Analisis Model Penelusuran Backward Chaining dalam Mendeteksi Tingkat Kecanduan Game pada Anak

DOI: https://doi.org/10.14710/jtsiskom.5.4.2017.129-134
Copyright (c) 2017 Jurnal Teknologi dan Sistem Komputer

Article Metrics: (Click on the Metric tab below to see the detail)

Article Info
Submitted: 2017-05-29
Published: 2017-10-13
Section: Articles
Fulltext PDF Tell your colleagues Email the author

Game addiction rate can be detected by applying expert system. This study developed a model of game addiction analysis using backward chaining. This model uses six types of game addiction behavior, among others, salience, euphoria, conflict, tolerance, withdrawal, relapse and reinstatement. Someone is said to be addicted to the game if it meets at least three types of game addiction behavior. Testing the validity of the model is done by testing the closeness of the agreement between the model analysis and expert analysis, resulting in a value of 0.78 which means having a strong agreement.

Tingkat kecanduan game dapat dideteksi dengan mengaplikasikan sistem pakar. Penelitian ini mengembangkan model analisis tingkat kecanduan game menggunakan backward chaining. Model ini menggunakan enam jenis perilaku kecanduan game antara lain, salience, euphoria, conflict, tolerance, withdrawal, relapse dan reinstatement. Seseorang dikatakan kecanduan game jika memenuhi paling sedikit tiga jenis perilaku kecanduan game. Pengujian validitas model dilakukan dengan menguji keeratan kesepakatan antara analisis model dan analisis pakar, menghasilkan nilai 0,78 yang berarti memiliki keeratan kesepakatan kuat.

Keywords

analisa; backward chaining; kecanduan game

References

  1. C. Green, and D. Bavelier, “The cognitive neuroscience of video game. Digital Media: Transformations in Human Communication,” Messaris & Humphreys, Eds, 2004.
  2. A. Latubessy, and M. N. Ahsin, “Hubungan Antara Adiksi Game Terhadap Keaktifan Pembelajaran Anak Usia 9-11 Tahun,” Jurnal Simetris, vol. 7, no. 2, pp. 687-692, 2016.
  3. E. J. Lee, “A case study of internet game addiction,” Journal of Addiction Nursing, vol. 2, no. 2, pp. 208-213, 2011.
  4. Faried, “Perilaku Remaja Pecandu Game Online,” Skripsi, IKIP PGRI, Semarang, 2012.
  5. S. Kusumadewi, “Artificial Intelligence (Teknik dan Aplikasinya),” Graha Ilmu,Yogyakarta, 2003.
  6. I. Akil, “Analisa Efektifitas Metode Forward Chaining Dan Backward Chaining Pada Sistem Pakar,” Jurnal Pilar Nusa Mandiri, vol. 13, no. 1, pp. 35-42, 2017.
  7. E. Sianturi, “Sistem Pakar Diagnosa Gejala Kecanduan Game Online Dengan Menggunakan Metode Certainty Factor,” Jurnal Pelita Informatika Budi Darma, vol. VII, no. 3, 2014.
  8. S. Iriani, “Penerapan Metode Backward Chaining pada Sistem Pakar Diagnosa Penyakit Tulang Manusia,” IJNS – Indonesian Journal on Networking and Security, vol. 4, no. 1, 2015.
  9. G. W. Sasmito, “Sistem Pakar Diagnosis Hama dan Penyakit Tanaman Hortikultura dengan Teknik Inferensi Forward dan Backward Chaining,” Jurnal Teknologi dan Sistem Komputer, vol. 5, no. 2, pp. 69-74, 2017.
  10. A. Latubessy, and E. Wijayanti, “Model Identifikasi Kecanduan Game Menggunakan Backward Chaining,” Jurnal Simetris, vol. 8, no. 1, pp. 9-14, 2017.

  1. Anastasya Latubessy  Orcid Scopus Scholar Sinta
    Program Studi Teknik Informatika, Universitas Muria Kudus, Indonesia
  2. Ahmad Jazuli  Sinta
    Program Studi Teknik Informatika, Universitas Muria Kudus, Indonesia