Klasifikasi Emosi pada Komentar YouTube menggunakan Algoritme Support Vector Machine
Kata Kunci:
klasifikasi emosi, information gain, TF-IDF, SVMAbstrak
Content creator telah menjadi profesi baru yang menjanjikan semenjak pesatnya perkembangan sosial media. Untuk menghasilkan sebuah konten yang dapat dinikmati penonton seorang content creator harus bisa memahami penontonnya. Salah satu cara yang dapat dilakukan adalah dengan mengetahui emosi penonton melalui komentar atau dalam machine learning dikenal juga dengan istilah klasifikasi emosi. Support Vector Machine merupakan algoritme supervised learning yang memiliki keunggulan dalam menggeneralisasi model secara baik dengan memanfaatkan ruang fitur berdimensi tinggi. Penelitian ini menggunakan algoritme Support Vector Machine dan Information Gain sebagai metode seleksi fitur. Dataset yang digunakan adalah komentar YouTube yang telah dilabeli dengan kelas senang, sedih dan marah. Proses klasifikasi emosi ini terdiri dari text preprocessing, seleksi fitur dengan Information Gain, ekstraksi fitur dengan TF-IDF (Term Frequency - Inverse Document Frequency) dan proses klasifikasi menggunakan algoritme Support Vector Machine. Proses pengujian menggunakan metode Stratified K-Fold dengan nilai k = 5. Hasil dari pengujian yang diperoleh adalah sebuah model Support Vector Machine dengan nilai akurasi 88,07% dan f1-measure 88,06%. Pada penelitian ditemukan bahwa penggunaan fitur seleksi Information Gain tidak meningkatkan performa dari model.
Referensi
Alhujaili, R. F., & Yafooz, W. M. S. (2021). Sentiment Analysis for Youtube Videos with User Comments: Review. Proceedings - International Conference on Artificial Intelligence and Smart Systems, ICAIS 2021, 814–820. https://doi.org/10.1109/ICAIS50930.2021.9396049
Allouch, M., Azaria, A., Azoulay, R., Ben-Izchak, E., Zwilling, M., & Zachor, D. A. (2019). Automatic Detection of Insulting Sentences in Conversation. 2018 IEEE International Conference on the Science of Electrical Engineering in Israel, ICSEE 2018, 1–5. https://doi.org/10.1109/ICSEE.2018.8646165
Azizah, E. N., & Rainarli, E. (2019). Support Vector Machine and Information Gain for Emotion Classification in Song Lyric. Elibrary.Unikom.Ac.Id, 112. https://elibrary.unikom.ac.id/998/14/UNIKOM_EVA NUR AZIZAH_JURNAL DALAM BAHASA INGGRIS.pdf
Candra Ardiansyah, Indriati, M. (2020). Klasifikasi Emosi pada Komentar Youtube Menggunakan Metode Modified K-Nearest Neighbor dengan BM25 dan Seleksi Fitur Chi-Square. Jurnal Pengembangan Teknologi Informasi Dan Ilmu Komputer, 4(4), 1027–1032. http://j-ptiik.ub.ac.id
Feldman, Ronen; Sanger, J. (2006). The Text Mining Handbook : Advanced Approaches in Analyzing Unstructured Data. Cambridge University Press.
Guo, J. (2022). Deep learning approach to text analysis for human emotion detection from big data. Journal of Intelligent Systems, 31(1), 113–126. https://doi.org/10.1515/jisys-2022-0001
Halim, E., Anindya, R., & Hebrard, M. (2020). The impact of motivation to watch youtube, subjective norms, behavior control, information success model to watching youtube engagement. Proceedings of 2020 International Conference on Information Management and Technology, ICIMTech 2020, August, 800–805. https://doi.org/10.1109/ICIMTech50083.2020.9211225
Jodha, R., Sanjay Bc, G., & Chowdhary, K. R. (2018). Text Classification using KNN with different Feature Selection Methods. International Journal of Research, 9(1), 51–58. www.ijrp.org
Kemper, T. D., & Lazarus, R. S. (1992). Emotion and Adaptation. Contemporary Sociology, 21(4), 522. https://doi.org/10.2307/2075902
Khalid, K., Rintyarna, B. S., & Arifin, A. Z. (2015). Seleksi Fitur Dua Tahap Menggunakan Information Gain dan Artificial Bee Colony untuk Kategorisasi Teks Berbasis Support Vector Machine. Systemic: Information System and Informatics Journal, 1(2), 22–26. https://doi.org/10.29080/systemic.v1i2.273
Lei, S. (2012). A feature selection method based on information gain and genetic algorithm. Proceedings - 2012 International Conference on Computer Science and Electronics Engineering, ICCSEE 2012, 2, 355–358. https://doi.org/10.1109/ICCSEE.2012.97
Shah, F. P., & Patel, V. (2016). A review on feature selection and feature extraction for text classification. Proceedings of the 2016 IEEE International Conference on Wireless Communications, Signal Processing and Networking, WiSPNET 2016, 2264–2268. https://doi.org/10.1109/WiSPNET.2016.7566545
Tzacheva, A., Ranganathan, J., & Mylavarapu, S. Y. (2020). Actionable Pattern Discovery for Tweet Emotions. Advances in Intelligent Systems and Computing, 965(July), 46–57. https://doi.org/10.1007/978-3-030-20454-9_5
Vijayakumar, S., & Wu, S. (1999). Sequential Support Vector Classi ers and Regression 1 Abstract 2 Introduction. Proc. International Conference on Soft Computing, (SOCO’99),Genoa, Italy, 610–619.
