Sentiment Analysis of Mie Gacoan Pemuda Cirebon Restaurant Reviews Using Support Vector Machine

Aditya Darusman

doi:10.59934/jaiea.v5i2.1905

Authors

Aditya Darusman STMIK IKMI Cirebon

DOI:

https://doi.org/10.59934/jaiea.v5i2.1905

Keywords:

sentiment analysis; Support Vector Machine; Google Maps; customer reviews; text mining.

Abstract

The growth of digital platforms has increased the use of sentiment analysis to understand public perceptions of business services. Customer reviews on Google Maps provide valuable insights but are unstructured and linguistically diverse, requiring robust analytical methods. This study conducts sentiment analysis on reviews of Mie Gacoan Pemuda Cirebon using a Support Vector Machine (SVM) classifier. The research focuses on designing an effective text preprocessing pipeline, identifying sentiment distribution, and evaluating SVM performance. The methodology includes web scraping, manual labeling, text preprocessing, TF-IDF feature extraction, dataset splitting, model training, and evaluation using accuracy, precision, recall, and F1-score. The results show that the majority of reviews are positive, and the SVM model achieves strong performance with an accuracy of 0.82. These findings provide an objective overview of customer perceptions and demonstrate the effectiveness of SVM for Indonesian-language sentiment classification. The model can support businesses in improving service quality based on customer feedback.

Downloads

Download data is not yet available.

References

Aldayel and W. Magdy, “Arabic sentiment analysis: A survey,” Journal of Information Science, vol. 47, no. 1, pp. 1–17, 2021.

M. Ali, S. Shah, F. Khan, and S. Raza, “Stratified sampling approaches for reliable machine learning evaluation,” International Journal of Data Science, vol. 9, no. 2, pp. 112–129, 2025.

H. Aljebreen, M. Almanea, and A. Alsubaihin, “Emoji normalization for sentiment analysis in multilingual contexts,” Journal of Computational Linguistics, vol. 49, no. 3, pp. 521–545, 2023.

Y. Asmare, T. Dagne, and M. Alemu, “Cross-validation strategies for robust text classification using SVM,” Procedia Computer Science, vol. 190, pp. 742–749, 2021.

M. Azmi, D. Pratama, and N. Sari, “Web scraping for customer feedback extraction in e-commerce platforms,” Indonesian Journal of Information Systems, vol. 8, no. 1, pp. 45–52, 2023.

T. Babatope, “Tokenization strategies and their effects on text classification,” Applied NLP Review, vol. 6, no. 2, pp. 98–113, 2024.

J. Batmetan and T. Hariguna, “Text mining and preprocessing strategies in Indonesian sentiment analysis,” Journal of Big Data Analytics, vol. 12, no. 1, pp. 77–89, 2024.

S. Becker, “Stopword removal and its influence on classifier performance,” Information Processing & Management, vol. 59, no. 4, 102–119, 2022.

[9] L. Chai, “Preprocessing pipelines for social media text mining,” Journal of Information Processing Systems, vol. 18, no. 6, pp. 1210–1223, 2022.

P. Chatterjee, A. Singh, and S. Roy, “Evaluating sentiment classifiers using confusion matrix metrics,” International Journal of Machine Learning, vol. 14, no. 2, pp. 89–104, 2023.

X. Chen, Y. Liu, and H. Zhao, “Dimensionality reduction techniques in TF-IDF-based document analysis,” Expert Systems with Applications, vol. 203, 117–142, 2022.

Chifu and M. Fournier, “Slang normalization in noisy text environments,” Computational Linguistics Review, vol. 5, no. 1, pp. 33–58, 2023.

E. Chongo and S. Soldera, “Weak supervision approaches for semi-automatic data labeling,” Machine Learning Research Letters, vol. 15, no. 3, pp. 224–238, 2024.

M. Colley and M. Asaduzzaman, “Document-level sentiment classification trends,” Journal of Data Mining & Digital Humanities, vol. 6, no. 1, pp. 44–59, 2021.

Dakwah, D. Nurhayati, and M. Prasetyo, “Indonesian sentiment analysis dataset challenges,” Indonesian Journal of Computational Linguistics, vol. 13, no. 1, pp. 55–70, 2024.

J. Dang, Y. Cheng, and P. Liu, “Comparative analysis of word embeddings vs. TF-IDF in sentiment tasks,” Knowledge-Based Systems, vol. 227, 107–130, 2021.

Das and S. Mukherjee, “Annotation guidelines for sentiment analysis datasets,” Language Resources and Evaluation Journal, vol. 57, no. 3, pp. 112–130, 2023.

D. Dimitrov, M. Becker, and M. Müller, “Multilabel annotation challenges in sentiment analysis,” ACL Anthology, pp. 634–649, 2021.

H. Ding, W. Zhu, and G. Li, “Hyperparameter tuning in SVM: A grid search-based approach,” Neural Computing and Applications, vol. 36, no. 7, pp. 3912–3925, 2024.

