EUVIMEDEUVIMED entdecken
Open Access · CC BY-SA 4.0

Sentiment Analysis of Athlete Naturalization Using Machine Learning Algorithms

R.Bimantoro Putra, Muhammad Dermawan Mulyodi Putro, Asmaul Husna RS, Mindi Richia Putri, Yayu Angriani

Jurnal MediaTIK · 08.07.2026 · 73-85

DOI: 10.59562/45ymq957 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Jurnal MediaTIK, online erschienen am 08.07.2026. Verfasst von R.Bimantoro Putra und 4 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-SA 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Athlete naturalization has become a prominent topic in Indonesia, generating extensive public discussion on social media platforms, particularly YouTube. Understanding public sentiment toward this issue is important for evaluating public responses to sports policies and national identity. This study compares the performance of four supervised machine learning algorithms, namely Support Vector Machine (SVM), Classification and Regression Tree (CART), Random Forest, and Extreme Gradient Boosting (XGBoost), for sentiment classification of YouTube comments related to athlete naturalization in Indonesia. A total of 5,132 comments were collected using the YouTube Data API v3 between January and March 2025. The data were preprocessed through cleaning, case folding, tokenization, slang normalization, stopword removal, and stemming, followed by feature extraction using Term Frequency–Inverse Document Frequency (TF–IDF). Sentiment labels were generated using a custom lexicon-based approach and classified into Positive, Neutral, and Negative categories. Hyperparameter optimization was performed using RandomizedSearchCV and Particle Swarm Optimization (PSO). Experimental results indicate that XGBoost achieved the best performance, with a validation accuracy of 97.73%, a testing accuracy of 98.64%, a Macro Average F1-Score of 0.96, and a Weighted Average F1-Score of 0.99. Neutral sentiment dominated the dataset, indicating that most users expressed informational or observational opinions regarding athlete naturalization. These findings demonstrate the effectiveness of XGBoost for sentiment classification while providing insights into public opinion on athlete naturalization. The results should be interpreted considering the use of lexicon-based sentiment labeling and data collected exclusively from YouTube.

Zitieren

APA

Putra, R., Putro, M. D. M., RS, A. H., Putri, M. R., & Angriani, Y. (2026). Sentiment Analysis of Athlete Naturalization Using Machine Learning Algorithms. Jurnal MediaTIK, 73-85. https://doi.org/10.59562/45ymq957

Vancouver

Putra R, Putro MDM, RS AH, Putri MR, Angriani Y. Sentiment Analysis of Athlete Naturalization Using Machine Learning Algorithms. Jurnal MediaTIK. 2026:73-85. doi:10.59562/45ymq957

BibTeX
@article{Putra2026,
  author = {Putra, R.Bimantoro and Putro, Muhammad Dermawan Mulyodi and RS, Asmaul Husna and Putri, Mindi Richia and Angriani, Yayu},
  title = {Sentiment Analysis of Athlete Naturalization Using Machine Learning Algorithms},
  journal = {Jurnal MediaTIK},
  year = {2026},
  pages = {73--85},
  doi = {10.59562/45ymq957}
}
Kostenlos starten →