A Comparative Analysis of Explainable AI Techniques for Sentiment Classification of TikTok & Tokopedia Reviews
DOI:
https://doi.org/10.25139/inform.v10i2.10748Keywords:
Sentiment Analysis, Explainable AI Lime, Decision Tree, K-Nearest Neighbors, E-Commerce, Random ForestAbstract
Explainable Artificial Intelligence (XAI) using the LIME (Local Interpretable Model-Agnostic Explanations) method to enhance the interpretability of sentiment classification for user reviews on TikTok and Tokopedia. Using TF-IDF for feature extraction, three machine learning classifiers —Random Forest, Decision Tree, and K-Nearest Neighbours—were evaluated through K-Fold Cross-Validation. Random Forest achieved the highest classification accuracy at 89.9%, followed by Decision Tree at 88.25%, and KNN at 81.51%. The most prominent terms in positive sentiment reviews included “mantap” (16,057.23) and “bagus” (15,310.02), while negative sentiment was associated with “biaya,” “sistem,” and “ganti.” LIME provided localized, interpretable insights by highlighting the important terms that influence each prediction. In terms of positive sentiment, words such as “Tokopedia,” “update,” and “go” had strong weights, whereas negative classifications were triggered by terms like “offline” and “error.” ROC Curve analysis further confirmed Random Forest’s strong performance, showing AUC scores of 0.88 for the negative class, 0.87 for the neutral class, and 0.88 for the positive class, outperforming the other models. The network graph also identified “Tokopedia” as a central node, with frequent co-occurrence of terms like “diskon” and “pengiriman,” reflecting key user expectations. These findings demonstrate that combining interpretable AI with high-performing classifiers offers a powerful approach for sentiment analysis in digital platforms. It enables stakeholders to understand user feedback better and make data-driven decisions to improve customer satisfaction and trust.
References
A. Dzulkarnain, B. Rahmy Lidiawaty, S. Hidayati, R. Andi Hidayah, and A. Pramesta Setyaningtitah, “Sentiment Analysis of Student Complaint Text for Finding Context,” Inform : Jurnal Ilmiah Bidang Teknologi Informasi dan Komunikasi, vol. 9, no. 2, pp. 121–125, Jun. 2024, doi: 10.25139/inform.v9i2.7743.
E. Yoshua and W. Maharani, “Depression Detection of Users in Social-Media Twitter Using Decision Tree with Word2Vec,” Inform : Jurnal Ilmiah Bidang Teknologi Informasi dan Komunikasi, vol. 9, no. 1, pp. 95–100, Feb. 2024, doi: 10.25139/inform.v9i1.7617.
M. R. Adi Nugraha and Y. Sibaroni, “Classification of Depression Expressions on Twitter Using Ensemble Learning with Word2Vec,” Inform : Jurnal Ilmiah Bidang Teknologi Informasi dan Komunikasi, vol. 9, no. 1, pp. 67–74, Jan. 2024, doi: 10.25139/inform.v9i1.7559.
M. Rusdi Rahman, A. Febri Diansyah, and H. Hanafi, “Sentiment Analysis on the Shopee Application on Playstore Using the Random Forest Classification Method,” Inform : Jurnal Ilmiah Bidang Teknologi Informasi dan Komunikasi, vol. 9, no. 1, pp. 20–24, Nov. 2023, doi: 10.25139/inform.v9i1.5465.
A. R. Putra and D. E. Ratnawati, “Analisis Sentimen Berbasis Aspek pada Aplikasi Mobile Menggunakan Naïve Bayes berdasarkan Ulasan Pengguna Playstore (Studi Kasus : Jconnect Mobile),” Jurnal Teknologi Informasi dan Ilmu Komputer, vol. 12, no. 2, pp. 293–300, Apr. 2025, doi: 10.25126/jtiik.2025127556.
F. Istighfarizky, N. A. Sanjaya ER, I. M. Widiartha, L. G. Astuti, I. G. N. A. C. Putra, and I. K. G. Suhartana, “Klasifikasi Jurnal menggunakan Metode KNN dengan Mengimplementasikan Perbandingan Seleksi Fitur,” JELIKU (Jurnal Elektronik Ilmu Komputer Udayana), vol. 11, no. 1, p. 167, Jul. 2022, doi: 10.24843/jlk.2022.v11.i01.p18.
