Analisis Sentimen dan Pemodelan Topik pada Ulasan Pengguna Aplikasi myIM3 Menggunakan Support Vector Machine dan Latent Dirichlet Allocation


  • Priyo Agung Prastyo * Mail Universitas Amikom Purwokerto, Purwokerto, Indonesia
  • Berlilana Berlilana Universitas Amikom Purwokerto, Purwokerto, Indonesia
  • Imam Tahyudin Universitas Amikom Purwokerto, Purwokerto, Indonesia
  • (*) Corresponding Author
Keywords: Latent Dirichlet Allocation (LDA); myIM3 Application; Sentiment Analysis; Support Vector Machine (SVM); User Reviews

Abstract

In the current digital era, mobile applications play a crucial role in enhancing user experience. This study analyzes user sentiment towards the myIM3 application and identifies key topics discussed in user reviews using Support Vector Machine (SVM) and Latent Dirichlet Allocation (LDA). The dataset comprises 1,000 user reviews from the Google Play Store, including review text, star ratings, review dates, and application versions. Data preprocessing involved cleaning, normalization, stop word removal, and lemmatization. Text data was transformed using Term Frequency-Inverse Document Frequency (TF-IDF). The dataset was split into training and testing sets (80:20 ratio). The SVM model, optimized with a linear kernel, achieved an accuracy of 84.65%, with a precision of 85% for negative sentiment, 84% for positive sentiment, and challenges in classifying neutral sentiment. Cross-validation ensured model robustness. LDA identified five primary topics: general user experience, application usability and purchase experience, positive feedback and functionality, general application evaluation, and network issues and pricing concerns. Techniques like oversampling, undersampling, and hybrid methods addressed imbalanced datasets to enhance model performance. The results revealed that 43% of reviews were positive, 42% were negative, and 15% were neutral. The key topics indicated that network issues and pricing were significant user concerns. These findings provide valuable insights for developers and stakeholders to improve user experience and refine application features based on user feedback.

Downloads

Download data is not yet available.

References

J. Huang, "Analysis of Airline Tweets Using Support Vector Machines," Journal of Transportation Research, vol. 22, no. 3, pp. 45-56, 2023.

Cahyo, A., Nugroho, B., and Sudirman, T., "Sentiment Analysis of IMDb Movie Reviews Using TF-IDF and SVM," Journal of Data Science, vol. 15, no. 1, pp. 34-42, 2023.

Benarafa, A., Rahman, F., and Lee, S., "Addressing Overfitting and Underfitting in Sentiment Analysis with WordNet Integration," Journal of Computational Linguistics, vol. 28, no. 2, pp. 123-135, 2023.

R. Hokijuliandy, Pratama, D., and Aditya, M., "Improving Sentiment Analysis of Mobile JKN Application Reviews Using Chi-Square Feature Selection and SVM," Journal of Health Informatics, vol. 10, no. 4, pp. 89-98, 2023.

R. Driyani, "Sentiment Analysis of Mobile Reviews on Twitter Using SVM with RBF Kernel," Journal of Social Media Studies, vol. 12, no. 2, pp. 200-215, 2021.

N. Obiedat, Alharbi, K., and Zhang, L., "Hybrid Approaches to Addressing Imbalanced Datasets in Sentiment Analysis," Journal of Artificial Intelligence Research, vol. 35, no. 5, pp. 67-78, 2022.

Putra, A., Wibowo, H., and Kusuma, F., "Enhancing Sentiment Analysis with SentiWordNet and SVM: A Hybrid Approach," Journal of Language Technology, vol. 18, no. 3, pp. 155-169, 2021.

Smith, D., "Machine Learning Techniques for Sentiment Analysis," International Journal of Data Science, vol. 20, no. 4, pp. 110-120, 2022.

Jones, T., "Text Mining and Sentiment Analysis with SVM and LDA," Journal of Information Technology, vol. 14, no. 2, pp. 85-95, 2021.

Lee, H., "Improving Sentiment Classification with Hybrid Models," Journal of Computational Intelligence, vol. 25, no. 3, pp. 99-108, 2022.

Williams, K., "Sentiment Analysis Using Advanced Machine Learning Techniques," Journal of Artificial Intelligence and Robotics, vol. 27, no. 1, pp. 60-70, 2023.

Brown, P., "Evaluating the Effectiveness of Sentiment Analysis Models," Journal of Data Mining and Knowledge Discovery, vol. 30, no. 2, pp. 130-140, 2021.

Kim, S., "Challenges and Solutions in Sentiment Analysis," Journal of Machine Learning Research, vol. 22, no. 5, pp. 145-155, 2023.

Ali, M., "A Comparative Study of Machine Learning Algorithms for Sentiment Analysis," Journal of Big Data Analytics, vol. 17, no. 3, pp. 75-85, 2022.

Patel, R., "Using SVM and LDA for Sentiment Analysis in Social Media," Journal of Social Network Analysis, vol. 19, no. 4, pp. 205-215, 2021.

Green, J., "Web Scraping Techniques for Data Collection in Sentiment Analysis," Journal of Data Engineering, vol. 10, no. 2, pp. 89-102, 2022.

Zhang, Y., "Cross-Validation Techniques for Machine Learning Models," Journal of Computational Statistics, vol. 28, no. 3, pp. 110-122, 2023.

Lin, J., "Latent Dirichlet Allocation for Topic Modeling in Reviews," Journal of Text Analytics, vol. 15, no. 1, pp. 45-60, 2023.

Zhao, F., "Evaluating Coherence in Topic Modeling with LDA," Journal of Machine Learning Techniques, vol. 18, no. 4, pp. 75-88, 2021.

Torres, M., "Handling Imbalanced Datasets in Sentiment Analysis," Journal of Advanced Data Analytics, vol. 14, no. 2, pp. 50-65, 2022.


Bila bermanfaat silahkan share artikel ini

Berikan Komentar Anda terhadap artikel Analisis Sentimen dan Pemodelan Topik pada Ulasan Pengguna Aplikasi myIM3 Menggunakan Support Vector Machine dan Latent Dirichlet Allocation

Dimensions Badge
Article History
Submitted: 2024-11-14
Published: 2024-12-18
Abstract View: 45 times
PDF Download: 52 times
How to Cite
Prastyo, P., Berlilana, B., & Tahyudin, I. (2024). Analisis Sentimen dan Pemodelan Topik pada Ulasan Pengguna Aplikasi myIM3 Menggunakan Support Vector Machine dan Latent Dirichlet Allocation. Building of Informatics, Technology and Science (BITS), 6(3), 1618-1626. https://doi.org/10.47065/bits.v6i3.6268
Issue
Section
Articles