Article Per Year (5 Year)
p-Index From 2021 - 2026
2.94
P-Index
This Author published in this journals
All Journal JIP: Jurnal Ilmiah PGMI Jurnal PAJAR (Pendidikan dan Pengajaran) Pendas : Jurnah Ilmiah Pendidikan Dasar Jurnal Ilmiah Sultan Agung Jurnal Pendidikan Sultan Agung Nusantara Journal of Multidisciplinary Science IPSSJ Jurnal Cahaya Edukasi Prosiding Seminar Nasional Indonesia Journal of Computer Science and Technology Application
Yulina Ismiyanti
Unknown Affiliation
Religion Humanities Civil Engineering, Building, Construction & Architecture Computer Science & IT Economics, Econometrics & Finance Education Electrical & Electronics Engineering Environmental Science Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Mathematics Nursing Public Health Social Sciences Other

Published : 21 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search
Journal : Journal of Computer Science and Technology Application

 1 
Machine Learning Enabled Social Media Competitive Intelligence System Hendri Handoko; Yulina Ismiyanti; Omar Arif Al-Kamari
CORISINTA Vol 3 No 1 (2026): February
Publisher : Pandawan Sejahtera Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33050/480er062

Abstract

Social media platforms generate massive volumes of publicly accessible digital data that reflect organizational competitive strategies, yet most existing competitor analyses remain manual, descriptive, and limited to surface-level engagement metrics, resulting in low scalability and weak strategic intelligence. This study proposes a Machine Learning Enabled Social Media Competitive Intelligence System designed to automate competitor strategy extraction through artificial intelligence and big data analytics. The objective is to develop a computational framework capable of identifying strategic content patterns, communication objectives, audience positioning, and paid advertising behaviors using data-driven techniques. Large-scale public data from social media posts, engagement indicators, and advertising transparency libraries are collected and processed through data preprocessing pipelines, including text normalization, tokenization, and feature extraction using TF-IDF and word embedding representations. Supervised machine learning algorithms are implemented to classify content themes, detect strategic clusters, and model competitive positioning patterns, while performance evaluation is conducted using accuracy, precision, recall, and F1-score metrics to ensure robustness and reliability. Experimental findings demonstrate that the proposed system significantly enhances analytical consistency, scalability, and strategic insight generation compared to traditional mixed method approaches. This research contributes to the advancement of AI-driven social media analytics and establishes a computational foundation for scalable big data-based competitive intelligence systems aligned with Artificial Intelligence and Big Data domains.
Co-Authors Arif Dwi Prasetya Bela Fina Apriliya Citra Setya Hadining Y, Jupriyanto Dea Ayu Safitri Diana Isrianti Fara Khoirun Nisa' Fitri Setiyowati HENDRI HANDOKO Latifatun Nadya Lestari Nur Fitriani Mahendra, Andreas Linggar Muhamad Afandi Muhamad Masrur Muhammad Syafiul Maula Nida Hasanah Nur Khodijah Nuhyal Ulia, Nuhyal Nuyulul Wafa Omar Arif Al-kamari Rida Fironika Kusumadewi Sari Yustiana Shinta Ainun Nafisah Siti Istithoah Solihudin, Muhamad Sri Wahyuningsih Yunita Sari Zainal Abidin