Last updated on Monday, October 06, 2025
@inproceedings{Biegel2011MSR,
author = {Benjamin Biegel and Quinten David Soetens and
Willi Hornig and Stephan Diehl and Serge Demeyer},
booktitle = {Proceedings {MSR}'11 (8th {IEEE} Working Conference
on Mining Software Repositories)},
month = may,
note = {Acceptance ratio: 20/61 = 32.7\%},
publisher = {{IEEE} Press},
title = {Comparison of Similarity Metrics for Refactoring
Detection},
year = {2011},
abstract = {Identifying refactorings in software archives has
been an active research topic in the last decade,
mainly because it is a prerequisite for various
software evolution analyses (e.g., error detection,
capturing intent of change, capturing and replaying
changes, and relating refactorings and software
metrics). Many of these techniques rely on similarity
measures to identify structurally equivalent code,
however, up until now the effect of this similarity
measure on the performance of the refactoring
identification algorithm is largely unexplored. In
this paper we replicate a well-known experiment from
Wei\ssgerbe and Diehl, plugging in three different
similarity measures (text-based, AST-based,
token-based). We look at the overlap of the results
obtained by the different metrics, and we compare the
results using recall and the computation time. We
conclude that the different result sets have a large
overlap and that the three metrics perform with a
comparable quality.},
annote = {internationalconference},
}