T. Duong and Q. Nguyen, “The effectiveness of stratified train-test split in text classification,” Data & Knowledge Engineering, vol. 145, 102143, 2023.

N. Ekolle and T. Kohno, “Cleaning noisy text: Removing URLs and symbols in social media data,” Social Media Analytics Journal, vol. 4, no. 2, pp. 122–137, 2023.

Evans, A. Marshall, and K. Ross, “Large-scale API-based data collection for customer insight mining,” Journal of Data Engineering, vol. 18, no. 1, pp. 55–67, 2024.

E. Guest, Z. Chen, and S. Han, “Disambiguating sarcastic expressions using transformer models,” ACL Transactions, vol. 9, no. 1, pp. 210–223, 2021.

X. Gong, S. Park, and J. Choi, “Train-test splits: Experimental guidelines for imbalanced datasets,” Journal of Intelligent Systems, vol. 34, no. 1, pp. 144–160, 2025.

S. Guindo, A. Abdou, and T. Jawara, “Hyperparameter optimization using grid search for SVM,” International Journal of Computer Vision and Pattern Recognition, vol. 3, no. 2, pp. 44–52, 2021.

K. Gunasekar and S. Thilagamani, “TF-IDF weighting impact on SVM sentiment classifiers,” International Journal of AI & Applications, vol. 14, no. 2, pp. 33–47, 2023.

Hammad, Y. Mansur, and D. Halim, “Digital review culture in online platforms,” Asian Journal of Information Studies, vol. 11, no. 3, pp. 129–145, 2022.

M. Hidayatullah, A. Yusuf, and S. Fikri, “Sentiment analysis in small cities: Challenges in Indonesian local contexts,” International Journal of Information Technology, vol. 9, no. 4, pp. 115–128, 2023.

Hutapea and A. Maharani, “Digital strategy adaptation in public service institutions,” Journal of Digital Transformation, vol. 5, no. 2, pp. 97–110, 2023.

R. Ipmawati, H. Prasetyo, and B. Setiawan, “Sentiment classification of Google Maps reviews using TF-IDF and SVM,” Indonesian Journal of Data Mining, vol. 7, no. 1, pp. 14–25, 2024.

Z. Ismet, F. Rahmawati, and I. Lestari, “Multi-topic challenges in online restaurant reviews,” Tourism Informatics Journal, vol. 6, no. 1, pp. 40–55, 2022.

M. Isnain, H. Yusuf, and T. Dewi, “Evaluating imbalance-sensitive classifiers in sentiment analysis,” International Journal of Machine Learning, vol. 13, no. 2, pp. 119–130, 2021.

Y. Jiang, J. Costa, and T. Miller, “Semi-supervised learning with pseudo-labeling for sentiment analysis,” Knowledge Engineering Review, vol. 40, no. 1, pp. 1–19, 2025.

J. Kim, C. Hsu, and V. Patel, “Leveraging Google Maps API for business performance analysis,” Journal of Business Analytics, vol. 7, no. 1, pp. 22–36, 2024.

[35] C. Kumar and S. R, “Comparative study of SVM and BERT for sentiment analysis,” Procedia Computer Science, vol. 215, pp. 108–117, 2022.

J. León-Sandoval, P. Gómez, and H. Ramirez, “Text cleaning procedures in social media analytics,” Information Sciences, vol. 598, pp. 55–74, 2022.

M. Leenings, M. Brinkmann, and A. Müller, “Reliable model evaluation through nested cross-validation,” Machine Learning Research, vol. 25, no. 4, pp. 330–349, 2024.

[38] D. Leung, “Social media text normalization techniques,” International Journal of Computational Linguistics, vol. 8, no. 2, pp. 113–127, 2022.

F. Li, Y. Zhang, and H. Sun, “Evaluating SVM models with multi-stage cross-validation,” Pattern Recognition Letters, vol. 153, pp. 85–92, 2021.

Y. Liu, H. Chen, and J. Zhao, “Parameter tuning for SVM in large-scale classification,” Knowledge-Based Systems, vol. 229, 107–141, 2021.

Lubis, D. Kurniawan, and N. Rahmawati, “Preprocessing Indonesian social media text for sentiment tasks,” Indonesian Journal of Electrical Engineering and Informatics, vol. 11, no. 2, pp. 442–455, 2023.

G. Lukwaro, B. Musau, and S. Otieno, “Investigating TF-IDF feature selection for document classification,” Applied Computing Review, vol. 5, no. 1, pp. 50–61, 2024.

Ma’ruf, R. Adawiyah, and D. Supriyadi, “SVM for Indonesian sentiment analysis: A performance review,” Journal of Computer Science, vol. 18, no. 2, pp. 145–159, 2022.

R. Maulana, M. Sari, and A. Putra, “Handling informal Indonesian text in sentiment analysis,” Journal of Language Technology, vol. 9, no. 1, pp. 35–48, 2023.

