Comparison of XGBoost and LSTM in Knowledge Discovery for GrokAI Mobile Application Sentiment Analysis
- Aliyananda Risyahputri Universitas Sriwijaya, Palembang, Indonesia
-
Dedy Kurniawan
*
Universitas Sriwijaya, Palembang,
Indonesia
- Ken Ditha Tania Universitas Sriwijaya, Palembang, Indonesia (*) Corresponding Author
Abstract
Generative AI has provided real benefits in key sectors of the public sector. However, the rapid expansion of AI assistant services also raises concerns about whether newly released products can consistently meet user expectations, especially as negative experiences are increasingly expressed through public reviews. Its positive impacts encourage competitive rivalry among AI assistant product developers, including xAI, which also participates by formulating the Grok AI application. As a relatively new product with over 50 million downloads, GrokAI needs to perform an evaluation to maintain its competitiveness. This condition leads to the research goal of analyzing user sentiment toward GrokAI application through reviews on Google Play Store and comparing the performance of Machine Learning and Deep Learning classification models within the framework of Knowledge Discovery in Databases (KDD). This study uses 11,108 review data classified using the VADER Lexicon method, resulting in 7,633 positive reviews and 3,475 negative reviews. The data is then tested on XGBoost (Extreme Gradient Boosting) and LSTM (Long-Short Term Memory) models. The results show that the XGBoost model performs slightly better with an accuracy of 87.22%, compared to LSTM, which reaches 86.58%. However, both models exhibit significant performance disparities in classifying negative classes due to the extreme difference in data quantity. The knowledge discovery process reveals that the majority of positive sentiment appreciates the free access and general functions of the application. Meanwhile, negative sentiment focuses on complaints related to response time, output quality, and specific features such as image and voice. The main recommendation is to maintain the advantage of free access also improve features and processing logic to sustain loyalty and service quality. Future research is suggested to test models with more balanced data and optimize dataset cleaning to improve accuracy in minority classes.
Downloads
References
V. Corvello, “Generative AI and the future of innovation management: A human centered perspective and an agenda for future research,” Journal of Open Innovation: Technology, Market, and Complexity, vol. 11, no. 1, p. 100456, 2025, doi: https://doi.org/10.1016/j.joitmc.2024.100456.
M. Albashrawi, “Generative AI for decision-making: A multidisciplinary perspective,” Journal of Innovation & Knowledge, vol. 10, no. 4, p. 100751, 2025, doi: https://doi.org/10.1016/j.jik.2025.100751.
S. Noy and W. Zhang, “Experimental evidence on the productivity effects of generative artificial intelligence,” Science (1979), vol. 381, no. 6654, pp. 187–192, 2023, doi: 10.1126/science.adh2586.
E. Brynjolfsson, D. Li, and L. Raymond, “Generative AI at Work*,” Q J Econ, vol. 140, no. 2, pp. 889–942, May 2025, doi: 10.1093/qje/qjae044.
M.-T. Huynh and T. Aichner, “In generative artificial intelligence we trust: unpacking determinants and outcomes for cognitive trust,” AI Soc, 2025, doi: 10.1007/s00146-025-02378-8.
M. Shukla, I. Goyal, B. Gupta, and J. Sharma, “A Comparative Study of ChatGPT, Gemini, and Perplexity,” International Journal of Innovative Research in Computer Science and Technology, vol. 12, pp. 10–15, Oct. 2024, doi: 10.55524/ijircst.2024.12.4.2.
K. Wangsa, S. Karim, E. Gide, and M. Elkhodr, “A Systematic Review and Comprehensive Analysis of Pioneering AI Chatbot Models from Education to Healthcare: ChatGPT, Bard, Llama, Ernie and Grok,” Future Internet, vol. 16, no. 7, 2024, doi: 10.3390/fi16070219.
U. Samet, “The positive influence of large language models on fact-checking practices: A case study of Grok,” World Journal of Advanced Engineering Technology and Sciences, vol. 15, no. 3, pp. 1727–1738, 2025, doi: https://doi.org/10.30574/wjaets.2025.15.3.1123.
xAI, “Grok.” Accessed: Nov. 01, 2025. [Online]. Available: https://play.google.com/store/apps/details?id=ai.x.grok&hl=id
M. Vadla, M. Suresh, and V. Viswanathan, “Enhancing Product Design through AI-Driven Sentiment Analysis of Amazon Reviews Using BERT,” Algorithms, vol. 17, p. 59, Oct. 2024, doi: 10.3390/a17020059.
