What I learned interviewing a robot. Notes on the experimental application of the EIAF methodology using the ChatGPT artificial intelligence tool
Article Sidebar
Main Article Content
This paper describes the EIAF (Exploratory Interview for Assessing Functionalities) methodology and proposes how communication researchers could use it to study characteristics or analyze texts created by generative artificial intelligence algorithms. To do this, an in-depth interview in portuguese, was conducted with the ChatGPT conversation tool, developed by OPENAI. A set of specific categories were developed: self-identification, uses and limitations, validation tests, additional experimentation and metrics, transparency, structuring, precision, variety and updating, all of which were used in the experiment to test the proposed methodology. The experiment showed that despite being correct and well-structured, the code-produced texts needed human revision, essential especially for material that deals with facts and objective data.
Article Details

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
(c) Márcio Carneiro dos Santos, 2023
Copyright

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0).
Márcio Carneiro dos Santos, Universidade Federal do Maranhão
Márcio Carneiro dos Santos. He holds a Doctorate from the Technology Intelligence and Digital Design (TIDD) program at PUC-SP. Coordinator of the Graduate Program in Communication - Professional Master’s Degree at UFMA. Professor of the Department of Social Communication in the area of Journalism in Digital Networks. Director of LABCOM-Media Convergence Laboratory. Leader of the research group CNPq - Technology and Digital Narratives - TECND. Coordinator of the Data Intelligence Center - NID and of the LABCOM Connect Initiative. Has published papers in the areas of Intelligent Systems Applied to Journalism, Narratives in Digital Environments, Immersive Journalism, Design Sciences, Network Theory, Social Network Analysis, and Philosophy of Technology. Adelmo Genro Filho Award, from the Brazilian Association of Journalism Researchers - SBPJor, in 2018 and 2022, in the Applied Research category. Master in Communication from Anhembi Morumbi University - São Paulo. Marketing Specialist by ISAN/FGV-Rio.
Amadeu, S. (2019). Democracia e os códigos invisíveis: Como os algoritmos estão modulando comportamentos e escolhas políticas. Edições Sesc (Coleção Democracia Digital).
AP - The Associated Press. (2022). Leveraging AI to advance the power of facts: Artificial Intelligence at the Associate Press. ap.org. https://www.ap.org/discover/artificial-intelligence
Dos Santos, M. C. (2016). Internet das Coisas e sistemas inteligentes no jornalismo: o conceito de presença diluído entre as narrativas da complexidade urbana. Comunicação & Inovação, 17(34), 21-39. https://doi.org/10.13037/ci.vol17n34.3769
Dos Santos, M. C. (2018). Inteligência híbrida e análise de sentimentos: integrando curadoria humana e coleta de dados automatizada para avaliar a comunicação de governo. Conexão-Comunicação e Cultura, 17(33).
Dos Santos, M. C. (2019). A datificação de um campo de conhecimento: como algoritmos, números e abordagens quantitativas estão mudando a comunicação. Organicom, 16(31), 145-157. https://doi.org/10.11606/issn.2238-2593.organicom.2019.161444
Guzman, A. L., & Seth, C. (2019). Artificial Intelligence and Communication: A Human–Machine Communication Research Agenda. New Media & Society, 22(1), 70-86. https://doi.org/10.1177/1461444819858691
Guzman, A. L. (2018). What is human-machine communication, anyway. In A.L. Guzman (Ed.), Human-machine communication: Rethinking communication, technology, and ourselves, (pp. 1-28). Peter Lang.
Jones, S. (2013). Against technology: From the Luddites to neo-Luddism. Routledge.
Latzer, M., Hollnbuchner, K., Just, N., & Saurwein, F. (2014). The economics of algorithmic selection on the Internet. In: J. Bauer, & M. Latzer (Eds.), Handbook on the Economics of the Internet, (pp. 395-425). Edward Elgar Publishing. https://doi.org/10.2139/ssrn.2710399
Lemos, A. (2020). Epistemologia da comunicação, neomaterialismo e cultura digital. Galáxia (43), 54-66. https://doi.org/10.1590/1982-25532020143970
Manovich, L. (2014). El software toma el mando. Editorial UOC.
Mayer-Schönberger, V., & Cukier, K. (2013). Big data: A revolution that will transform how we live, work, and think. Houghton Mifflin Harcourt.
Mollman, S. (2022, December 09). ChatGPT has gained 1 million followers in a single week. Here’s why the A.I. chatbot is primed to disrupt search as we know it. Yahoo Finance. https://finance.yahoo.com/news/chatgpt-gained-1-million-followers-224523258.html
Musiani, F. (2013). Governance by algorithms. Internet Policy Review, 2(3), 1-8. https://doi.org/10.14763/2013.3.188
Napoli, P. (2013). The algorithm as an institution: Toward a theoretical framework for automated media production and consumption. Fordham University Schools of Business Research Paper. https://doi.org/10.2139/ssrn.2260923
Reiter, E., Sripada, S., & Robertson, R. (2003). Acquiring correct knowledge for natural language generation. Journal of Artificial Intelligence Research, 18, 491-516. https://doi.org/10.1613/jair.1176
Silva, T. (2019). Racismo Algorítmico em Plataformas Digitais: microagressões e discriminação em código. In: Anais VI Simpósio Internacional Lavits. https://lavits.org/wp-content/uploads/2019/12/Silva-2019-LAVITSS.pdf
Squirra, S. (2016a). A informação essencial a vida, as máquinas e a comunicação. Lumina, 10(2). https://doi.org/10.34019/1981-4070.2016.v10.21211
Squirra, S. (2016b). A tecnologia e a evolução podem levar a comunicação para a esfera das mentes. Revista Famecos, 23(1), Id21275. https://doi.org/10.15448/1980-3729.2016.1.21275
Lima Jr, W., & Vergili, R. (2018). Digital Inclusion and Computational Thinking: New Challenges and Opportunities for Media Professionals. In: Information and Technology Literacy: Concepts, Methodologies, Tools, and Applications, (pp. 759-773). Information Resources Management Association.
Veel, K. (2018). Make data sing: The automation of storytelling. Big Data & Society, 5(1). https://doi.org/10.1177/2053951718756686