Analisis Opini Publik Menggunakan Sentiment Analysis Dengan Model RoBERTa Pada Pengguna Twitter Terhadap Tingkat Polaritas Pendapat Tentang ChatGPT

• Danu Febriansyah
• 2023

---

ChatGPT, dikembangkan oleh OpenAI, adalah model bahasa yang memanfaatkan arsitektur transformer dalam Generative Pre-trained Transformer (GPT). Melalui teknik pre-training, model ini mempelajari struktur bahasa dan pengetahuan umum dari dataset teks besar. Dirancang khusus untuk tugas percakapan, ChatGPT mampu memahami dan menghasilkan teks terstruktur sebagai respons terhadap pertanyaan atau pernyataan pengguna. Meskipun memiliki potensi besar, perlu diingat bahwa ChatGPT tetap merupakan representasi kecerdasan buatan dengan keterbatasan dalam memahami konteks yang kompleks atau membuat penilaian moral yang canggih. Oleh karena itu, analisis opini publik, terutama dari Twitter, menjadi penting. Dalam penyusunan skripsi, pengumpulan data opini publik dari Twitter dilakukan melalui teknik scraping data. Data opini tersebut, yang mencakup 20.000 pendapat pengguna Twitter tentang ChatGPT, dianalisis menggunakan model Robustly optimized BERT Pretraining approach (RoBERTa). Hasil penelitian menunjukkan bahwa opini publik pengguna Twitter terhadap ChatGPT cenderung netral, sesuai dengan sentimen yang dihasilkan oleh model RoBERTa. Penelitian ini memberikan pemahaman yang berharga tentang bagaimana masyarakat merespons ChatGPT. Meskipun model ini dinilai netral oleh pengguna Twitter, penting untuk terus mengkaji dan meningkatkan model ini agar dapat menjawab tantangan dan harapan masyarakat secara lebih baik. Dengan perkembangan teknologi, penelitian semacam ini menjadi kunci untuk memastikan pengembangan dan penerapan model kecerdasan buatan yang bertanggung jawab dan etis dalam kehidupan sehari-hari.

• ChatGPT
• RoBERTa
• Sentiment Analysis

Alarifi, A., Tolba, A., Al-Makhadmeh, Z., & Said, W. (2020). A big data approach to sentiment analysis using greedy feature selection with cat swarm optimization-based long short-term memory neural networks. Journal of Supercomputing, 76(6), 4414–4429. https://doi.org/10.1007/s11227-018- 2398-2

Bengesi, S., Oladunni, T., Olusegun, R., & Audu, H. (2023). A Machine LearningSentiment Analysis on Monkeypox Outbreak: An Extensive Dataset to Show the Polarity of Public Opinion From Twitter Tweets. IEEE Access, 11, 11811–11826. https://doi.org/10.1109/ACCESS.2023.3242290

Biringkanae, P., & Bunahri, R. R. (2023). Literature Review Penggunaan Teknologi Kecerdasan Buatan dalam Penerbangan: Analisis Perkembangan Teknologi, Potensi Keamanan, dan Tantangan. Jurnal Ilmu Manajemen Terapan, 4(5), 745–752. https://doi.org/10.31933/jimt.v4i5

Dai, J., Pan, F., Shou, Z., & Zhang, H. (2021). RoBERTa-IAN for aspect-level sentiment analysis of product reviews. Journal of Physics: Conference Series, 1827(1). https://doi.org/10.1088/1742-6596/1827/1/012079

Dwivedi, Y. K., Kshetri, N., Hughes, L., Slade, E. L., Jeyaraj, A., Kar, A. K., Baabdullah, A. M., Koohang, A., Raghavan, V., Ahuja, M., Albanna, H., Albashrawi, M. A., Al-Busaidi, A. S., Balakrishnan, J., Barlette, Y., Basu, S., Bose, I., Brooks, L., Buhalis, D., … Wright, R. (2023). “So what if ChatGPT wrote it?” Multidisciplinary perspectives on opportunities, challenges and implications of generative conversational AI for research, practice and policy. International Journal of Information Management, 71. https://doi.org/10.1016/j.ijinfomgt.2023.102642

Haluza, D., & Jungwirth, D. (2023). Artificial Intelligence and Ten Societal Megatrends: An Exploratory Study Using GPT-3. Systems, 11(3), 120. https://doi.org/10.3390/systems11030120

IBM Global AI Adoption Index 2022. (2022).

Liao, W., Zeng, B., Yin, X., & Wei, P. (2021). An improved aspect-category sentiment analysis model for text sentiment analysis based on RoBERTa. Applied Intelligence, 51(6), 3522–3533. https://doi.org/10.1007/s10489- 020-01964-1

Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., & Stoyanov, V. (2019). RoBERTa: A Robustly Optimized BERT Pretraining Approach. http://arxiv.org/abs/1907.11692

McCarthy, M., & Byrd, M. (2021, July 2). How to build AI that society wants and needs. Https://Www.Weforum.Org/Agenda/2021/07/How-to-Build-AiThat-Society-Wants-and-Needs/.