Yoga Religia, Agung Nugroho, and Wahyu Hadikristanto, “Klasifikasi Analisis Perbandingan Algoritma Optimasi pada Random Forest untuk Klasifikasi Data Bank Marketing,” Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), vol. 5, no. 1, pp. 187–192, Feb. 2021, doi: 10.29207/resti.v5i1.2813.
Riza Adrianti Supono and Muhammad Azis Suprayogi, “Perbandingan Metode TF-ABS dan TF-IDF Pada Klasifikasi Teks Helpdesk Menggunakan K-Nearest Neighbor,” Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), vol. 5, no. 5, pp. 911–918, Oct. 2021, doi: 10.29207/resti.v5i5.3403.
H. Nalatissifa, W. Gata, S. Diantika, and K. Nisa, “Perbandingan Kinerja Algoritma Klasifikasi Naive Bayes, Support Vector Machine (SVM), dan Random Forest untuk Prediksi Ketidakhadiran di Tempat Kerja,” Jurnal Informatika Universitas Pamulang, vol. 5, no. 4, p. 578, Dec. 2021, doi: 10.32493/informatika.v5i4.7575.
N. N. Marpid, Y. I. Kurniawan, and S. P. Rahayu, “Analysis Of The Movie Database Film Rating Prediction With Ensemble Learning Using Random Forest Regression Method,” Jurnal Teknik Informatika (Jutif), vol. 6, no. 1, pp. 1–10, Feb. 2025, doi: 10.52436/1.jutif.2025.6.1.1563.
D. R. K. Saputra, Y. V. Via, and A. N. Sihananto, “Deteksi Anomali Menggunakan Ensemble Learning Dan Random Oversampling Pada Penipuan Transaksi Keuangan,” Jurnal Informatika dan Teknik Elektro Terapan, vol. 12, no. 3, Aug. 2024, doi: 10.23960/jitet.v12i3.4910.
N. Charibaldi, A. Harfiani, and O. Samuel Simanjuntak, “Comparison of the Effect of Word Normalization on Naïve Bayes Classifier and K-Nearest Neighbor Methods for Sentiment Analysis,” Inform : Jurnal Ilmiah Bidang Teknologi Informasi dan Komunikasi, vol. 9, no. 1, pp. 25–31, Dec. 2023, doi: 10.25139/inform.v9i1.7111.
N. Rikatsih, M. Anshori, R. Siwi Pradini, and F. Faurika, “K-Nearest Neighbor Method for Early Detection of Diabetes Patients Based on Symptoms and Clinical Data,” Inform : Jurnal Ilmiah Bidang Teknologi Informasi dan Komunikasi, vol. 9, no. 2, pp. 187–193, Aug. 2024, doi: 10.25139/inform.v9i2.8582.
C. M. Tri Yunanda, M. Hanafi, and W. M. Pradnya Dhuhita, “Sentiment Analysis on TikTok Shop Reviews Using Long Short-Term Memory Method to Find Business Opportunity,” Inform : Jurnal Ilmiah Bidang Teknologi Informasi dan Komunikasi, vol. 9, no. 1, pp. 1–7, Sep. 2023, doi: 10.25139/inform.v9i1.6524.
A. Maghfiroh, Y. Findawati, and U. Indahyanti, “Klasifikasi Penipuan pada Rekening Bank menggunakan Pendekatan Ensemble Learning,” Building of Informatics, Technology and Science (BITS), vol. 4, no. 4, Mar. 2023, doi: 10.47065/bits.v4i4.3212.
A. Nugroho and Y. Religia, “Analisis Optimasi Algoritma Klasifikasi Naive Bayes menggunakan Genetic Algorithm dan Bagging,” Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), vol. 5, no. 3, pp. 504–510, Jun. 2021, doi: 10.29207/resti.v5i3.3067.
