ICSME 2023
Sun 1 - Fri 6 October 2023 Bogotá, Colombia
Thu 5 Oct 2023 14:25 - 14:36 at Session 2 Room - RGD 04 - Refactoring Chair(s): Massimiliano Di Penta, Oscar Chaparro

The use of machine learning to automate the detection of refactoring candidates is a rapidly evolving research area. The majority of work in this direction uses source code metrics and commit messages to predict refactoring candidates and do not exploit the rich semantics of source code. This paper proposes a new approach for extract method refactoring candidates identification. First, we propose a novel mechanism to identify negative samples for the refactoring candidate identification task. We then employ a self-supervised autoencoder to acquire a compact representation of source code generated by a pre-trained large language model. Subsequently, we train a binary classifier to predict extract method refactoring candidates. Experiments show that our new approach outperforms the state of the art by 30% in terms of F1 score. The proposed work has implications for researchers and practitioners. Software developers may use the proposed automated approach to predict refactoring candidates better. This study will facilitate the development of improved refactoring candidate identification methods that the researchers in the field could use and extend.

Thu 5 Oct

Displayed time zone: Bogota, Lima, Quito, Rio Branco change

13:30 - 15:00
13:30
11m
Talk
Towards a Catalog of Refactorings for Elixir
New Ideas and Emerging Results Track
Lucas Francisco da Matta Vegi Federal University of Minas Gerais (UFMG), Marco Tulio Valente Federal University of Minas Gerais, Brazil
Pre-print
13:41
11m
Talk
An Automated Code Update Tool For Python Packages
Tool Demo Track
Nacho Navarro J.P. Morgan AI Research, Petr Babkin , Salwa Alamir J.P. Morgan AI Research, Sameena Shah J.P. Morgan AI Research
13:52
11m
Talk
Test Code Refactoring Unveiled: Where and How Does It Affect Test Code Quality and Effectiveness?
Registered Reports Track
Fabio Palomba University of Salerno, Ivan Machado Federal University of Bahia
14:03
11m
Talk
Towards Code Improvements Suggestions from Client Exception Analysis
New Ideas and Emerging Results Track
Diego Marcilio USI Università della Svizzera italiana, Carlo A. Furia Università della Svizzera italiana (USI)
Pre-print
14:14
11m
Talk
Deterministic Automatic Refactoring at Scale
Tool Demo Track
14:25
11m
Talk
Automatic Refactoring Candidate Identification Leveraging Effective Code Representation
New Ideas and Emerging Results Track
Indranil Palit Dalhousie University, Gautam Shetty Dalhousie University, Hera Arif Dalhousie University, Tushar Sharma Dalhousie University
Pre-print
14:36
11m
Talk
RefSearch: A Search Engine for Refactoring
Tool Demo Track
Motoki Abe Tokyo Institute of Technology, Shinpei Hayashi Tokyo Institute of Technology
DOI Pre-print
14:47
13m
Live Q&A
1:1 Q&A
Research Track