Improving Sentiment Classification of Indonesia's School Zoning Admission Policy on Twitter
Article Sidebar
Main Article Content
Abstract
Since 2016, the Indonesian government has implemented a zoning-based policy for its online New Student Admission (Penerimaan Peserta Didik Baru, PPDB) system to ensure equitable access to quality education. Despite this intent, the policy has repeatedly drawn mixed public reactions, and in 2024 the debate intensified on social media, particularly on Twitter (X), which has become a primary channel for the public to express opinions on the policy. Understanding this sentiment at scale requires an approach that can cope with the unstructured, informal, and slang-heavy nature of Indonesian social media text. This study proposes a hybrid sentiment analysis approach that combines the InSet (Indonesia Sentiment) Lexicon with a Recurrent Neural Network (RNN) based on Long Short-Term Memory (LSTM) to classify public sentiment toward the 2024 PPDB zoning policy from 1,771 crawled tweets. Two scenarios were tested: Scenario 1 used an LSTM model trained on text alone, while Scenario 2 combined the LSTM with InSet Lexicon polarity scores as an auxiliary input. Scenario 1 achieved a training accuracy of 94.61% but only 66.18% on validation data, indicating overfitting, whereas Scenario 2 achieved a validation accuracy of 95%, with 92% precision, 96% recall, and a 93% F1-score. The results indicate that combining lexicon-based scoring with LSTM substantially improves classification accuracy and generalization on Indonesian-language, informal social media text, and that the overall public sentiment toward the 2024 zoning policy tended to be positive.
Article Details
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
References
[1] Anzaldi and Sukmana, “SWOT analysis of the zoning system policy in new student admission,” 2022.
[2] Y. Sulistyosari, A. Wardana, and S. A. Dwiningrum, “School zoning and equal education access in Indonesia,” Int. J. Eval. Res. Educ. (IJERE), pp. 586–593, 2023.
[3] T. Widiyati and A. Sudrajat, “Conflict and overlapping authorities in the newly implemented school zoning policy in Indonesia: The case in the urban–rural regency of Magelang,” in Proc. 2nd Int. Conf. Soc. Sci. Character Educ. (ICoSSCE), Atlantis Press, 2019.
[4] Christina and Sherly, “Sarcasm in sentiment analysis of Indonesian text: A literature review,” J. Teknol. Inf., pp. 54–59, 2019.
[5] R. I. Terecha, F. Wahyudi, and U. M. Jannah, “Penanganan negasi dalam analisa sentimen Bahasa Indonesia,” JUSIFOR, vol. 1, no. 1, pp. 51–58, 2022.
[6] Ariyanto and Chamidah, “Comparison of SVM and Naive Bayes methods for Indonesian sentiment analysis,” 2021.
[7] E. Daniati and H. Utama, “Analisis sentimen dengan pendekatan ensemble learning dan word embedding pada Twitter,” J. Inf. Syst. Manag. (JOISM), pp. 125–231, 2023.
[8] S. Kausar, X. Huahu, W. Ahmad, and M. Y. Shabir, “A sentiment polarity categorization technique for online product reviews,” IEEE Access, vol. 8, pp. 3594–3605, 2020.
[9] F. Koto and Rahmaningtyas, “InSet lexicon: Evaluation of a word list for Indonesian sentiment analysis in microblogs,” in Int. Conf. Asian Lang. Process. (IALP), 2017, pp. 391–394.
[10] B. Liu, Sentiment Analysis and Opinion Mining. Morgan & Claypool Publishers, 2012.
[11] A. Nurkasanah and M. Hayaty, “Feature extraction using lexicon on the emotion recognition dataset of Indonesian text,” Ultimatics J. Tek. Inform., vol. 14, no. 1, pp. 20–27, 2022.
[12] D. A. Firdlous, “Analisis sentimen publik Twitter terhadap Pemilu 2024 menggunakan model Long Short-Term Memory (LSTM),” Undergraduate thesis, Universitas Pendidikan Indonesia, 2023.
[13] K. Elshakankery et al., “Hybrid deep learning for sentiment polarity determination of Arabic microblogs,” in Neural Information Processing (ICONIP), Part II, 2019.
[14] A. Al Farisi, Arini, Wardhani, Matin, and Y. Durachman, “K-Means algorithm and Levenshtein Distance algorithm for sentiment analysis of school zonation system policy,” in 2021 6th Int. Conf. Informatics Comput. (ICIC), 2021, pp. 1–6.
[15] D. Anggraini and Tursina, “Sentiment analysis of new student admission zoning system policy using K-Nearest Neighbor and Levenshtein Distance,” 2019.
[16] A. A. Dwisanny and S. Suptami, “Twitter opinion sentiment analysis based on new student admission zoning issues using the Naïve Bayes and TensorFlow methods,” in 9th Int. Conf. Signal Process. Intell. Syst. (ICSPIS), 2023, pp. 1–8.
[17] M. N. Chozin, L. W. Savitri, R. E. Apriyanto, and M. Marzuki, “Public perception in evaluating Indonesia's school zoning admission policy: Insight into the ongoing debate,” Al-Ishlah J. Pendidikan, vol. 17, no. 1, pp. 751–770, 2025.
[18] G. F. S. Medantoro and M. Muljono, “Comparative analysis of IndoBERT and classic machine learning models for sentiment classification of education policy on social media X,” J. Appl. Inform. Comput. (JAIC), vol. 10, no. 1, pp. 548–557, 2026.
[19] W. Nugraha, M. T. Julianto, M. K. Najib, and E. Khatizah, “Public sentiment toward the Indonesian capital relocation policy on X using a BiLSTM-CNN model,” J. Telematika, vol. 20, no. 2, pp. 114–126, 2025.
[20] S. Shevira, I. D. Suarjaya, and P. W. Buana, “Pengaruh kombinasi dan urutan pre-processing pada tweets Bahasa Indonesia,” J. Ilm. Teknol. Komput., pp. 1–8, 2022.
[21] Bunyamin, F. A. Huda, and A. Ardiyanti, “Indonesian stemmer for ambiguous word based on context,” in Int. Conf. Data Sci. Its Appl. (ICoDSA), 2021, pp. 1–9.
[22] S. J. Putra, I. Khalil, M. N. Gunawan, R. Amin, and T. Sutabari, “A hybrid model for social media sentiment analysis for Indonesian text,” in Int. Conf. Inf. Integr. Web-based Appl. Serv., 2018, pp. 297–301.