
Yogyakarta”. Seminar Nasional Teknologi Informasi dan
Komunikasi, 163-168.
[10] Gorunescu, F. (2011). Data Mining Concept Model and Techniques.
Berlin: Springer. ISBN 978-3-642-19720-8
[11] Dua, S. & Xian Du. (2011). Data Mining and Machine Learning in
Cybersecurity. USA:Taylor & Francis Group. ISBN-13: 978-1-4398-
3943-0
[12] Diwandari, S., Setiawan, N.A. (2015). Perbandingan Algoritme J48
dan NBTree untuk Klasifikasi Diagnosa Penyakit pada Soybean.
Seminar Nasional Teknologi Informasi dan Komunikasi, 205-212.