Analysis of the Best Social Media Platforms for Promotion Using Machine Learning and RFE Feature Selection: A Comparative Study of Gradient Boosting, XGBoost, CNN, and SVR
DOI:
https://doi.org/10.30871/jaic.v10i1.12049Keywords:
Machine Learning, KDD, Social Media Promotion, CNN, Feature Selection RFEAbstract
This study aims to identify the most effective social media platforms for digital marketing. The use of social media for promotion continues to grow, yet many businesses still struggle to determine which platforms have the greatest impact. Therefore, this study compares the performance of various machine learning platforms to predict the best platform. The algorithms used are Gradient Boosting Regressor, XGBoost Regressor, Convolutional Neural Network (CNN), and Support Vector Regression (SVR) to estimate digital conversion potential based on user reviews, ad reach, and content trend patterns. A Knowledge Discovery in Databases (KDD) workflow is used to identify the most important key factors. This process includes data preprocessing, TF-IDF feature extraction, sentiment analysis, feature engineering, and feature elimination (RFE). The results showed that the CNN algorithm excelled in prediction, with the highest R² score of 0.74 and the lowest RMSE of 14.78. CNN predictions showed YouTube topping the list in terms of conversion potential, followed by Facebook and TikTok. These results highlight the higher promotional effectiveness of video-based platforms and the importance of machine learning in digital marketing decision-making. However, this study is limited by its reliance on static user review and ad reach data, which may not fully capture the dynamic changes of social media platforms.
Downloads
References
[1] W. Huang, “How Can a Brand Utilize Social Media to Achieve Impressive Promotion,” Commun. Humanit. Res., vol. 16, no. 1, pp. 116–120, 2023, doi: 10.54254/2753-7064/16/20230564.
[2] M. N. Najmi Nuji, A. Ali, W. N. Wan Noordin, B. A. N. Mohamed Thaheer, and V. Mathiew, “Of Trust and Influence: A Look At Social Media Influencers and Brand Promotion,” Int. J. Acad. Res. Bus. Soc. Sci., vol. 13, no. 6, pp. 2152–2170, 2023, doi: 10.6007/ijarbss/v13-i6/15444.
[3] N. S. Amdan et al., “Optimalisasi Pemanfaatan Media Sosial dalam Promosi Kampung Wisata Pekijing,” J. Pengabdi. Pada Masy., vol. 7, no. 1, pp. 72–79, 2022, doi: 10.30653/002.202271.26.
[4] M. Cinelli et al., “Promoting engagement with quality communication in social media,” PLoS One, vol. 17, no. 10 October, pp. 1–19, 2022, doi: 10.1371/journal.pone.0275534.
[5] J. Li, “A Study of Utilizing Social Media for Luxury Brand Promotion,” vol. 35, pp. 373–379, 2024.
[6] S. Jiang, “Social Media Health Promotion and Audience Engagement : The Roles of Information Dissemination , Organization-Audience Interaction , and Action Confidence Building Social Media Health Promotion and Audience Engagement : The Roles of Information Dissemination , Organization-Audience Interaction , and Action Confidence Building,” no. November, 2022, doi: 10.1080/10410236.2022.2150809.
[7] W. E. Kedi, C. Ejimuda, and C. Idemudia, “Machine learning software for optimizing SME social media marketing campaigns,” vol. 5, no. 7, pp. 1634–1647, 2024, doi: 10.51594/csitrj.v5i7.1349.
[8] N. C. Ramadhan, H. H. H, T. Rohana, and A. M. Siregar, “TIN : Terapan Informatika Nusantara Optimasi Algoritma Machine Learning Menggunakan Seleksi Fitur Xgboost Untuk Klasifikasi Kanker Payudara TIN : Terapan Informatika Nusantara,” vol. 5, no. 2, pp. 162–171, 2024, doi: 10.47065/tin.v5i2.5408.
[9] N. Sulistianingsih, S. Agrippina, A. Yusuf, F. N. Sari, and M. P. Juniarta, “JTIM : Jurnal Teknologi Informasi dan Multimedia Analisis Pengaruh Recursive Feature Elimination Terhadap Kinerja Model Prediksi Dini Diabetes Mellitus di RS PKU Muhammadiyah Bima,” vol. 7, no. 3, pp. 548–560, 2025.