Vyom Srivastava. (2021). Emotion Detection using Python. WordPress, 6(6), 1228–1232. https://geekyhumans.com/emotion-detection-using-python-and-deepface/
Wulandini, F., & Nugroho, A. S. (2009). Text Classification Using Support Vector Machine for Webmining Based Spatio Temporal Analysis of the Spread of Tropical Diseases. International Conference on Rural Information and Communication Technology 2009 Text, 189–192.
Alhujaili, R. F., & Yafooz, W. M. S. (2021). Sentiment Analysis for Youtube Videos with User Comments: Review. Proceedings - International Conference on Artificial Intelligence and Smart Systems, ICAIS 2021, 814–820. https://doi.org/10.1109/ICAIS50930.2021.9396049
Allouch, M., Azaria, A., Azoulay, R., Ben-Izchak, E., Zwilling, M., & Zachor, D. A. (2019). Automatic Detection of Insulting Sentences in Conversation. 2018 IEEE International Conference on the Science of Electrical Engineering in Israel, ICSEE 2018, 1–5. https://doi.org/10.1109/ICSEE.2018.8646165
Azizah, E. N., & Rainarli, E. (2019). Support Vector Machine and Information Gain for Emotion Classification in Song Lyric. Elibrary.Unikom.Ac.Id, 112. https://elibrary.unikom.ac.id/998/14/UNIKOM_EVA NUR AZIZAH_JURNAL DALAM BAHASA INGGRIS.pdf
Candra Ardiansyah, Indriati, M. (2020). Klasifikasi Emosi pada Komentar Youtube Menggunakan Metode Modified K-Nearest Neighbor dengan BM25 dan Seleksi Fitur Chi-Square. Jurnal Pengembangan Teknologi Informasi Dan Ilmu Komputer, 4(4), 1027–1032. http://j-ptiik.ub.ac.id
Feldman, Ronen; Sanger, J. (2006). The Text Mining Handbook : Advanced Approaches in Analyzing Unstructured Data. Cambridge University Press.
Guo, J. (2022). Deep learning approach to text analysis for human emotion detection from big data. Journal of Intelligent Systems, 31(1), 113–126. https://doi.org/10.1515/jisys-2022-0001
Halim, E., Anindya, R., & Hebrard, M. (2020). The impact of motivation to watch youtube, subjective norms, behavior control, information success model to watching youtube engagement. Proceedings of 2020 International Conference on Information Management and Technology, ICIMTech 2020, August, 800–805. https://doi.org/10.1109/ICIMTech50083.2020.9211225
Jodha, R., Sanjay Bc, G., & Chowdhary, K. R. (2018). Text Classification using KNN with different Feature Selection Methods. International Journal of Research, 9(1), 51–58. www.ijrp.org
Kemper, T. D., & Lazarus, R. S. (1992). Emotion and Adaptation. Contemporary Sociology, 21(4), 522. https://doi.org/10.2307/2075902
Khalid, K., Rintyarna, B. S., & Arifin, A. Z. (2015). Seleksi Fitur Dua Tahap Menggunakan Information Gain dan Artificial Bee Colony untuk Kategorisasi Teks Berbasis Support Vector Machine. Systemic: Information System and Informatics Journal, 1(2), 22–26. https://doi.org/10.29080/systemic.v1i2.273
Lei, S. (2012). A feature selection method based on information gain and genetic algorithm. Proceedings - 2012 International Conference on Computer Science and Electronics Engineering, ICCSEE 2012, 2, 355–358. https://doi.org/10.1109/ICCSEE.2012.97
Shah, F. P., & Patel, V. (2016). A review on feature selection and feature extraction for text classification. Proceedings of the 2016 IEEE International Conference on Wireless Communications, Signal Processing and Networking, WiSPNET 2016, 2264–2268. https://doi.org/10.1109/WiSPNET.2016.7566545
Tzacheva, A., Ranganathan, J., & Mylavarapu, S. Y. (2020). Actionable Pattern Discovery for Tweet Emotions. Advances in Intelligent Systems and Computing, 965(July), 46–57. https://doi.org/10.1007/978-3-030-20454-9_5
Vijayakumar, S., & Wu, S. (1999). Sequential Support Vector Classi ers and Regression 1 Abstract 2 Introduction. Proc. International Conference on Soft Computing, (SOCO’99),Genoa, Italy, 610–619.
Vyom Srivastava. (2021). Emotion Detection using Python. WordPress, 6(6), 1228–1232. https://geekyhumans.com/emotion-detection-using-python-and-deepface/
Wulandini, F., & Nugroho, A. S. (2009). Text Classification Using Support Vector Machine for Webmining Based Spatio Temporal Analysis of the Spread of Tropical Diseases. International Conference on Rural Information and Communication Technology 2009 Text, 189–192.
Diterbitkan
Cara Mengutip
Terbitan
Bagian
Lisensi
Hak Cipta (c) 2023 Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Artikel ini berlisensiCreative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
