Emoji-Based Sentiment Classification Using Ensemble Learning with Cross-Validation: A Lightweight Approach for Social Media Analysis
Klasifikasi Sentimen Berbasis Emoji Menggunakan Ensemble Learning dengan Validasi Silang: Pendekatan Ringan untuk Analisis Media Sosial
DOI:
https://doi.org/10.25134/ilkom.v19i2.396Keywords:
Emoji Sentiment Analysis, Ensemble Learning, Voting Classifier, Cross-Validation, Social MediaAbstract
The increasing use of emojis in online communication reflects emotional expression that is often more immediate and intuitive than text. This study proposes a lightweight sentiment classification approach that utilizes only emoji features extracted from social media posts, without relying on textual content. The importance of this research lies in its relevance to short-form digital content, where textual sentiment cues are minimal or absent. To address the classification problem, we implement and compare multiple machine learning models including Random Forest (RF), Support Vector Machine, and an ensemble Voting Classifier combining both. Emoji tokens were vectorized using character-level count vectorization, and performance was evaluated using 5-fold cross-validation to ensure robustness and generalizability. Results show that the ensemble model achieved the highest average accuracy of 93.6%, outperforming the individual classifiers. These findings confirm that emojis alone can serve as reliable indicators of sentiment and support the deployment of fast, interpretable, and scalable models for social media sentiment analysis.
Downloads
References
[1] Q. A. Xu, C. Jayne, and V. Chang, “An emoji feature-incorporated multi-view deep learning for explainable sentiment classification of social media reviews,” Technol. Forecast. Soc. Change, vol. 202, p. 123326, 2024.
[2] N. Alamsyah, A. P. Kurniati, and others, “Airfare Fluctuation Analysis with Event and Sentiment Features by Stacking Ensemble Model,” in 2024 Ninth International Conference on Informatics and Computing (ICIC), IEEE, 2024, pp. 1–6.
[3] W. Erpurini, A. G. Putrada, N. Alamsyah, S. F. Pane, and M. N. Fauzan, “Confirmatory Factor Analysis for The Impact of Students’ Social Medial on University Digital Marketing,” in 2023 International Conference on Computer Science, Information Technology and Engineering (ICCoSITE), IEEE, 2023, pp. 615–620.
[4] J. Yu and C. Qi, “Machine Learning-Based Sentiment Analysis in English Literature: Using Deep Learning Models to Analyze Emotional and Thematic Content in Texts,” IEEE Access, 2025.
[5] C. M. Liapis, A. Karanikola, and S. Kotsiantis, “Enhancing sentiment analysis with distributional emotion embeddings,” Neurocomputing, vol. 634, p. 129822, 2025.
[6] R. Ahamad and K. N. Mishra, “Exploring sentiment analysis in handwritten and E-text documents using advanced machine learning techniques: a novel approach,” J. Big Data, vol. 12, no. 1, p. 11, 2025.
[7] S. Wang, Q. Liu, Y. Hu, and H. Liu, “Public Opinion Evolution Based on the Two-Dimensional Theory of Emotion and Top2Vec-RoBERTa,” Symmetry, vol. 17, no. 2, p. 190, 2025.
[8] Y. Shen et al., “The DeepMoji algorithm for fast and accurate classification of massive books based on emotion encoding with redefined weights in multihead attention,” in Third International Conference on Algorithms, Network, and Communication Technology (ICANCT 2024), SPIE, 2025, pp. 189–195.
[9] W. Fouda, A. Hegazy, N. M. Alnaqbi, E. Ozbilge, and E. Özbilge, “Enhancing educational environments with Social Media Feedback Evaluation Employing Hybrid Neutrosophic Decision Optimization (HNDO) and Neutrosophic Sentiment Fusion (NSF).,” Int. J. Neutrosophic Sci. IJNS, vol. 26, no. 1, 2025.
[10] N. Alamsyah, T. P. Yoga, B. Budiman, and others, “IMPROVING TRAFFIC DENSITY PREDICTION USING LSTM WITH PARAMETRIC ReLU (PReLU) ACTIVATION,” JITK J. Ilmu Pengetah. Dan Teknol. Komput., vol. 9, no. 2, pp. 154–160, 2024.
[11] S. Kusal, S. Patil, and K. Kotecha, “Multimodal text-emoji fusion using deep neural networks for text-based emotion detection in online communication,” J. Big Data, vol. 12, no. 1, pp. 1–25, 2025.
[12] P. M. Hancock, C. Hilverman, S. W. Cook, and K. M. Halvorson, “Emoji as gesture in digital communication: Emoji improve comprehension of indirect speech,” Psychon. Bull. Rev., vol. 31, no. 3, pp. 1335–1347, 2024.
[13] A. G. Putrada, N. Alamsyah, and M. N. Fauzan, “BERT for sentiment analysis on rotten tomatoes reviews,” in 2023 International Conference on Data Science and Its Applications (ICoDSA), IEEE, 2023, pp. 111–116.
[14] N. Alamsyah, A. P. Kurniati, and others, “Event Detection Optimization Through Stacking Ensemble and BERT Fine-tuning For Dynamic Pricing of Airline Tickets,” IEEE Access, 2024.
[15] N. Alamsyah and others, “Analisis Perbandingan Sentimen Pengguna Twitter Terhadap Layanan Salah Satu Provider Internet Di Indonesia Menggunakan Metode Klasifikasi,” TEMATIK, vol. 10, no. 2, pp. 246–251, 2023.
[16] N. Alamsyah, B. Budiman, R. Nursyanti, E. Setiana, and V. R. Danestiara, “Approximate Bayesian Inference for Bayesian Confidence Quantification in DNA Sequence Classification Using Monte Carlo Dropout Approach,” Innov. Innov. Res. Inform., vol. 7, no. 1, 2025.
[17] A. Khan, D. Majumdar, and B. Mondal, “Sentiment analysis of emoji fused reviews using machine learning and Bert,” Sci. Rep., vol. 15, no. 1, p. 7538, 2025.
[18] N. Alamsyah, V. R. Danestiara, B. Budiman, R. Nursyanti, E. Setiana, and A. Hendra, “OPTIMIZED FACEBOOK PROPHET FOR MPOX FORECASTING: ENHANCING PREDICTIVE ACCURACY WITH HYPERPARAMETER TUNING,” J. Techno Nusa Mandiri, vol. 22, no. 1, pp. 90–98, 2025.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Nur Alamsyah, Gunthur Bayu Wibisono, Titan Parama Yoga, Budiman, Acep Hendra
This work is licensed under a Creative Commons Attribution 4.0 International License.