[10] W. J. Ladeira, F. D. O. Santini, T. Rasul, S. Elhajjar, N. Yasin, and S. Akhtar, “Big data analytics and the use of artificial intelligence in the services industry : a meta- analysis,” vol. 2069, 2024, doi: 10.1080/02642069.2024.2374990.
[11] J. Lucas, J. M. Alvarez, S. Fidler, and M. T. Law, “Optimizing Data Collection for Machine Learning,” pp. 1–28.
[12] M. A. Palomino, “applied sciences Evaluating the Effectiveness of Text Pre-Processing in Sentiment Analysis,” 2022.
[13] R. Roshan, I. A. Bhacho, S. Zai, and I. Ahmad, “Comparative Analysis of TF – IDF and Hashing Vectorizer for Fake News Detection in Sindhi : A Machine Learning and Deep Learning Approach †,” 2023.
[14] A. M. Priyatno, T. Widiyaningtyas, I. Engineering, and U. N. Malang, “A Systematic Literature Review : Recursive Feature,” vol. 9, no. 2, pp. 196–207, 2024, doi: 10.33480/jitk.v9i2.5015.INTRODUCTION.
[15] R. Oktafiani, U. T. Yogyakarta, A. H. Hermawan, U. T. Yogyakarta, D. Avianto, and U. T. Yogyakarta, “Pengaruh Komposisi Split data Terhadap Performa Klasifikasi Penyakit Kanker Payudara Menggunakan Algoritma Machine Learning Pengaruh _ Komposisi _ Split _ Data _ Terhadap _ Performa _ Klasifikasi Penyakit _ Kanker _ Payudara _ Menggunakan Algoritma _ Machine _ Learning,” no. August, 2023, doi: 10.34128/jsi.v9i1.622.
[16] V. R. Joseph, “Optimal ratio for data splitting,” no. April, 2022, doi: 10.1002/sam.11583.
[17] A. Purnomo, A. G. Putrada, and R. Habibi, “MDI and PI XGBoost regression-based methods : regional best pricing prediction for logistics services,” vol. 22, no. 5, 2024, doi: 10.12928/TELKOMNIKA.v22i5.26037.
[18] M. Alam, I. M. Rafiqul, M. M. H. Sizan, and A. A. Akash, “The Integration of Machine Learning in information technologies: Future Trends and predictions,” pp. 75–84, doi: 10.32996/jcsts.
[19] K. He, Q. Yang, L. Ji, J. Pan, and Y. Zou, “Financial Time Series Forecasting with the Deep Learning Ensemble Model,” pp. 1–15, 2023.
[20] C. Yang, J. Shao, Y. Liu, P. Jou, and Y. Lin, “Application of Fuzzy-Based Support Vector Regression to Forecast of International Airport Freight Volumes,” pp. 1–18, 2022.
[21] E. Rizkiani and D. Brahma, “Perbandingan Performa Algoritma Metode Bagging dan Boosting pada Prediksi Konsentrasi PM 10 di Jakarta Utara,” vol. 01, pp. 74–81, 2024.
[22] M. A. Sembiring, F. W. Sembiring, and S. Informasi, “Analisa Kinerja Model Regresi Dalam Machine Learning,” vol. 8, no. 1, pp. 144–152, 2024.
[23] P. Karunia, D. R. Cahyaningrum, and E. Apriani, “Entrepreneurship and Tourism Digital Marketing ’ s Big Potential on Tiktok Platform : Users , Audiences , And Social Media Competitions Journal of Management , Entrepreneurship and Tourism,” vol. 3, no. 2, pp. 211–221, 2025.
[24] D. Rosalia, “Strategi Komunikasi Digital dalam Pemasaran: Studi Peran Media Sosial dalam Keputusan Pembelian Konsumen,” vol. 9, no. 2, pp. 488–499, 2025.
[25] D. Ardiyanto, “Komunikasi Promosi Di Era Digitalisasi,” vol. 4, pp. 4414–4421, 2025.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Maulina Putri, Aria Hendrawan
This work is licensed under a Creative Commons Attribution-ShareAlike 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 a Creative Commons Attribution License (Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) ) that allows others to share the work with an acknowledgement 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 acknowledgement 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 (See The Effect of Open Access).
