Evaluating Fasttext and Glove Embeddings for Sentiment Analysis of AI-Generated Ghibli-Style Images
Keywords:
Sentimen Analysis, Word Embedding, FastText, GloVe, Ghibli AIAbstract
The development of text-to-image generation technology based on artificial intelligence has triggered mixed public reactions, especially when applied to iconic visual styles such as Studio Ghibli. This research aims to evaluate public sentiment towards the phenomenon of Ghibli-style AI images by comparing two static word embedding methods, namely FastText and GloVe, on three classification algorithms: Logistic Regression, Random Forest, and Convolutional Neural Network (CNN). Data in the form of Indonesian tweets were collected from Twitter using hashtags such as #ghibli, #ghiblistyle, and #hayaomiyazaki during the period 25 March to 25 April 2025. Each tweet was manually labelled with positive or negative sentiment, then preprocessed and represented using pre-trained FastText and GloVe embeddings. Evaluation was conducted using accuracy, precision, recall, and F1-score metrics, both macro and weighted. Results showed that FastText consistently performed the best on most models, especially in terms of precision and overall accuracy, thanks to its ability to handle sub-word information and spelling variations in social media texts. The combination of CNN with FastText yielded the highest performance with a macro F1-score of 76.56% and accuracy of 84.69%. However, GloVe still showed competitive performance in recall on the Logistic Regression model, making it relevant for contexts that prioritise sentiment detection coverage. This study emphasizes the importance of selecting embeddings and models that are appropriate to the characteristics of the data and the purpose of the analysis in informal social media-based sentiment classification.
Downloads
References
[1] I. N. Khasanah, “Sentiment Classification Using fastText Embedding and Deep Learning Model,” Procedia CIRP, vol. 189, pp. 343–350, 2021, doi: 10.1016/j.procs.2021.05.103.
[2] C. Ouni, E. Benmohamed, and H. Ltifi, “Deep learning-based Soft word embedding approach for sentiment analysis,” Procedia Comput. Sci., vol. 246, no. C, pp. 1355–1364, 2024, doi: 10.1016/j.procs.2024.09.720.
[3] N. Badri, F. Kboubi, and A. H. Chaibi, “Combining FastText and Glove Word Embedding for Offensive and Hate speech Text Detection,” Procedia Comput. Sci., vol. 207, no. Kes, pp. 769–778, 2022, doi: 10.1016/j.procs.2022.09.132.
[4] S. Ghosal and A. Jain, “Depression and Suicide Risk Detection on Social Media using fastText Embedding and XGBoost Classifier,” Procedia Comput. Sci., vol. 218, pp. 1631–1639, 2022, doi: 10.1016/j.procs.2023.01.141.
[5] J. Devlin, M.-W. Chang, K. Lee, K. T. Google, and A. I. Language, “BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding,” Naacl-Hlt 2019, no. Mlm, pp. 4171–4186, 2018, [Online]. Available: https://aclanthology.org/N19-1423.pdf
[6] J. Pennington, R. Socher, and C. D. Manning, “Glove: Global vectors for word representation,” Proc. 2014 Conf. Empir. methods Nat. Lang. Process., pp. 1532–1543, 2014.
[7] P. Bojanowski, E. Grave, A. Joulin, and T. Mikolov, “Enriching Word Vectors with Subword Information,” Trans. Assoc. Comput. Linguist., vol. 5, pp. 135–146, 2017.
[8] L. Xiaoyan, R. C. Raga, and S. Xuemei, “GloVe-CNN-BiLSTM Model for Sentiment Analysis on Text Reviews,” J. Sensors, vol. 2022, 2022, doi: 10.1155/2022/7212366.
[9] M. S. Mahmud, M. T. Islam, A. J. Bonny, R. K. Shorna, J. H. Omi, and M. S. Rahman, “Deep Learning Based Sentiment Analysis from Bangla Text Using Glove Word Embedding along with Convolutional Neural Network,” 2022 13th Int. Conf. Comput. Commun. Netw. Technol. ICCCNT 2022, no. December, 2022, doi: 10.1109/ICCCNT54827.2022.9984392.
[10] Siti Khomsah, Rima Dias Ramadhani, and Sena Wijaya, “The Accuracy Comparison Between Word2Vec and FastText On Sentiment Analysis of Hotel Reviews,” J. RESTI (Rekayasa Sist. dan Teknol. Informasi), vol. 6, no. 3, pp. 352–358, 2022, doi: 10.29207/resti.v6i3.3711.
[11] A. Ilmania, Abdurrahman, S. Cahyawijaya, and A. Purwarianti, “Aspect Detection and Sentiment Classification Using Deep Neural Network for Indonesian Aspect-Based Sentiment Analysis,” Proc. 2018 Int. Conf. Asian Lang. Process. IALP 2018, pp. 62–67, 2019, doi: 10.1109/IALP.2018.8629181.
