https://ejournal.uin-suka.ac.id/saintek/ijid <p>IJID (International Journal on Informatics for Development) is a biannual peer-reviewed journal published by the Faculty of Science and Technology, Universitas Islam Negeri (UIN) Sunan Kalijaga Yogyakarta, Indonesia, in June and December. The journal welcomes contributions of innovative and not previously published works in subjects covered by the Journal from scholars of related disciplines.</p> Faculty of Science and Technology, Universitas Islam Negeri (UIN) Sunan Kalijaga Yogyakarta en-US IJID (International Journal on Informatics for Development) 2252-7834 <a href="http://creativecommons.org/licenses/by-nc-nd/4.0/" rel="license"><img style="border-width: 0;" src="https://i.creativecommons.org/l/by-nc-nd/4.0/80x15.png" alt="Creative Commons License" /></a><br /><span>IJID (International Journal on Informatics for Development)</span> is licensed under a <a href="http://creativecommons.org/licenses/by-nc-nd/4.0/" rel="license">Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License</a> https://ejournal.uin-suka.ac.id/saintek/ijid/article/view/5195 <p><strong>This study proposes a hybrid feature selection approach that combines Pearson Correlation and Principal Component Analysis (PCA) to improve classification performance in opinion mining tasks. The rapid growth of e-commerce on social media platforms, such as TikTok, has generated a significant volume of user-generated reviews, which are valuable sources of consumer sentiment. However, the high dimensionality of textual data poses challenges in achieving accurate sentiment classification. To address this issue, the proposed method first applies Pearson Correlation to remove irrelevant features with weak correlation to sentiment labels, followed by PCA to reduce dimensionality. The dataset consists of user reviews from the TikTok Seller platform. Experiments using SVM, Naive Bayes, and Random Forest show that the hybrid approach achieves the highest accuracy of 86.2% (SVM and RF), improving over PCA-only by +0.9% and recovering 13.8% accuracy loss for Naive Bayes (from 72.0% to 83.1%). The results demonstrate that integrating correlation- and projection-based methods yields a more compact and effective feature set. This approach is especially suited for opinion mining in noisy, high-dimensional e-commerce data.</strong></p> Nova Tri Romadloni Wakhid Kurniawan Muhammad Yusuf Ariyadi Burhan Efendi Copyright (c) 2025 http://creativecommons.org/licenses/by-nc-nd/4.0 2025-11-18 2025-11-18 601 615