Sentiment Analysis Classification of Deepseek AI on Twitter (X) Big Data Using SOM-LSTM
DOI:
https://doi.org/10.59563/djtech.v7i1.419Keywords:
Analisis Sentimen, Big Data, Deepseek AI, SOM–LSTM, Twitter (X)Abstract
Urgensi penelitian ini adalah perlunya mengidentifikasi dan mengklasifikasikan sentimen publik terhadap DeepSeek AI di Twitter (X) secara akurat dan efisien menggunakan metode SOM-LSTM untuk memahami persepsi masyarakat berbasis big data. Analisis sentimen terhadap opini publik mengenai DeepSeek AI pada media sosial Twitter (X) penting dilakukan untuk mengidentifikasi kecenderungan persepsi pengguna terhadap perkembangan teknologi kecerdasan buatan. Penelitian ini bertujuan mengklasifikasikan sentimen publik terhadap DeepSeek AI menggunakan model hibrida Self-Organizing Map–Long Short-Term Memory (SOM–LSTM). Data penelitian terdiri atas 10.000 cuitan yang dikumpulkan melalui Twitter API menggunakan kata kunci “DeepSeek AI” pada periode Januari 2024–Juli 2025. Data melalui tahap pelabelan otomatis menggunakan BERT, preprocessing, tokenisasi, dan representasi kata menggunakan GloVe berdimensi 100 sebelum diproses menggunakan SOM–LSTM. SOM digunakan untuk melakukan pengelompokan fitur secara tidak terawasi, sedangkan LSTM digunakan untuk mempelajari hubungan sekuensial dalam teks. Evaluasi dilakukan menggunakan accuracy, precision, recall, dan F1-score dengan membandingkan kinerja SOM–LSTM terhadap LSTM sebagai model baseline. Hasil penelitian menunjukkan bahwa SOM–LSTM memperoleh accuracy sebesar 0,98, precision sebesar 0,99, recall sebesar 0,98, dan F1-score sebesar 0,98, sedangkan LSTM memperoleh accuracy sebesar 0,85. Hasil tersebut menunjukkan bahwa integrasi SOM dapat meningkatkan kinerja klasifikasi dibandingkan LSTM tunggal pada dataset yang digunakan. Secara substantif, hasil analisis menunjukkan dominasi sentimen negatif terhadap DeepSeek AI. Temuan penelitian ini dapat menjadi informasi pendukung bagi peneliti, pengembang, dan pemangku kepentingan dalam memahami persepsi publik serta mengidentifikasi isu yang berkaitan dengan penggunaan dan pengembangan teknologi AI.
References
D. Guo et al., “DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning,” Nature, vol. 645, no. 8081, pp. 633–638, 2025, http://dx.doi.org/10.1038/s41586-025-09422-z.
Y. Zhang, S. Wang, and B. Liu, “Deep learning for sentiment analysis: A survey,” WIREs Data Mining and Knowledge Discovery, vol. 8, no. 4, 2018. https://doi.org/10.1002/widm.1253.
S. Rosenthal et al., “SemEval-2015 Task 10: Sentiment analysis in Twitter,” Proceedings of the 9th International Workshop on Semantic Evaluation, pp. 451–463, 2015. https://doi.org/10.18653/v1/S15-2078.
S. Nakov et al., “SemEval-2016 Task 4: Sentiment analysis in Twitter,” Proceedings of the 10th International Workshop on Semantic Evaluation, pp. 1–18, 2016. https://doi.org/10.18653/v1/S16-1001.
S. Hochreiter and J. Schmidhuber, “Long short-term memory,” Neural Computation, vol. 9, no. 8, pp. 1735–1780, 1997. https://doi.org/10.1162/neco.1997.9.8.1735.
M. Vesanto and E. Alhoniemi, “Clustering of the self-organizing map,” IEEE Transactions on Neural Networks, vol. 11, no. 3, pp. 586–600, 2000. https://doi.org/10.1109/72.846731.
A. M. Isa, S. Kallimani, and V. S. Lee, “Using self-organizing map for text document clustering,” Expert Systems with Applications, 2008. https://doi.org/10.1016/j.eswa.2008.07.082.
M. Jahin et al., “A hybrid transformer and attention-based BiLSTM model for sentiment analysis of tweets,” Scientific Reports, 2024. https://doi.org/10.1038/s41598-024-76079-5
J. Pennington, R. Socher, and C. D. Manning, “GloVe: Global vectors for word representation,” Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, pp. 1532–1543, 2014. https://doi.org/10.3115/v1/D14-1162.
J. Devlin et al., “BERT: Pre-training of deep bidirectional transformers for language understanding,” Proceedings of NAACL-HLT, pp. 4171–4186, 2019. https://doi.org/10.18653/v1/N19-1423.
D. Jurafsky and J. H. Martin, Speech and Language Processing, 3rd ed., online manuscript, 2026.
S. Islam et al., “A survey on sentiment analysis: Challenges and future directions,” Artificial Intelligence Review, 2023. https://doi.org/10.1007/s10462-022-10386-z.
D. Q. Nguyen et al., “BERTweet: A pre-trained language model for English Tweets,” Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pp. 9–14, 2020. https://doi.org/10.18653/v1/2020.emnlp-demos.2.
F. Barbieri et al., “TweetEval: Unified benchmark and comparative evaluation for tweet classification,” Findings of the Association for Computational Linguistics: EMNLP 2020, pp. 1644–1650, 2020. https://doi.org/10.18653/v1/2020.findings-emnlp.148.
C. Hutto and E. Gilbert, “VADER: A parsimonious rule-based model for sentiment analysis of social media text,” Proceedings of the International AAAI Conference on Web and Social Media, vol. 8, no. 1, pp. 216–225, 2014. https://doi.org/10.1609/icwsm.v8i1.14550.
B. Pang and L. Lee, “Opinion mining and sentiment analysis,” Foundations and Trends in Information Retrieval, vol. 2, no. 1–2, pp. 1–135, 2008. https://doi.org/10.1561/1500000011.
B. Liu, Sentiment Analysis and Opinion Mining. Cham, Switzerland: Springer, 2012. https://doi.org/10.2200/S00416ED1V01Y201204HLT016.
A. Severyn and A. Moschitti, “Twitter sentiment analysis with deep convolutional neural networks,” Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 959–962, 2015. https://doi.org/10.1145/2766462.276783.
P. Nakov, “Sentiment analysis in Twitter: A SemEval perspective,” Proceedings of the 10th International Workshop on Semantic Evaluation, 2016. https://doi.org/10.18653/v1/W16-0427.
I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. Cambridge, MA, USA: MIT Press, 2016.
V. Deska, A. Armanto, and E. Elmayati, “Deteksi Serangan Man-In-The-Middle (MITM) Berbasis Machine Learning pada Dataset CIC IIOT 2025”, djtech, vol. 6, no. 2, pp. 168-184, Jul. 2026. https://doi.org/10.59563/djtech.v6i2.317
A. . Syavira, “Empirical Comparison: Analysis of Initial Set-up of BGP Dynamic Routing and Static Routing in Three Administrative Domain Network Interconnection”, djtech, vol. 6, no. 2, pp. 115-128, May 2026. https://doi.org/10.59563/djtech.v6i2.379
