Klasifikasi Sentimen Masyarakat Terhadap Kaesang Pangarep pada Media Sosial Twitter/X Menggunakan MLP Classifier dengan Fitur FastText
- Veci Cahyono Tarmizi Universitas Islam Negeri Sultan Syarif Kasim Riau, Pekanbaru, Indonesia
-
Surya Agustian
*
Universitas Islam Negeri Sultan Syarif Kasim Riau, Pekanbaru,
Indonesia
- Okfalisa Okfalisa Universitas Islam Negeri Sultan Syarif Kasim Riau, Pekanbaru, Indonesia
- Pizaini Pizaini Universitas Islam Negeri Sultan Syarif Kasim Riau, Pekanbaru, Indonesia (*) Corresponding Author
Abstract
Social media has become a primary channel for the public to express their opinions and reactions toward various political developments in Indonesia. One of the prominent discussions revolves around Kaesang Pangarep’s appointment as the Chairman of the Indonesian Solidarity Party (PSI). This study aims to analyze and classify public sentiment regarding this issue by employing the Multi-Layer Perceptron (MLP) algorithm integrated with FastText-based text representation. The dataset was collected from Twitter using keywords such as “Kaesang PSI”, and was further expanded with additional data from general topics including Covid-19 and Open Topic, ensuring a balanced distribution across positive, neutral, and negative sentiment categories for a more comprehensive representation of public opinion. The model’s performance was evaluated through four metrics: accuracy, precision, recall, and F1 Score. The experimental results demonstrate that the MLP–FastText model achieved consecutive scores of 0. 5129 for F1 Score, 0. 6035 for accuracy, 0. 5319 for precision, and 0. 5996 for recall. These findings indicate that the combination of MLP and FastText effectively captures sentiment patterns within textual data, particularly in the context of unstructured and dynamic social media content, and performs well when enhanced with relevant external data augmentation strategies.
Downloads
References
Agustian, S., et al. (2024). New directions in text classification research: Maximizing the performance of sentiment classification from limited data. https://github.com/s4gustian/Small_DataSet_Sentiment_Classification
Agustian, S., Syah, M. I., Fatiara, N., & Abdillah, R. (2024). New directions in text classification research: Maximizing the performance of sentiment classification from limited data. arXiv. https://arxiv.org/abs/2407.05627
Ali Kandhro, I., Chhajro, M. A., Kumar, K., Lashari, H. N., & Khan, U. (2019). Student feedback sentiment analysis model using various machine learning schemes: A review. Indian Journal of Science and Technology, 14(12), 1–9. https://doi.org/10.17485/ijst/2019/v12i14/143243
Alnuaim, A. A., et al. (2022). Human-computer interaction for recognizing speech emotions using multilayer perceptron classifier. Journal of Healthcare Engineering, 2022, 1–12. https://doi.org/10.1155/2022/6005446
Andika, L. A., Azizah, P. A. N., & Respatiwulan, R. (2019). Analisis sentimen masyarakat terhadap hasil quick count pemilihan presiden Indonesia 2019 pada media sosial Twitter menggunakan metode naive Bayes classifier. Indonesian Journal of Applied Statistics, 2(1), 34. https://doi.org/10.13057/ijas.v2i1.29998
Angelone, A. M., Galassi, A., & Vittorini, P. (2022). Improved automated classification of sentences in data science exercises. In F. De la Prieta et al. (Eds.), Methodologies and intelligent systems for technology enhanced learning (pp. 12–21). Springer. https://doi.org/10.1007/978-3-030-86618-1_2
Arasy, A., Agustian, S., Handayani, L., & Iskandar, I. (2025). Klasifikasi sentimen menggunakan metode multilayer perceptron dengan fitur TF-IDF. MALCOM: Indonesian Journal of Machine Learning and Computer Science, 5(3), 908–919. https://doi.org/10.57152/malcom.v5i3.2052
Ardinata, P. M. S., Permana, A. A. J., Wijaya, I. N. S. W., Teknik, F., & Kejuruan, D. (2024). Identifikasi dan normalisasi teks slang dengan FastText pada Twitter dalam bahasa Indonesia. Jurnal Pendidikan Teknologi dan Kejuruan, 21(1). https://doi.org/10.23887/jptkundiksha.v21i1.66381
Baihaqi, W. M., Yunita, I. R., Damayanti, A. S. T., & Akhaerunnisa, L. (2023). Analysis of classification algorithm performance on user review sentiment of the Muamalat DIN application. CogITo Smart Journal, 9(2), 241–251. https://doi.org/10.31154/cogito.v9i2.511.241-251
El Saputra, Y., Agustian, S., Yusra, Y., & Ramadhani, S. (2024). Klasifikasi sentimen SVM dengan dataset yang kecil pada kasus Kaesang sebagai ketua umum PSI. KLIK: Kajian Ilmiah Informatika dan Komputer, 4(6), 2902–2908. https://doi.org/10.30865/klik.v4i6.1944