V. Novalia, K. D. Tania, A. Meiriza, and A. Wedhasmara, “Knowledge Discovery of Application Review Using Word Embedding’s Comparison with CNN-LSTM Model on Sentiment Analysis,” in 2024 International Conference on Electrical Engineering and Computer Science (ICECOS), IEEE, 2024, pp. 234–238. doi: https://doi.org/10.1109/ICECOS63900.2024.10791113.
C. Singh, T. Imam, S. Wibowo, and S. Grandhi, “A Deep Learning Approach for Sentiment Analysis of COVID-19 Reviews,” Applied Sciences, vol. 12, no. 8, 2022, doi: 10.3390/app12083709.
R. Kurniawan, H. Oktafia, and R. Aprisusanti, “Sentiment Analysis of Google Play Store User Reviews on Digital Population Identity App Using K- Nearest Neighbors,” Jurnal Sisfokom (Sistem Informasi dan Komputer), vol. 13, Oct. 2024, doi: 10.32736/sisfokom.v13i2.2071.
U. Kulsum, M. Jajuli, and N. Sulistiyowati, “Analisis Sentimen Aplikasi WETV di Google Play Store Menggunakan Algoritma Support Vector Machine,” Journal of Applied Informatics and Computing, vol. 6, pp. 205–212, Oct. 2022, doi: 10.30871/jaic.v6i2.4802.
E. Damayanti, A. V. Vitianingsih, S. Kacung, H. Suhartoyo, and A. Lidya Maukar, “Sentiment Analysis of Alfagift Application User Reviews Using Long Short-Term Memory (LSTM) and Support Vector Machine (SVM) Methods,” Decode: Jurnal Pendidikan Teknologi Informasi, vol. 4, no. 2, pp. 509–521, Jun. 2024, doi: 10.51454/decode.v4i2.478.
M. J. Setiawan and V. R. S. Nastiti, “DANA App Sentiment Analysis: Comparison of XGBoost, SVM, and Extra Trees,” Jurnal Sisfokom (Sistem Informasi dan Komputer), 2024, doi: https://doi.org/10.32736/sisfokom.v13i3.2239.
V. Prasetyo, M. Naufal, and K. Wijaya, “Sentiment Analysis of ChatGPT on Indonesian Text using Hybrid CNN and Bi-LSTM,” Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), vol. 9, pp. 327–333, Apr. 2025, doi: 10.29207/resti.v9i2.6334.
N. Widaad and D. Anggraini, “SENTIMENT ANALYSIS OF CHATGPT APP USER REVIEWS USING SVM AND CNN METHODS,” Jurnal Teknik Informatika (Jutif), 2024, doi: https://doi.org/10.52436/1.jutif.2024.5.6.4010.
C. A. Palacios, J. A. Reyes-Suárez, L. A. Bearzotti, V. Leiva, and C. Marchant, “Knowledge Discovery for Higher Education Student Retention Based on Data Mining: Machine Learning Algorithms and Case Study in Chile,” Entropy, vol. 23, no. 4, 2021, doi: 10.3390/e23040485.
Y. Singgalen, S. Wahyuningtyas, E. Widodo, M. Dasra, and R. Setiawan, “KNOWLEDGE DISCOVERY IN DATABASES FOR HOTEL SERVICE QUALITY IMPROVEMENT THROUGH DATA- MINING APPROACH,” J Theor Appl Inf Technol, vol. 102, pp. 9004–9020, Dec. 2024.
A. Dogan and D. Birant, “Machine learning and data mining in manufacturing,” Expert Syst Appl, vol. 166, p. 114060, 2021, doi: https://doi.org/10.1016/j.eswa.2020.114060.
Heri Suroyo and E. J. Pratama, “Comparison of Text Representation Methods for Sentiment Analysis Using Support Vector Machine,” Journal of Advances in Information and Industrial Technology, vol. 7, no. 1, pp. 21–30, May 2025, doi: 10.52435/jaiit.v7i1.610.
