Proceedings of the International Conference on Communication and New Media Studies (COMNEWS 2025)

<Previous Article In Volume
Next Article In Volume>

Sentiment Analysis of Tiktok and Instagram Comments Using a Context-Aware, Multilingual Web Tool

Authors
Rosalina Rosalina1, *, Abdurrahman Khairi1, Filbert Meliala1, Jason Anthony Wibowo1, Sarah Kimberly Fischer1, Williem Williem1
1President University, Bekasi, Indonesia
*Corresponding author. Email: rosalina@president.ac.id
Corresponding Author
Rosalina Rosalina
Available Online 30 April 2026.
DOI
10.2991/978-2-38476-573-7_2How to use a DOI?
Keywords
Sentiment analysis; TikTok; Instagram; Natural Language Processing; Social Media; Gemini 2.0
Abstract

This study presents a context-aware sentiment analysis system developed to address the challenges of analyzing user-generated comments on Instagram and TikTok. These platforms are major digital engagement tools in Indonesia, yet their high volume of informal, emoji-rich, and multilingual content makes manual sentiment interpretation impractical. To address this, we developed a web-based application that utilizes Gemini 2.0 Flash, a state-of-the-art natural language model, integrated with FastAPI and ReactJS, to classify sentiments in comments with contextual awareness. The system also incorporates emoji interpretation and supports Bahasa Indonesia and English. Performance evaluation on 2,000 real-world comments showed 87.2% accuracy, surpassing traditional tools such as VADER. This tool enables brands and influencers to make data-driven decisions by exporting sentiment trends in real time. Challenges include slang interpretation, API rate limitations, and short-comment ambiguity. Future enhancements include video transcription and regional dialect support.

Copyright
© 2026 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

<Previous Article In Volume
Next Article In Volume>
Volume Title
Proceedings of the International Conference on Communication and New Media Studies (COMNEWS 2025)
Series
Advances in Social Science, Education and Humanities Research
Publication Date
30 April 2026
ISBN
978-2-38476-573-7
ISSN
2352-5398
DOI
10.2991/978-2-38476-573-7_2How to use a DOI?
Copyright
© 2026 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

risenwbib
TY  - CONF
AU  - Rosalina Rosalina
AU  - Abdurrahman Khairi
AU  - Filbert Meliala
AU  - Jason Anthony Wibowo
AU  - Sarah Kimberly Fischer
AU  - Williem Williem
PY  - 2026
DA  - 2026/04/30
TI  - Sentiment Analysis of Tiktok and Instagram Comments Using a Context-Aware, Multilingual Web Tool
BT  - Proceedings of the International Conference on Communication and New Media Studies (COMNEWS 2025)
PB  - Atlantis Press
SP  - 4
EP  - 13
SN  - 2352-5398
UR  - https://doi.org/10.2991/978-2-38476-573-7_2
DO  - 10.2991/978-2-38476-573-7_2
ID  - Rosalina2026
ER  -