MULTI LABEL KLASIFIKASI GENRE FILM BERDASARKAN SINOPSIS MENGGUNAKAN METODE LONG SHORT-TERM MEMORY (LSTM)
DOI:
https://doi.org/10.36595/misi.v8i1.1436Keywords:
Klasifikasi Multilabel, LSTM, Word Embedding, Glove, Word2Vec, FastTextAbstract
Film merupakan sarana hiburan yang dapat dinikmati oleh banyak orang, bukan hanya sebagai hiburan tetapi juga merupakan sarana pemasaran, perdagangan dan pendidikan. Genre merupakan salah satu karakteristik penting dari sebuah film. Oleh sebab itu klasifikasi genre merupakan cara untuk menemukan hubungan dari masing-masing film sehingga memudahkan penonton untuk menemukan film yang sesuai. Klasifikasi genre film mungkin sangat komprehensif atau beragam berdasarkan kriteria, ada banyak genre yang serupa dalam satu film mungkin termasuk beberapa genre di dalamnya. Untuk menyelesaikan masalah tersebut peneliti mengusulkan klasifikasi multilabel genre film berdasarkan sinopsis menggunakan algoritma Long Short Term Memory (LSTM) dan membandingkan kinerja word embedding Word2Vec, GloVe dan FastText. Arsitektur model LSTM yang diusulkan terdiri dari beberapa layer yakni layer Embedding, SpastialDropout1d, LSTM dan Dese. Nilai dari masing-masing layer yakni 300, 0.5, 128, dan 18. Pengujian dilakukan dengan tiga scenario menunjukkan word embedding GloVe mengungguli Word2Vec dan FastText dengan f1-score 0.603, 0.591 dan 0.580.
References
R. Saptya, M. Permana, L. Puspitasari, and S. Indriani, “Industri film Indonesia dalam perspektif sineas Komunitas Film Sumatera Utara,” vol. 3, no. 2, pp. 185–199, 2019.
C. M. Karolina, E. Maryani, and W. Sjuchro, “Implikasi genre film dan pemahaman penonton film tuna netra di ‘ Bioskop Harewos ,’” vol. 4, no. 1, pp. 123–142, 2020.
H. S. Spilker, “The dimensions of streaming?: toward a typology of an evolving concept,” 2020, doi: 10.1177/0163443720904587.
K. Kundalia, Y. Patel, and M. Shah, “Multi-label Movie Genre Detection from a Movie Poster Using Knowledge Transfer Learning,” Augmented Human Research, vol. 5, no. 1, 2020, doi: 10.1007/s41133-019-0029-y.
N. Hossain, M. Ahamad, S. Aktar, and M. A. Moni, “Movie Genre Classification with Deep Neural Network using Poster Images,” pp. 27–28, 2021.
J. A. Wi, S. Jang, and Y. Kim, “Poster-Based Multiple Movie Genre Classification Using Inter-Channel Features,” IEEE Access, vol. 8, no. April, pp. 66615–66624, 2020, doi: 10.1109/ACCESS.2020.2986055.
P. Matthews and K. Glitre, “Genre analysis of movies using a topic model of plot summaries,” J Assoc Inf Sci Technol, vol. 72, no. 12, pp. 1511–1527, 2021, doi: 10.1002/asi.24525.
A. M. Ertugrul and P. Karagoz, “Movie Genre Classification from Plot Summaries Using Bidirectional LSTM,” Proceedings - 12th IEEE International Conference on Semantic Computing, ICSC 2018, vol. 2018-Janua, pp. 248–251, 2018, doi: 10.1109/ICSC.2018.00043.
J. Wehrmann, M. A. Lopes, and R. C. Barros, “Self-attention for synopsis-based multi-label movie genre classification,” Proceedings of the 31st International Florida Artificial Intelligence Research Society Conference, FLAIRS 2018, pp. 236–241, 2018.
V. D. F. Giuseppe Portolese, “On the Use of Synopsis-based Features for Film Genre Classification,” 2018.
Giuseppe Portolese and V. D. F. Marcos Aur´elio Domingues, “Exploring Textual Features for Multi-label Classification of Portuguese Film Synopses,” pp. 669–681, 2019.
P. G. Shambharkar, “Genre Classification of Movie Trailers using 3D Convolutional Neural Networks,” no. Iciccs, pp. 850–858, 2020.
R. B. Mangolin et al., “A multimodal approach for multi-label movie genre classification,” Multimed Tools Appl, vol. 81, no. 14, pp. 19071–19096, Jun. 2022, doi: 10.1007/s11042-020-10086-2.
J. Díaz-Ramírez, “Machine Learning and Deep Learning,” Ingeniare, vol. 29, no. 2, pp. 182–183, 2021, doi: 10.4067/S0718-33052021000200180.
Y. Bengio, P. Simard, and P. Frasconi, “Learning Long-Term Dependencies with Gradient Descent is Difficult,” 1994.
Sepp Hochreiter and Jurgen Schmidhuber, “LONG SHORT TERM MEMORY,” Neural Comput, 1997.
R. B. Mangolin et al., “A multimodal approach for multi-label movie genre classification,” 2020.
V. Battu, V. Batchu, R. R. Reddy, M. K. Reddy, and R. Mamidi, “Predicting the genre and rating of a movie based on its synopsis,” Proceedings of the 32nd Pacific Asia Conference on Language, Information and Computation, PACLIC 2018, no. December, pp. 52–62, 2018.
D. A. Lebaron, “Multi-label Movie Genre Classification Using Multiple Modalities,” 2018.
S. Basu, S. Kumar, S. S. Banga, and H. Garg, “Using an Ensemble Learning Approach on Traditional Machine Learning Methods to Solve a Multi-Label Classification Problem,” pp. 761–772, 2021, doi: 10.1007/978-981-15-7533-4_60.
S. Guehria, H. Belleili, and N. Azizi, “‘ One vs All ’ Classi fi er Analysis for Multi-label Movie Genre Classi fi cation Using Document Embedding,” vol. 1, pp. 478–487, 2021.
J. Wang, “Using Machine Learning to Identify Movie Genres through Online Movie Synopses,” Proceedings - 2020 2nd International Conference on Information Technology and Computer Application, ITCA 2020, pp. 691–697, 2020, doi: 10.1109/ITCA52113.2020.00008.
A. C. Saputra, “Klasifikasi Genre Film berdasarkan Sinopsis Film Indonesia,” pp. 201–204, 2019.
D. Sarkar, Text Analytics with Python. Apress, 2019. doi: 10.1007/978-1-4842-4354-1.
M. Berranem, N. Azizi, A. Boukhamla, and I. Gasmi, “LSTMs Classifiers Fusion For Multi-Label Text Classification,” 2022.
Downloads
Additional Files
Published
How to Cite
Issue
Section
License
Semua tulisan pada jurnal ini menjadi tanggungjawab penuh penulis.
