Learning a First Programming Language with LLM Tutor

The paper presents the use of Large Language Models (LLM) and Chatbots as tutors when students need to learn novel concepts related to programming.Traditional methods of teaching and learning new programming concepts involve the students and teachers exploring one idea at a time -sequence, selection, and iteration -followed by more complex concepts.Traditional methods include using textbooks, computers, presentations, etc., and the teacher has the central role in the classroom.LLMs can help make complex topics more accessible for teachers to teach and for students to explore.Passive lectures and frontal teaching methods are replaced by the interactive use of LLM/chatbots, where the teacher has a central role in checking the information produced by the LLM/chatbot and is the key mediator between students and the LLM.The study was conducted with 30 students (n=30) in two groups.One group used LLM/chatbot as the core resource for first-time learning the programming language (n=15), while the second group used standard teaching and learning methods (n=15).The results show a significant improvement for first-time learning the programming language with the help of LLM -students showed better results in the assessment, besides being happier with the experience and the learning process.The study also demonstrates potential problems with this method, such as time, resources, accessibility issues, and initial preparation.

Authors

Institutions

Publication Details

Published
2025-01-01
DOI
https://doi.org/10.15308/sinteza-2025-331-336
Primary Topic
Educational Technology and Assessment
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Learning a First Programming Language with LLM Tutor

Milić Vukojičić, Ivana Korica
Educational Technology and Assessment
article

Learning a First Programming Language with LLM Tutor

Milić Vukojičić, Ivana Korica
article en

Abstract

The paper presents the use of Large Language Models (LLM) and Chatbots as tutors when students need to learn novel concepts related to programming.Traditional methods of teaching and learning new programming concepts involve the students and teachers exploring one idea at a time -sequence, selection, and iteration -followed by more complex concepts.Traditional methods include using textbooks, computers, presentations, etc., and the teacher has the central role in the classroom.LLMs can help make complex topics more accessible for teachers to teach and for students to explore.Passive lectures and frontal teaching methods are replaced by the interactive use of LLM/chatbots, where the teacher has a central role in checking the information produced by the LLM/chatbot and is the key mediator between students and the LLM.The study was conducted with 30 students (n=30) in two groups.One group used LLM/chatbot as the core resource for first-time learning the programming language (n=15), while the second group used standard teaching and learning methods (n=15).The results show a significant improvement for first-time learning the programming language with the help of LLM -students showed better results in the assessment, besides being happier with the experience and the learning process.The study also demonstrates potential problems with this method, such as time, resources, accessibility issues, and initial preparation.

Department of Physics, Mathematics and Informatics (BY), Institute of International Politics and Economics (RS)
Quality Education
Openalex Percentile: Top 81%
Educational Technology and Assessment
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.