V. Çetin and O. Yıldız, “A comprehensive review on data preprocessing techniques in data analysis,” Pamukkale Üniversitesi Mühendislik Bilimleri Dergisi, vol. 28, no. 2, pp. 299–312, 2022, doi: doi:10.5505/pajes.2021.62687.
H.-T. Duong and T.-A. Nguyen-Thi, “A review: preprocessing techniques and data augmentation for sentiment analysis,” Comput Soc Netw, vol. 8, no. 1, p. 1, 2021, doi: 10.1186/s40649-020-00080-x.
A. Kukkar, R. Mohana, A. Sharma, A. Nayyar, and M. Shah, “Improving Sentiment Analysis in Social Media by Handling Lengthened Words,” IEEE Access, vol. 11, pp. 9775–9788, Jan. 2023, doi: 10.1109/ACCESS.2023.3238366.
A. Majid, D. Nugraha, and F. Adhinata, “Sentiment Analysis on Tiktok Application Reviews Using Natural Language Processing Approach,” Journal of Embedded Systems, Security and Intelligent Systems, pp. 32–38, Aug. 2023, doi: 10.59562/jessi.v4i1.471.
J. Fehle, T. Schmidt, and C. Wolff, “Lexicon-based Sentiment Analysis in German: Systematic Evaluation of Resources and Preprocessing Techniques,” in Conference on Natural Language Processing, 2021. doi: 10.5283/epub.50833.
S. Biswas, K. Young, and J. Griffith, A Comparison of Automatic Labelling Approaches for Sentiment Analysis. 2022. doi: 10.5220/0011265900003269.
S. Tzimiris, S. Nikiforos, M. N. Nikiforos, D. Mouratidis, and K. L. Kermanidis, “A Comparative Evaluation of Transformer-Based Language Models for Topic-Based Sentiment Analysis,” Electronics (Basel), vol. 14, no. 15, 2025, doi: 10.3390/electronics14152957.
V. Nurcahyawati, Z. Mustaffa, and M. Khalaf, “Exceeding Manual Labeling: VADER Lexicon as an Accurate Alternative to Automatic Sentiment Classification,” The International Arab Journal of Information Technology, vol. 22, Jan. 2025, doi: 10.34028/iajit/22/2/2.
M. Arief and N. A. Samsudin, “Hybrid Approach with VADER and Multinomial Logistic Regression for Multiclass Sentiment Analysis in Online Customer Review,” International Journal of Advanced Computer Science and Applications, vol. 14, no. 12, 2023, doi: 10.14569/IJACSA.2023.0141232.
I. Aggarwal, S. Joseph, N. Jaganathan, A. Patel, V. Kumar, and M. Devarapalli, “Sentiment Analysis in Healthcare: A Comparison of VADER, BERT, and Flair NLP Models on Patient Reviews of Pain Management Physicians,” Cureus, vol. 17, Jul. 2025, doi: 10.7759/cureus.88902.
R. Wati, S. Ernawati, and H. Rachmi, “Pembobotan TF-IDF Menggunakan Naïve Bayes pada Sentimen Masyarakat Mengenai Isu Kenaikan BIPIH,” Jurnal Manajemen Informatika (JAMIKA), vol. 13, no. 1, pp. 84–93, Apr. 2023, doi: 10.34010/jamika.v13i1.9424.
A. Erkan and T. Gungor, “Analysis of Deep Learning Model Combinations and Tokenization Approaches in Sentiment Classification,” IEEE Access, vol. PP, p. 1, Jan. 2023, doi: 10.1109/ACCESS.2023.3337354.
A. Samih, A. Ghadi, and A. Fennan, “Enhanced sentiment analysis based on improved word embeddings and XGboost,” International Journal of Electrical and Computer Engineering, vol. 13, no. 2, pp. 1827–1836, 2023, doi: http://doi.org/10.11591/ijece.v13i2.pp1827-1836.
G. S. N. Murthy, S. R. Allu, B. Andhavarapu, M. Bagadi, and M. Belusonti, “Text based sentiment analysis using LSTM,” Int. J. Eng. Res. Tech. Res, vol. 9, no. 05, pp. 32–41, 2020, doi: https://doi.org/10.17577/IJERTV9IS050290.