Goh, A. M., & Yann, X. L. (2021). A novel sentiments analysis model using perceptron classifier. International Journal of Electronics Engineering and Applications, 10(2), 1–10. https://doi.org/10.30696/IJEEA.IX.IV.2021.01-10
Heidari, A. A., Faris, H., Mirjalili, S., Aljarah, I., & Mafarja, M. (2020). Ant lion optimizer: Theory, literature review, and application in multi-layer perceptron neural networks. In S. Mirjalili, J. Song Dong, & A. Lewis (Eds.), Nature-inspired optimizers: Theories, literature reviews and applications (pp. 23–46). Springer. https://doi.org/10.1007/978-3-030-12127-3_3
Khan, A., Majumdar, D., & Mondal, B. (2025). Sentiment analysis of emoji fused reviews using machine learning and BERT. Scientific Reports, 15(1), Article 7538. https://doi.org/10.1038/s41598-025-92286-0
Kuyumcu, B., Aksakalli, C., & Delil, S. (2019). An automated new approach in fast text classification (fastText). In Proceedings of the 3rd International Conference on Natural Language Processing and Information Retrieval (pp. 1–4). ACM. https://doi.org/10.1145/3342827.3342828
Naldi, A., & Agustian, S. (2023). Klasifikasi sentimen vaksin COVID-19 menggunakan K-nearest neighbor berdasarkan word embeddings FastText pada Twitter. ZONAsi: Jurnal Sistem Informasi, 5(2), 323–333. https://doi.org/10.31849/zn.v5i2.12548
Pasaribu, F. H., Khairina, N., Noviandri, D., Susilawati, S., & Syah, R. (2023). Analysis of the multilayer perceptron algorithm on Twitter user’s sentiment towards the COVID-19 vaccine. Journal of Informatics and Telecommunication Engineering, 7(1), 155–163. https://doi.org/10.31289/jite.v7i1.9664
Pranata, J., Agustian, S., Jasril, J., & Haerani, E. (2025). Penggunaan model bahasa indoBERT pada metode random forest untuk klasifikasi sentimen dengan dataset terbatas. Building of Informatics, Technology and Science (BITS), 6(3), 1668–1676. https://doi.org/10.47065/bits.v6i3.6335
Prastowo, E. Y., Endroyono, & Yuniarno, E. M. (2019). Combining SentiStrength and multilayer perceptron in Twitter sentiment classification. In 2019 International Seminar on Intelligent Technology and Its Applications (ISITIA) (pp. 381–386). IEEE. https://doi.org/10.1109/ISITIA.2019.8937134
Qi, Y., & Shabrina, Z. (2023). Sentiment analysis using Twitter data: A comparative application of lexicon- and machine-learning-based approach. Social Network Analysis and Mining, 13(1), Article 31. https://doi.org/10.1007/s13278-023-01030-x
Rohman, N. (2023). Peran Partai Solidaritas Indonesia (PSI) dalam pemilihan presiden 2024: Analisis terhadap pemilih pemula. JPW (Jurnal Politik Walisongo), 5(1), 85–102. https://doi.org/10.21580/jpw.v5i1.18330
Susilawati, S., & Iqbal, M. (2025). Penerapan metode Naïve Bayes untuk mengidentifikasi sentimen pengguna pada ulasan aplikasi ReelShort di Google Play Store. SIMKOM, 10(1), 49–59. https://doi.org/10.51717/simkom.v10i1.686
Umer, M., et al. (2023). Impact of convolutional neural network and FastText embedding on text classification. Multimedia Tools and Applications, 82(4), 5569–5585. https://doi.org/10.1007/s11042-022-13459-x
Wang, Y., Guo, J., Yuan, C., & Li, B. (2022). Sentiment analysis of Twitter data. Applied Sciences, 12(22), Article 11775. https://doi.org/10.3390/app122211775
Wijaya, T. N., Indriati, R., & Muzaki, M. N. (2021). Analisis sentimen opini publik tentang Undang-Undang Cipta Kerja pada Twitter. Jambura Journal of Electrical and Electronics Engineering, 3(2), 78–83. https://doi.org/10.37905/jjeee.v3i2.10885
Wisnu, H., Afif, M., & Ruldevyani, Y. (2020). Sentiment analysis on customer satisfaction of digital payment in Indonesia: A comparative study using KNN and Naïve Bayes. In Journal of Physics: Conference Series (Vol. 1444, No. 1, Article 012034). Institute of Physics Publishing. https://doi.org/10.1088/1742-6596/1444/1/012034
Yang, E., et al. (2023). Transformer versus traditional natural language processing: How much data is enough for automated radiology report classification? British Journal of Radiology, 96(1149). https://doi.org/10.1259/bjr.20220769
Yusanto, Y., & Akbar, M. (2024). Analisis sentimen Jogja darurat sampah di Twitter menggunakan ekstraksi fitur model Word2Vec dan convolutional neural network. TIN: Terapan Informatika Nusantara, 4(10), 679–688. https://doi.org/10.47065/tin.v4i10.4952
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel Klasifikasi Sentimen Masyarakat Terhadap Kaesang Pangarep pada Media Sosial Twitter/X Menggunakan MLP Classifier dengan Fitur FastText
Pages: 1105-1114
Copyright (c) 2025 Veci Cahyono Tarmizi, Surya Agustian, Okfalisa Okfalisa; Pizaini Pizaini
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (Refer to The Effect of Open Access).
