Teachers in the Digital Age: Sentiment Analysis of the Merdeka Mengajar Platform in the Indonesian Curriculum Policy

Abstract

Introduction: The Platform Merdeka Mengajar (PMM) was launched on February 11, 2022, as a digital tool to support the implementation of the Merdeka Curriculum in Indonesia. The platform provides teachers with references, learning materials, and professional development resources. Despite its intended benefits, user reviews on the PMM application vary, with both positive and negative feedback reflected in star ratings and comments. Understanding these sentiments is crucial for improving the platform’s effectiveness and ensuring better adoption by educators.

Objectives: The Platform Merdeka Mengajar (PMM) was launched on February 11, 2022, as a digital tool to support the implementation of the Merdeka Curriculum in Indonesia. The platform provides teachers with references, learning materials, and professional development resources. Despite its intended benefits, user reviews on the PMM application vary, with both positive and negative feedback reflected in star ratings and comments. Understanding these sentiments is crucial for improving the platform’s effectiveness and ensuring better adoption by educators.

Methods: This study employs a quantitative approach, analyzing 8,581 user reviews from Google Play. The dataset is processed using Orange 3 software, incorporating text preprocessing, sentiment classification, and emotion analysis. Three machine learning models—Naïve Bayes, Neural Networks, and Linear Regression—are compared for classification performance, evaluated through accuracy, precision, recall, and F1-score metrics.

Results: Findings indicate that 89.55% of reviews are positive, with joy (35.92%) and trust (33.31%) being the most frequently expressed emotions. Negative sentiment accounts for 5.21%, primarily due to performance-related issues. Public opinion analysis reveals that users appreciate the platform’s content and usability, while technical challenges remain a concern. The Naïve Bayes model achieved an accuracy of 84.2%, demonstrating its effectiveness in sentiment classification.

Conclusions: This research contributes to the growing body of literature on educational technology adoption in Indonesia by employing big data sentiment analysis. It provides empirical evidence on user perceptions, offering valuable recommendations for digital transformation in education.