F. Horasan and B. Bilen, “LSTM Network based Sentiment Analysis for Customer Reviews,” Politeknik Dergisi, vol. 25, no. 3, pp. 959–966, 2022, doi: 10.2339/politeknik.844019.
W. A. Wily, S. Anggai, and T. Tukiyat, “ANALISIS SENTIMEN ULASAN PENGGUNA APLIKASI MEDIA SOSIAL X DI PLAY STORE MENGGUNAKAN ALGORITMA LONG SHORT-TERM MEMORY (LSTM) DAN GATED RECURRENT UNIT (GRU): Studi Kasus pada Ulasan Pengguna di Google Play Store,” Jurnal SISKOM-KB (Sistem Komputer dan Kecerdasan Buatan), vol. 9, no. 1, pp. 63–72, 2025, doi: https://doi.org/10.47970/siskom-kb.v9i1.875.
Y. A. Pradana, I. Cholissodin, and D. Kurnianingtyas, “Analisis sentimen pemindahan ibu kota Indonesia pada media sosial Twitter menggunakan metode LSTM dan Word2Vec,” Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer, vol. 7, no. 5, pp. 2389–2397, 2023.
X. Wen and W. Li, “Time series prediction based on LSTM-attention-LSTM model,” IEEE access, vol. 11, pp. 48322–48331, 2023, doi: https://doi.org/10.1109/ACCESS.2023.3276628.
S. Lonang, A. Yudhana, and M. K. Biddinika, “Analisis Komparatif Kinerja Algoritma Machine Learning untuk Deteksi Stunting,” J. Media Inform. Budidarma, vol. 7, no. 4, p. 2109, 2023, doi: http://dx.doi.org/10.30865/mib.v7i3.6368.
A. Bagheri, S. Taghvaeian, and D. Delen, “A text analytics model for agricultural knowledge discovery and sustainable food production: A case study from Oklahoma Panhandle,” Decision Analytics Journal, vol. 9, p. 100350, 2023, doi: https://doi.org/10.1016/j.dajour.2023.100350.
M. Pratiwi and K. Tania, “Knowledge Discovery Through Topic Modeling on GoPartner User Reviews Using BERTopic, LDA, and NMFKnowledge Discovery Melalui Pemodelan Topik pada Ulasan Pengguna Aplikasi GoPartner Menggunakan BERTopic, LDA, dan NMF,” Journal of Applied Informatics and Computing, vol. 9, pp. 1–7, Jan. 2025, doi: 10.30871/jaic.v9i1.8782.
N. A. Sofiah, K. D. Tania, A. Meiriza, and A. Wedhasmara, “A Comparative Assessment SARIMA and LSTM Models for the Gurugram Air Quality Index’s Knowledge Discovery,” in 2024 International Conference on Electrical Engineering and Computer Science (ICECOS), 2024, pp. 26–31. doi: 10.1109/ICECOS63900.2024.10791243.
S. A. Putri, K. Ditha Tania, N. Kawadha, and P. Gumay, “Knowledge Discovery Through Sentiment Analysis and Topic Modeling of BCA Mobile and MyBCA,” Journal of Mathematics, Computations, and Statistics, vol. 8, no. 2, pp. 669–682, 2025, doi: 10.35580/jmathcos.v8i2.9782.
J. Zhou, Z. Liang, Y. Fang, and Z. Zhou, “Exploring public response to ChatGPT with sentiment analysis and knowledge mapping,” IEEE Access, vol. 12, pp. 50504–50516, 2024, doi: https://doi.org/10.1109/ACCESS.2024.3386362.
E. H. Lobo et al., “Detecting user experience issues from mHealth apps that support stroke caregiver needs: an analysis of user reviews,” Front Public Health, vol. 11, p. 1027667, 2023.
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel Comparison of XGBoost and LSTM in Knowledge Discovery for GrokAI Mobile Application Sentiment Analysis
Pages: 1637-1648
Copyright (c) 2025 Aliyananda Risyahputri, Dedy Kurniawan, Ken Ditha Tania
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution 4.0 International License 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 (Refer to The Effect of Open Access).
