Mira Afrina
Department of Information Systems, Faculty of Computer Science, Universitas Sriwijaya, South Sumatera, Indonesia

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

IndoBERTweet-Based Sentiment Analysis of AIESEC Indonesia's Instagram Comments for Brand Image Assessment An'nur Aisyah Ghaidah Senjaya Mangkunegara; Apriansyah Putra; Ken Ditha Tania; Mira Afrina
Brilliance: Research of Artificial Intelligence Vol. 6 No. 4 (2026): Brilliance: Research of Artificial Intelligence, Article Research November 2026
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v6i4.9805

Abstract

Social media platforms such as Instagram have become strategic channels through which organizations shape their brand image, and public comments on official accounts often reflect collective perceptions that are difficult to interpret manually because of their volume and informal language style. AIESEC Indonesia, the national chapter of the world's largest youth-run international non-governmental organization, relies heavily on its official Instagram account to communicate its leadership-development programs and cross-cultural exchange opportunities to Indonesian youth, yet no prior study has systematically examined how comment sentiment reflects the organization's brand image at the national level. This study aims to identify the sentiment tendencies of public comments on AIESEC Indonesia's Instagram posts, to evaluate the performance of IndoBERTweet in classifying these Indonesian-language comments through sentiment analysis, and to interpret the resulting sentiment distribution as a brand image indicator. A descriptive quantitative approach was applied, in which comments were collected through crawling, cleaned and normalized, manually labeled into positive, neutral, and negative categories, and classified using a fine-tuned IndoBERTweet model evaluated with accuracy, precision, recall, and F1-score. Results from 755 comments show 60.7% positive, 32.6% neutral, and 6.8% negative sentiment. IndoBERTweet achieved 83.3% accuracy and a 0.813 macro F1-score, outperforming the baseline by improving negative sentiment detection. Conclusively, AIESEC maintains a highly favorable brand image, and IndoBERTweet can effectively automate feedback monitoring. These findings are expected to provide an evidence-based understanding of public perception toward AIESEC Indonesia on social media.