ICSE 2024
Fri 12 - Sun 21 April 2024 Lisbon, Portugal

Onboarding new developers is a challenge for any software project. Addressing this challenge relies on human resources (e.g., having a senior developer write documentation or mentor the new developer). One promising solution is using annotated code tours. While this approach partially lifts the need for mentorship, it still requires a senior developer to write this interactive form of documentation. This paper argues that a Large Language Model (LLM) might help with this documentation process. Our approach is to record the stack trace between a failed test and a faulty method. We then extract code snippets from the methods in this stack trace using CodeQL, a static analysis tool and have them explained by gpt-3.5-turbo-1106, the LLM behind ChatGPT. Finally, we evaluate the quality of a sample of these generated tours using a checklist. We show that the automatic generation of code tours is feasible but has limitations like redundant and low-level explanations.

Sat 20 Apr

Displayed time zone: Lisbon change

16:00 - 17:30
Session 2 - Frontiers of collaborative developmentNLBSE at Maria Helena Vieira da Silva
Chair(s): Andrea Di Sorbo University of Sannio, Maliheh Izadi Delft University of Technology, Sebastiano Panichella Zurich University of Applied Sciences
16:00
20m
Full-paper
Unveiling Disparities: NLP Analysis of Software Industry and Vocational Education Gaps
NLBSE
Emil Bäckstrand Mid Sweden University, Rasmus Djupedal Mid Sweden University, Lena-Maria Öberg Mid Sweden University, Francisco Gomes de Oliveira Neto Chalmers | University of Gothenburg
16:20
15m
Short-paper
Towards LLM-Generated Code Tours for Onboarding
NLBSE
Martin Balfroid , Benoît Vanderose University of Namur, Xavier Devroey University of Namur
DOI Pre-print
16:35
15m
Short-paper
Automated Extraction of Compliance Elements in Software Engineering Contracts Using Natural Language Generation
NLBSE
Gokul Rejithkumar TCS Research, Preethu Rose Anish TCS Research, Pratik Sonar TCS Research, Smita Ghaisas TCS Research
16:50
20m
Full-paper
Emotion Classification In Software Engineering Texts: A Comparative Analysis of Pre-trained Transformers Language Models
NLBSE
Mia Mohammad Imran Virginia Commonwealth University
17:10
15m
Short-paper
Understanding Emojis :) in Useful Code Review Comments
NLBSE
Sharif Ahmed Boise State University, USA, Nasir Eisty Boise State University
17:25
5m
Day closing
Awards & Closing
NLBSE