Yoga Religia, Agung Nugroho, and Wahyu Hadikristanto, “Klasifikasi Analisis Perbandingan Algoritma Optimasi pada Random Forest untuk Klasifikasi Data Bank Marketing,” Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), vol. 5, no. 1, pp. 187–192, Feb. 2021, doi: 10.29207/resti.v5i1.2813.
I. L. Kharisma, D. A. Septiani, A. Fergina, and K. Kamdan, “Penerapan Algoritma Decision Tree untuk Ulasan Aplikasi Vidio di Google Play,” Jurnal Nasional Teknologi dan Sistem Informasi, vol. 9, no. 2, pp. 218–226, Sep. 2023, doi: 10.25077/teknosi.v9i2.2023.218-226.
M. Reza, A. Dores, S. N. Ambo, and P. Meilina, “Perbandingan Metode Machine Learning Untuk Sentimen Analisis Review Penjualan Produk,” 2025.
R. Tsania, S. A. Putri, D. E. Ratnawati, and D. W. Brata, “Perbandingan Naïve Bayes dan K-Nearest Neighbor untuk Analisis Sentimen Aplikasi Gapura UB Berdasarkan Ulasan Pengguna pada Playstore,” 2023.
R. A. Khomeini Noor Bintang and N. T. Romadloni, “Perbandingan Kinerja Algoritma Klasifikasi Pada Review Pengguna Aplikasi Netflix,” Jurnal Informatika dan Teknik Elektro Terapan, vol. 13, no. 2, Apr. 2025, doi: 10.23960/jitet.v13i2.6303.
M. F. Y. Herjanto and C. Carudin, “Analisis Sentimen Ulasan Pengguna Aplikasi Sirekap Pada Play Store Menggunakan Algoritma Random Forest Classifer,” Jurnal Informatika dan Teknik Elektro Terapan, vol. 12, no. 2, Apr. 2024, doi: 10.23960/jitet.v12i2.4192.
N. B. Sidauruk, N. Riza, R. Nuraini, and S. Fatonah, “Penggunaan Metode Svm Dan Random Forest Untuk Analisis Sentimen Ulasan Pengguna Terhadap KAI Access Di Google Playstore,” 2023.
D. Saputro and D. Wahyu Utomo, “Rekomendasi Produk E-commerce Berbasis Klasifikasi Ulasan Menggunakan Ensemble Random Forest dan Teknik Boosting,” vol. 15, no. 02, 2024, doi: 10.35970/infotekmesin.v15i2.2315.
S. Syafrizal, M. Afdal, and R. Novita, “Analisis Sentimen Ulasan Aplikasi PLN Mobile Menggunakan Algoritma Naïve Bayes Classifier dan K-Nearest Neighbor,” MALCOM: Indonesian Journal of Machine Learning and Computer Science, vol. 4, no. 1, pp. 10–19, Dec. 2023, doi: 10.57152/malcom.v4i1.983.
M. Iqbal, A. Davy Wiranata, R. Suwito, and R. Faiz Ananda, “KLIK: Kajian Ilmiah Informatika dan Komputer Perbandingan Algoritma Naïve Bayes, KNN, dan Decision Tree terhadap Ulasan Aplikasi Threads dan Twitter,” Media Online, vol. 4, no. 3, pp. 1799–1807, 2023, doi: 10.30865/klik.v4i3.1402.
D. E. Sondakh, S. W. Taju, M. G. Tene, and A. E. T. Pangaila, “Sistem Analisis Sentimen Ulasan Aplikasi Belanja Online Menggunakan Metode Ensemble Learning Sentiment Analysis System for Online Shopping Application Reviews Using Ensemble Learning Method,” Cogito Smart Journal |, vol. 9, no. 2, 2023.
C. G. Indrayanto, D. E. Ratnawati, and B. Rahayudi, “Analisis Sentimen Data Ulasan Pengguna Aplikasi MyPertamina di Indonesia pada Google Play Store menggunakan Metode Random Forest,” 2023.
Downloads
Published
How to Cite
Issue
Section
License
Authors who publish with Inform: Jurnal Ilmiah Bidang Teknologi Informasi dan Komunikasi agree to the following terms:
-
Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (CC BY-SA 4.0) that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
-
Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
-
Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
