Usando chatGPT para programar en una asignatura de Algoritmia

• Autores: Arturo González Escribano
• Localización: Actas de las Jornadas sobre la Enseñanza Universitaria de la Informática (JENUI), ISSN 2531-0607, Nº. 9 (Actas de las XXX Jornadas sobre Enseñanza Universitaria de la Informática (La Coruña, 19, 20 y 21 de), 2024, págs. 35-42
• Idioma: español
• Enlaces
  • Texto completo
• Resumen

  • The focus of Algorithms courses is teaching to identify and use the most appropriate algorithms and data structures to solve different kinds of problems. In general, it is taken for granted that the students have the programing skills to understand the algorithms and develop their own practical problem solutions. In our course we propose practical assignments to develop several programs that solve the same problem with different algorithms, variants and data structures. This allows the students the comparison of the different solutions in terms of programming effort and performance impact. In previous academic years we detected that the amount of hours invested by the students in the programming tasks was too high, and they also showed problems to apply previous programming knowledge to real cases. This deviates the focus from the algorithms, the use of abstractions and the impact of alternatives to the challenges associated to the usage of the programming language and the programming structures. This work describes an experience conducted this academic year in which we have proposed to the students the use of chatGPT 3.5 to develop from scratch all the programs and alternatives of the practical assignments. We describe and evaluate the implementation and evaluation methods used. We present results about the participation, dedication and subjective perception of the students of the learning experience. Finally, we present conclusions about the execution of the experience and the problems detected.

• Referencias bibliográficas
  • [1] Christos Anagnostopoulos. ChatGPT impacts in programming education: A recent literature overview that debates ChatGPT responses. F1000Research,...
  • [2] David Baidoo-Anu y Leticia Owusu Ansah. Edu- cation in the era of generative artificial intelligence (AI): Understanding the potential...
  • [3] Brett A. Becker, Paul Denny, James Finnie- Ansley, Andrew Luxton-Reilly, James Prather y Eddie Antonio Santos. Programming is hard or...
  • [4] Jonnathan Berrezueta-Guzmán y Stephan Krusche. Recommendations to create programming exercises to overcome ChatGPT. Conference on Software...
  • [5] Alessio Buscemi. A comparative study of code generation using ChatGPT 3.5 across 10 programming languages. arXiv.org, arXiv:2308.04477v1,...
  • [6] Grant Cooper. Examining science education in ChatGPT: An exploratory study of generative artificial intelligence. Journal of Science Education...
  • [7] Arghavan Moradi Dakhel, Vahid Majdinasab, Amin Nikanjam, Foutse Khomh, Michel C. Desmarais y Zhen Ming (Jack) Jiang. Github copilot AI...
  • [8] Philip J. Guo. Six opportunities for scientists and engineers to learn programming using AI tools such as ChatGPT. Computing in science...
  • [9] Philipp Haindl y Gerald Weinberger. Students’ experiences of using ChatGPT in an undergraduate programming course. IEEE Access, 12:43519–43529,...
  • [10] Minjie Hu, Tony Assadi y Hamid Mahroeian. Ex- plicitly introducing ChatGPT into first-year programming practice: Challenges and impact....
  • [11] Sajed Jalil, Suzzana Rafi, Thomas D. LaToza, Kevin Moran y Wing Lam. ChatGPT and software testing education: Promises & perils. En...
  • [12] Natalie Kiesler y Daniel Schiffner. Large language models in introductory programming education: ChatGPT’s performance and implications...
  • [13] Isaac Lera, Gabriel Moyà-Alcover, Carlos Guerrero y Antoni Jaume i Capó. Reflexiones y perspectivas del uso de chatGPT en la docencia...
  • [14] Francisco de Sande González y Pablo López Ra- mos. El impacto de asistentes basados en ia en la enseñanza-aprendizaje de la programación...