E. Mata, “Stopword lists for modern NLP applications,” Journal of Computational Linguistics Research, vol. 14, no. 1, pp. 15–27, 2025.

[46] M. Meem and K. Hasan, “IndoBERT vs SVM: A comparative analysis,” Computational Linguistics Asia, vol. 4, no. 2, pp. 55–70, 2023.

Neto and I. Paraboni, “Feature selection methods for text classification,” Language Resources & Evaluation, vol. 55, pp. 879–898, 2021.

G. Pant, V. Sharma, and S. Khatri, “Evaluation protocols in machine learning experiments,” Journal of AI Research, vol. 12, no. 3, pp. 221–238, 2023.

M. Piles et al., “Stability measures in feature selection,” Genomics Data Science, vol. 17, no. 2, pp. 533–547, 2021.

Pohl, F. Wiese, and S. Hartmann, “Nested CV for hyperparameter optimization in SVM,” Knowledge and Information Systems, vol. 66, no. 1, pp. 33–55, 2024.

R. Prasad and R. Bakhshi, “Classification report metrics for evaluating sentiment models,” Journal of Data Science Methods, vol. 5, no. 3, pp. 112–128, 2022.

M. Riyadi, D. Sutrisno, and A. Wibowo, “Accuracy evaluation strategies in sentiment classification,” Journal of Intelligent Systems, vol. 11, no. 1, pp. 99–108, 2021.

M. Saifullah, D. Rahmadani, and P. Lestari, “Stopwords in Indonesian NLP: A performance study,” Journal of Information Technology Research, vol. 7, no. 1, pp. 21–39, 2024.

Sentiment Analysis Using Text Mining: A Survey, International Journal of Information Science, vol. 19, no. 2, pp. 55–77, 2023.

L. Shi, P. Xu, and H. Yang, “Multi-class evaluation techniques in NLP models,” Journal of Computational Intelligence, vol. 32, no. 1, pp. 77–94, 2025.

[56] R. Siddiqui, N. Patel, and S. Kumar, “Preventing data leakage in text classification experiments,” Machine Learning & Applications Journal, vol. 19, no. 1, pp. 64–79, 2024.

P. Sivakumar, R. Menon, and V. Haridas, “Train-test splitting strategies for text analytics,” Expert Systems Review, vol. 11, no. 2, pp. 155–170, 2024.

T. Song, R. Li, and S. Zhao, “Expert-guided annotation systems for sentiment datasets,” Journal of Language Resources, vol. 18, no. 2, pp. 215–230, 2024.

[59] A. Sumantiawan, Y. Putra, and B. Hermawan, “Challenges in big data sentiment analytics,” Journal of Information Systems, vol. 9, no. 1, pp. 55–71, 2023.

Toma, D. Ciobanu, and A. Pop, “Train-test evaluation in machine learning pipelines,” Journal of Computational Methods, vol. 11, no. 4, pp. 212–223, 2021.

[61] P. Wankhade, D. Sharma, and Y. Patel, “Context-aware embeddings for sentiment classification,” NLP Advances Journal, vol. 5, no. 1, pp. 44–60, 2022.

Wang, H. Chen, and Y. Li, “SVM for high-dimensional text classification,” Pattern Analysis and Applications, vol. 25, no. 2, pp. 341–359, 2022.

H. Wang, J. Liu, and Q. Zhao, “Support Vector Machines in modern NLP tasks,” IEEE Access, vol. 11, pp. 44521–44533, 2023.

[64] C. Weinand, S. Bai, and J. Müller, “Visualization of TF-IDF features using t-SNE,” Data Visualization Journal, vol. 14, no. 1, pp. 91–108, 2025.

F. Williady and Y. Ban, “Large-scale online review scraping for restaurant analytics,” Journal of Data Acquisition, vol. 10, no. 2, pp. 77–93, 2023.

L. Wong, “Self-training techniques for sentiment classification,” Machine Learning Frontier, vol. 8, no. 3, pp. 119–135, 2021.

[67] M. Yang, Z. Chen, and T. Lei, “SVM model validation with K-fold cross-validation,” Computers & Industrial Engineering, vol. 160, 107–118, 2021.

Yasir, S. Malik, and R. Noor, “Handling data leakage in model development,” AI Review, vol. 14, no. 2, pp. 186–199, 2022.

Zahrah, R. Putri, and B. Nugraha, “Sentiment analysis of Google Maps reviews using SVM,” Journal of Applied Data Science, vol. 3, no. 1, pp. 44–58, 2024.

L. Zaki, A. Irawan, and M. Sunardi, “Improving class balance in sentiment datasets,” Information Technology Journal, vol. 18, no. 3, pp. 317–329, 2022.

Zheng, R. Li, and Q. Han, “TF-IDF and PCA for document analysis,” Information Extraction Review, vol. 7, no. 1, pp. 55–70, 2023.

Zou, J. Liu, and W. Chen, “Digital divide challenges in public sector analytics,” Information Society Journal, vol. 40, no. 2, pp. 133–148, 2024.