Personality Modulation in Generative AIs: Improving Human-Machine Interactions

• João F. M. Almeida CESAR School
• Willian N. Grillo CESAR School

DOI: https://doi.org/10.5753/ihc_estendido.2024.243618

Abstract

With the advent of artificial intelligence (AI)-based tools, new possibilities have emerged for the creation of conversational agents. This article explores the capability of generative artificial intelligence, specifically the GPT language model, to modulate its responses based on personality traits informed through prompts. The study employed the "Personality Prompting (P2)" technique by inducing high neuroticism traits to analyze responses compared to a neutral text. The analysis revealed that the responses exhibited characteristics typical of the trait, suggesting that conversational interactions enabled by generative AI can be modulated to provide better experiences.

References

Amin, M. M., Cambria, E. and Schuller, B. W. (2023). Will affective computing emerge from foundation models and general artificial intelligence? a first evaluation of chatgp. IEEE Intelligent Systems, 38(2):15-23.

Erickson, T. (1997). Design Agent As If People Mattered. In: Software Agents, pages 79-96. AAAI Press.

Franceschini, A., Gropp, B., Moreira, B. D., Matheus, C. E., Perez, C., Puoli, C. and Aratangy, V. L. (2012). Teoria e Prática da Pesquisa Aplicada. Elsevier Ltd.

Grillo, W. N and Barros, H. O. (2022). Desenhando conversas com personalidade: aplicação do processo de design para desenvolvimento de framework de design conversacional. DAT Journal, 7(2): 246-259.

Ji, Y., Wu, W., Zheng, H., Hu, Y., Chen, X. and He, L. (2023). Is chatgpt a good personality recognizer? a preliminary study. arXiv preprint arXiv:2307.03952.

Jiang, G., Xu, M., Zhu, S. C., Han, W., Zhang, C. and Zhu, Y. (2024). Evaluating and inducing personality in pre-trained language models. Advances in Neural Information Processing Systems, 36

Norman, D. A. (2008) Emotional Design: why we love (or hate) everyday things, Rocco.

Oliveira, E. G. (2023). Chatbots: a importância do processamento de língua natural para a experiência do usuário. Trabalho de Conclusão de Curso (Graduação em Linguística) - Universidade Federal de São Carlos, São Paulo.

Roffo, G., Giorgetta, C., Ferrario, R., & Cristani, M. (2014). Just the way you chat: Linking personality, style and recognizability in chats. In Human Behavior Understanding: 5th International Workshop, HBU 2014, Zurich, Switzerland, September 12, 2014. Proceedings 5, pages 30-41. Springer International Publishing.