Prediction Popularity of Movies in Indonesia UsingData Mining Algorithm Classification

Prediction Popularity of Movies in Indonesia UsingData Mining Algorithm Classification

• By Sulistyowati, Daning Nur; Gata, Windu; Amsury, Fachri; Yunita,Norma; Junaidi, Agus; Setiadi, Ahmad;
• Seminar Internasional
• 131
• 19-32

The development of the movie business a rapid progress had an impact tothe audience a movie that need movie with the quality of the image, sound, story lineand positive value contained therein sothat the audiens of the movie are stillenthusiastic in following the latest movie. An assessment is needed so that the filmindustry is still growing continuously. Assessment from the public and especially theaudience of the movie itself is used to determine the most desirable type of movie.This study aims to predict the level of popularity of the movie in Indonesia byanalyzing the rating of a film. The result of research by the ROC curve showed AUCvalues using Naive Bayes models amounted to 0,836 K-Nearest Neighbors modelsamounted to 0.818 and 0.767 for decision tree models. Of the three models two ofwhich belong to the classification of Good classification is naive Bayes algorithmand k-nearest neighbors with AUC values between 0,80 to 0,90. The model ofdecision tree algorithm included in Fair classification classification, had AUC valuesbetween 0,70 to 0,80.

• Katakunci Classification, Prediction, Movie Popularity, Naïve bayes, Data Mining
• URL http://
• Penerbit ,

REFERENSI

Ahmed, M., Jahangir, M., Afzal, H., Majeed, A., & Siddiqi, I. (2015). Using crowd-source based features from social media and conventional features to predict themovies popularity. Proceedings-2015 IEEE International Conference on SmartCity, SmartCity 2015,Stainable Computing and Communic, (March 2016), 273–278. https://doi.org/10.1109/SmartCity.2015.83

Alfisahrin, S. N. (2014). Komparasi Algoritma C4.5, Naive Bayes dan NeuralNetwork UntukMemprediksi Penyakit Jantung. Jakarta : Pascasarjana MagisterIlmu Komputer STMIK Nusa Mandiri.

Apala, K. R., Jose, M., Motnam, S., Chan, C., Liszka, K. J., & Gregorio, F. De.(2013). Prediction of Movies Box Office Performance Using Social Media.IEEE/ACM International Conference on Advances in Social Networks Analysisand Mining, (July), 1209–1214. https://doi.org/10.1145/2492517.2500232

Bellazzi, R., & Zupanb, B. (2008). Predictive Data Mining In Clinical Medicine:Current Issue And Guidelines. International Journal Of Medical Informatics, 81–97.

Bhave, A., Kulkarni, H., Biramane, V., & Kosamkar, P. (2015). Role of differentfactors in predicting movie success. 2015 International Conference on PervasiveComputing (ICPC), 00(c), 1–4.https://doi.org/10.1109/PERVASIVE.2015.7087152

Budi, S. (2017). Text Mining Untuk Analisis Sentimen Review Film MenggunakanAlgoritma K-Means. Techno.COM, 16(1), 1–8.

Chandani, V., Wahono, R. S., & Purwanto, . (2015). Komparasi AlgoritmaKlasifikasi Machine Learning Dan Feature Selection pada Analisis SentimenReview Film. Journal of Intelligent Systems, 1(1), 55–59.

Gumilar, D., Pudjiantoro, T. H., & Yuniarti, R. (2017). Prediksi Kepopuleran LaguBerdasarkan Tangga Lagu Billboard Menggunakan Decision Tree Dan K-Means.Prosiding SNATIF Ke-4 Tahun 2017, 187–192. https://doi.org/10.1007/s12664-012-0191-3

Iskandar, D., & Suprapto, Y. . (2015). Perbandingan Akurasi Klasifikasi TingkatKemiskinan Antara Algoritma C45 dan Naive Bayes. Ilmiah NERO, 2(1), 37–43.

Jangid, B. M.,Jadhav, C. K., Dhokate, S. M., Jadhav, G. M., & Bhandari, G. M.(2017). Movies Popularity Prediction Using Social Media and ConventionalFeatures, (i), 5794–5798. https://doi.org/10.15680/IJIRSET.2017.0604192

Latif, M. H., & Afzal, H. (2016). Prediction ofMovies popularity Using MachineLearning Techniques. IJCSNS International Journal of Computer Science andNetwork Security, 16(8), 127–131.

McLeon, R. G. P. S. (2008). Sistem Informasi Manajemen. Salemba Empat.

Murnawan, & Sinaga, A. (2017). ImplementasiSentiment Analysis untukMenentukan Tingkat Popularitas Tujuan Wisata. Prosiding Seminar NasionalTeknologi Dan Rekayasa Informasi Tahun 2017, (November), 12–18.

Nugroho, Y. S., & Pratiwi, R. W. (2016). Prediksi Rating Film Menggunakan MetodeNaïve Bayes.Jurnal Teknik Elektro (ISSN 1411-0059), 8(2), 60–63.

Nuraeni, N. (2017). Penentuan Calon Pegawai di PTPN 12 Kota Blater TempurejoJember dengan Metode Naive Bayes. Seminar Nasional Teknologi Informasi DanMultimetida, 61–66.

Nuraeni, N. (2017). Penentuan Kelayakan Kredit Dengan Algoritma Naïve BayesClassifier : Studi Kasus Bank Mayapada Mitra Usaha Cabang PGC. Jurnal TeknikKomputer AMIK BSI, III(1), 9–15. https://doi.org/ISSN. 2442-2436

Pristiyanti, R. I., Fauzi, M. A., & Muflikhah, L. (2017). SentimentAnalysisPeringkasan Review Film Menggunakan Metode Information Gain dan K-NearestNeighbor, 2(3), 1179–1186.

Utami, L. A. (2017). Melalui Komparasi Algoritma Support Vector Machine Dan K-Nearest Neighbor Berbasis Paerticle Swarm Optimization, 13((1)), 103–112.

Vercillis, C. (2009). Business Intelligence: Data Mining and Optimization forDecision Making.

Wisudawati, J., Adiwijaya, & Faraby, S. Al. (2017). Klasifikasi Sentimen padaMovie Review dengan Metode Multinomial Naïve Bayes. E-Proceeding ofEngineering, 4(2), 2978–2988.

Witten, I. H., Frank, E., & Hall, M. A. (2011). Data Mining Practical MachineLearning Tools And Techniques. Burlington, Usa: Morgan Kaufmann Publishes.

Yulietha, I. M., Faraby, S. Al, & Adiwijaya. (2017). Klasifikasi Sentimen ReviewFilm Menggunakan Algoritma Support Vector Machine. E-Proceeding ofEngineering, 4(3), 4740–4750.