Please use this identifier to cite or link to this item:
https://research.matf.bg.ac.rs/handle/123456789/3251| Title: | Assessing ChatGPT for Algorithm Time Complexity Education | Authors: | Pešić, Đorđe Vujošević Janičić, Milena Mišić, Marko Protić, Jelica |
Affiliations: | Informatics and Computer Science | Keywords: | algorithm time complexity;ChatGPT;exam questions assembly;programming education | Issue Date: | 1-Jan-2025 | Rank: | M33 | Publisher: | Springer | Related Publication(s): | Foundations of Computer Science and Frontiers in Education: Computer Science and Computer Engineering 20th International Conference, FCS 2024, and 20th International Conference, FECS 2024 | Journal: | Communications in Computer and Information Science | Conference: | World Congress in Computer Science, Computer Engineering and Applied Computing, CSCE : International Conference Foundations of Computer Science FCS (20 ; 2024 ; Las Vegas) World Congress in Computer Science, Computer Engineering and Applied Computing, CSCE : International Conference Frontiers in Education: Computer Science and Computer Engineering FECS (20 ; 2024 ; Las Vegas) |
Abstract: | We present the results of experiments performed using ChatGPT versions 3.5 and 4o to explore the possibilities of generating and solving exam questions related to the time complexity analysis of algorithms in programming courses. Both well-known and artificial code segments for educational purposes were observed. We concluded that ChatGPT can help automate exam question assembling and solving, but it is unreliable. We also observed that ChatGPT 4o is more descriptive and in some cases more successful in generating and solving test problems correctly. |
URI: | https://research.matf.bg.ac.rs/handle/123456789/3251 | ISBN: | [9783031859298] | ISSN: | 18650929 | DOI: | 10.1007/978-3-031-85930-4_17 |
| Appears in Collections: | Research outputs |
Show full item record
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.