Claim Missing Document
Check
Articles

SMOTE and BERT Approaches for Handling Class Imbalance in Sentiment Analysis of the CoreTax Application on Big Data Ginting, Meiliyani Br; Surbakti, Asprina Br; Ilham, Safarul; Utomo, Dito Putro; Ginting, Raheliya Br
Building of Informatics, Technology and Science (BITS) Vol 7 No 2 (2025): September 2025
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i2.8310

Abstract

Coretax is a tax information system developed by the Directorate General of Taxes (DJP) to support digital and integrated tax administration processes, covering everything from taxpayer registration to reporting and auditing. Although it was designed to improve efficiency, transparency, and accuracy in tax management, its implementation has sparked mixed reactions among the public due to various technical challenges and the complexity of the annual tax reporting process. This situation highlights the need for a sentiment analysis that can objectively capture public perceptions of the system’s performance. In this study, Natural Language Processing (NLP) and Machine Learning techniques were applied to analyze 3,000 tweets from Twitter (X) related to Coretax. One of the main issues identified in the dataset is class imbalance, where positive sentiments significantly outnumber negative and neutral ones, leading to biased classification results. To address this issue, the Synthetic Minority Over-sampling Technique (SMOTE) was used to balance the dataset by generating synthetic samples for the minority classes. The BERT model was then employed for sentiment classification because of its strong ability to understand contextual meaning through its transformer-based architecture. Experimental results show that before applying SMOTE, the BERT model achieved an accuracy of 77%, which increased to 80% after SMOTE was implemented, along with improvements in precision, recall, and F1-score, particularly for the minority classes. These findings demonstrate that the combination of SMOTE and BERT significantly enhances the performance of sentiment analysis in understanding public responses to Coretax. This approach can serve as a valuable reference for evaluating and improving tax digitalization policies, ensuring they are more effective, inclusive, and responsive to public needs.
Co-Authors A M Hatuaon Sihite Abdul Karim Ade Ambarwati Br Ginting Aminuddin Aziz Annisa Apriliani Annisa Fadillah Siregar Annisah Annisah Asprina Br Surbakti, Asprina Br Atira Nabila Azlan, Azlan Bernadus Gunawan Sudarsono Bister Purba Boby Septia Pranata Br Ginting, Raheliya Butar Butar, Roi Martin Cici Alfiani Pradika Dita Dewi Maulida Sari Tanjung Dwi Asdini Efori Buulolo Eka Pratiwi Sumantri Faisal Amir Feby Ronauli Lubis, Eka Fince Tinus Waruwu Firman Telaumbanua Ginting, Winda Widia Br Guidio Leonarde Ginting Guidio Leonarde Ginting Hasibuan, Nelly Astuty Hendrikus Daely Ida Rizky Nasution Ihsan Ihsan Ilham Mubarik Ilham, Safarul Imam Saputra Imam Saputra Indini, Dwina Pri Irfan Nainggolan Iskandar Zulkarnain Johanes Mario Purba Keke Annisa Siregar Kurnia Ulfa M Mesran Manik, Lastri Meiliyani Br Ginting, Meiliyani Br Mesran, Mesran Miftahul Khairat Miko Putra Haposan Tinambunan Muhammad Syahrizal Murdani Murdani, Murdani Nainggolan, Dian Wichita Nainggolan, Laksono Nasib Marbun Nasib Sihombing Nastiti, Sindy Nelly Astuti Hasibuan Nona Oktari Noveriang Ndruru Novida Sari, Sri Nurjannah Oktari, Nona Pitriani Piliang Purba, Andrean Saputra Purba, Bister Purba, Roulina Agape Radius Kharisman Ndruru Raheliya Br Ginting, Raheliya Br Rahmi Danur, Surizar Rama Prameswara Ritonga Refika Ratna Dilla Rian Syahputra Rivalri Kristianto Hondro Rizqi Dwikunti Siregar, Dini Roni Yunis Russy Amelia Samueal Damanik Santri W Pasaribu Saragi, Naomi Labora Saragih, Soumi Rohmah Sarumaha, Lukas Sarwandi Wandi Sawitri Sawitri Selly Armasari Sihotang, Dahner Ismanda Bertenius Simatupang, Meylita Putri Sirait, Pahala Siregar, Tesa Aurelia Sitepu, Harun Rivaldo Soeb Aripin Suginam Suharti Suharti Sulistianingsih, Indri Surya Darma Nasution Susi Mardiana Giawa Sussolaikah, Kelik Tesa Aurelia Siregar Ulva Rizky Amanda Virdyra Tasril Yohana Br Ginting, Dewi Zahri Hubby Ramadhani