Pengaruh Gaya Komunikasi Tertulis Mahasiswa Ilmu Komunikasi Uin Raden Fatah Palembang Terhadap Akurasi Jawaban Pada ChatGPT
DOI:
https://doi.org/10.31004/joecy.v5i2.2646Keywords:
communication style, written communication, ChatGPTAbstract
The study purpose was to examine the extent to which students’ written communication style affects the accuracy of ChatGPT’s responses. As ChatGPT becomes increasingly utilized as an academic support tool, the ability to craft precise prompts is crucial. This research employed a descriptive quantitative approach and a light experimental design. The sample included 50 Communication Science students at UIN Raden Fatah Palembang, class of 2022, selected through purposive sampling. Students submitted their typical prompts, which were categorized into informative, narrative, descriptive, and persuasive styles. ChatGPT's responses were evaluated based on relevance, completeness, and factual accuracy.
Results revealed that the descriptive style yielded the highest accuracy score (M = 4.10), followed by informative (M = 3.74), narrative (M = 3.51), and persuasive (M = 3.23). Pearson correlation analysis showed a significant positive relationship (r = 0.413, p = 0.003) between communication style and response accuracy. A simple linear regression produced the equation Y = 3.392 + 0.113X, indicating that an improvement in communication quality leads to more accurate ChatGPT responses..
This study highlights the importance of writing skills in digital interaction and recommends integrating AI literacy into higher education curricula so that students can effectively communicate with AI-powered systems..
References
Atreja, Shubham, Joshua Ashkinaze, Lingyao Li, Julia Mendelsohn, and Libby Hemphill. “Prompt Design Matters for Computational Social Science Tasks but in Unpredictable Ways,” 2024. http://arxiv.org/abs/2406.11980.
Bozkurt, Aras. “Tell Me Your Prompts and I Will Make Them True: The Alchemy of Prompt Engineering and Generative AI.” Open Praxis 16, no. 2 (2024): 111–18. https://doi.org/10.55982/openpraxis.16.2.661.
Brown, Tom, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, et al. “Language Models Are Few-Shot Learners.” In Advances in Neural Information Processing Systems, edited by H Larochelle, M Ranzato, R Hadsell, M F Balcan, and H Lin, 33:1877–1901. Curran Associates, Inc., 2020. https://proceedings.neurips.cc/paper_files/paper/2020/file/1457c0d6bfcb4967418bfb8ac142f64a-Paper.pdf.
Ciampa, K., Z. M. Wolfe, and B. Bronstein. “ChatGPT in Education: Transforming Digital Literacy Practices.” Journal of Adolescent & Adult Literacy 67, no. 3 (2023): 186–195. https://doi.org/https://doi.org/10.1002/jaal.1330.
Gonen, Hila, Srini Iyer, Terra Blevins, Noah A. Smith, and Luke Zettlemoyer. “Demystifying Prompts in Language Models via Perplexity Estimation.” Findings of the Association for Computational Linguistics: EMNLP 2023, 2023, 10136–48. https://doi.org/10.18653/v1/2023.findings-emnlp.679.
Nazari, Mostafa, and Golsa Saadi. “Developing Effective Prompts to Improve Communication with ChatGPT: A Formula for Higher Education Stakeholders.” Discover Education 3, no. 1 (2024). https://doi.org/10.1007/s44217-024-00122-w.
Norton, R. “Foundation of a Communicator Style Construct.” Human Communication Research 4 (1978): 99 –112. https://communication.iresearchnet.com/interpersonal-communication/communicator-style/.
Pawlik, Lukasz. “How the Choice of LLM and Prompt Engineering Affects Chatbot Effectiveness.” Electronics (Switzerland) 14, no. 5 (2025): 1–16. https://doi.org/10.3390/electronics14050888.
Priyatno, D. Pintar Mengolah Data Statistik Dengan SPSS. Yogyakarta: Mediakom., 2020.
Sugiyono. Metode Penelitian Kuantitatif, Kualitatif, Dan R&D. Bandung: Alfabeta., 2021.
Wang, Li, Xi Chen, Xiang Wen Deng, Hao Wen, Ming Ke You, Wei Zhi Liu, Qi Li, and Jian Li. “Prompt Engineering in Consistency and Reliability with the Evidence-Based Guideline for LLMs.” Npj Digital Medicine 7, no. 1 (2024): 1–9. https://doi.org/10.1038/s41746-024-01029-4.
Yustika, Devi, Sudarti, and R. Handayani. “Analisis Regresi Linier Sederhana Untuk Mengestimasi Pengaruh Kemampuan Self Regulated Learning Terhadap Hasil Belajar Siswa Menggunakan Model Pembelajaran RASI.” Jurnal Pendidikan MIPA 22, no. 2 (2022): 294‑297.
Zhao, Tony Z., Eric Wallace, Shi Feng, Dan Klein, and Sameer Singh. “Calibrate Before Use: Improving Few-Shot Performance of Language Models.” Proceedings of Machine Learning Research 139 (2021): 12697–706.
Zhao, X., A. Cox, and L. Cai. “ChatGPT and the Digitisation of Writing.” Humanities and Social Sciences Communications, 11 (2024): 482. https://doi.org/10.1057/s41599-024-02591-3.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Muhammad Ravi Aziz Anafi, Abdur Razzaq, Muhamad Yudistira Nugraha
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