[12] A. N. Azhar, M. L. Khodra, and A. P. Sutiono, “Multi-label Aspect Categorization with Convolutional Neural Networks and Extreme Gradient Boosting,” Proc. Int. Conf. Electr. Eng. Informatics, vol. 2019-July, no. July, pp. 35–40, 2019, doi: 10.1109/ICEEI47359.2019.8988898.
[13] A. Nurdin, B. Anggo Seno Aji, A. Bustamin, and Z. Abidin, “Perbandingan Kinerja Word Embedding Word2Vec, Glove, Dan Fasttext Pada Klasifikasi Teks,” J. Tekno Kompak, vol. 14, no. 2, p. 74, 2020, doi: 10.33365/jtk.v14i2.732.
[14] R. P. Hastuti, V. Riona, and M. Hardiyanti, “Content Retrieval dengan Fasttext Word Embedding pada Learning Management System Olimpiade,” J. Internet Softw. Eng., vol. 4, no. 1, pp. 18–22, 2023, doi: 10.22146/jise.v4i1.6766.
[15] T. F. Abdillah, “Comparison of TF-IDF and GloVe Word Embedding for Sentiment Analysis of 2024 Presidential Candidates,” vol. 6, no. 2, pp. 961–969, 2024, doi: 10.47065/bits.v6i2.5668.
[16] S. A. Assaidi and F. Amin, “Analisis Sentimen Evaluasi Pembelajaran Tatap Muka 100 Persen pada Pengguna Twitter menggunakan Metode Logistic Regression,” J. Pendidik. Tambusai, vol. 6, no. 2, pp. 13217–13227, 2022.
[17] L. Breiman, Random Forests. 2001.
[18] Bahwari, “Sentiment Analysis Using Random Forest Algorithm - Online Social Media Based,” J. Inf. Technol. ITS Util., vol. 2, no. 2, pp. 29–33, 2019, [Online]. Available: https://www.researchgate.net/publication/338548518_Sentiment_Analysis_Using_Random_Forest_Algorithm_Online_Social_Media_Based
[19] A. Hadi, M. Qamal, and Y. Afrillia, “Comparison of Random Forest Algorithm Classifier and Naïve Bayes Algorithm in Whatsapp Message Type Classification,” pp. 9–17, 2025.
[20] Y. Achmad, R. C. Wihandika, and C. Dewi, “Klasifikasi emosi berdasarkan ciri wajah wenggunakan convolutional neural network,” J. Pengemb. Teknol. Inf. dan Ilmu Komput., vol. 3, no. 11, pp. 10595–10604, 2019.
[21] H. Murfi, S. Theresia Gowandi, G. Ardaneswari, and S. Nurrohmah, “BERT-based combination of convolutional and recurrent neural network for indonesian sentiment analysis,” Appl. Soft Comput., vol. 151, pp. 1–15, 2024, doi: 10.1016/j.asoc.2023.111112.
[22] M. A. Nasichuddin, T. B. Adji, and W. Widyawan, “Performance Improvement Using CNN for Sentiment Analysis,” IJITEE (International J. Inf. Technol. Electr. Eng., vol. 2, no. 1, 2018, doi: 10.22146/ijitee.36642.
[23] Tjong, G. Hartoko, and H. Leong, “Comparison Of Glove And Fasttext Algorithms On Cnn For Classification Of Indonesian News Categories,” Proxies, vol. 7, no. 1, pp. 24–32, 2023.
[24] D. R. Putri, E. Y. Puspaningrum, H. Maulana, U. Pembangunan, N. Veteran, and J. Timur, “Indonesia Neural Network,” vol. 12, no. 3, pp. 2759–2769, 2024.
[25] S. Ghosal and A. Jain, “Depression and Suicide Risk Detection on Social Media using fastText Embedding and XGBoost Classifier,” Procedia Comput. Sci., vol. 218, pp. 1631–1639, 2022, doi: 10.1016/j.procs.2023.01.141.
[26] W. Yudi, “GloVe untuk Wikipedia Bahasa Indonesia,” https://yudiwbs.wordpress.com/2018/04/02/glove-untuk-wikipedia-bahasa-indonesia/.
[27] E. Grave, P. Bojanowski, P. Gupta, A. Joulin, and T. Mikolov, “Learning Word Vectors for 157 Languages,” Proc. Int. Conf. Lang. Resour. Eval. (LREC 2018), 2018.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 I Gusti Ngurah Sentana Putra, Muhammad Yusran, Jefita Resti Sari, Cici Suhaeni, Bagus Sartono, Gerry Alfa Dito
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).