Metz, C. (2021). Genius Makers (P. W. Tam, J. Kerstetter, S. Morrow, & D. Cullen, Eds.). Dutton.

Munikar, M., Shakya, S., & Shrestha, A. (2019). Fine-grained Sentiment Classification using BERT.

Nath, R. (2020). Alan Turing’s Concept of Mind. Journal of Indian Council of Philosophical Research, 37(1), 31–50. https://doi.org/10.1007/s40961- 019-00188-0

Naudé, W., & Dimitri, N. (2020). The race for an artificial general intelligence: implications for public policy. AI and Society, 35(2), 367–379. https://doi.org/10.1007/s00146-019-00887-x

OpenAI. (2023). GPT-4 Technical Report. http://arxiv.org/abs/2303.08774

Prianto, C., Andarsyah, R., & Harani, N. H. (2022). Rancang Bangun Kamus Digital Berbasis Chatbot Menggunakan Pendekatan Pattern Matching. JURNAL MEDIA INFORMATIKA BUDIDARMA, 6(4), 2327. https://doi.org/10.30865/mib.v6i4.4910

Russel, S., & Norvig, P. (2022). Artificial Intelligence: A Modern Approach, Global Edition (T. Johnson, Ed.; Fourth Edition, Vol. 2021). Pearson.

Sally, S. (2022). Sentiment Analysis On Youtube Smartphone Unboxing Video Reviews in Srilanka. International Journal of Research - GRANTHAALAYAH, 10(11), 53–63. https://doi.org/10.29121/granthaalayah.v10.i11.2022.4884

Schmidt, S., Zorenböhmer, C., Arifi, D., & Resch, B. (2023). Polarity-Based Sentiment Analysis of Georeferenced Tweets Related to the 2022 Twitter Acquisition. Information (Switzerland), 14(2). https://doi.org/10.3390/info14020071

Shalumov, V., & Haskey, H. (2023). HeRo: RoBERTa and Longformer Hebrew Language Models. https://github.com

Suwarningsih, W., Pratama, R. A., Rahadika, F. Y., & Purnomo, M. H. A. (2022). RoBERTa: language modelling in building Indonesian questionanswering systems. Telkomnika (Telecommunication Computing Electronics and Control), 20(6), 1248–1255. https://doi.org/10.12928/TELKOMNIKA.v20i6.24248

Taecharungroj, V. (2023). “What Can ChatGPT Do?” Analyzing Early Reactions to the Innovative AI Chatbot on Twitter. Big Data and Cognitive Computing, 7(1), 35. https://doi.org/10.3390/bdcc7010035

Taghandiki, K., & Ehsan, E. R. (2023). Types of Approaches, Applications and Challenges in the Development of Sentiment Analysis Systems. http://arxiv.org/abs/2303.11176

Tan, K. L., Lee, C. P., Anbananthen, K. S. M., & Lim, K. M. (2022). RoBERTaLSTM: A Hybrid Model for Sentiment Analysis With Transformer and Recurrent Neural Network. IEEE Access, 10, 21517–21525. https://doi.org/10.1109/ACCESS.2022.3152828

Thormundsson, 2023. (n.d.). Retrieved May 17, 2023, from https://www.statista.com/statistics/656596/worldwide-chatbot-market/

Tika Adilah, M., Supendar, H., Ningsih, R., Muryani, S., & Solecha, K. (2020). Sentiment Analysis of Online Transportation Service using the Naïve Bayes Methods. Journal of Physics: Conference Series, 1641(1). https://doi.org/10.1088/1742-6596/1641/1/012093 51

Van Bavel, J. J., Rathje, S., Harris, E., Robertson, C., & Sternisko, A. (2021). How social media shapes polarization. In Trends in Cognitive Sciences (Vol. 25, Issue 11, pp. 913–916). Elsevier Ltd. https://doi.org/10.1016/j.tics.2021.07.013

Viesdel, J. (2019, September 12). The Birthplace of AI. Https://Www.Cantorsparadise.Com/the-Birthplace-of-Ai-9ab7d4e5fb00.

Wooldrige, M. (2021). A Brief History of Artificial Intelligence. Flatiron Books. ZEMČÍK, Mgr. T. (2019). A Brief History of Chatbots. DEStech Transactions on Computer Science and Engineering, aicae. https://doi.org/10.12783/dtcse/aicae2019/31439

Zha, Y., Yang, Y., Li, R., & Hu, Z. (2023). Text Alignment Is An Efficient Unified Model for Massive NLP Tasks. http://arxiv.org/abs/2307.02729