Back to search

École de technologie supérieure

On the effect of data mining techniques on recommending source code changes

Abstract

dc:description

Past and recent research has leveraged data mining to build approaches and techniques that can guide developers during their source code changes. To the best of our knowledge, very few works have investigated advanced data mining techniques (e.g., FP-Growth, Relim, or Eclat, etc.) and--or compared their results with other algorithms or a baseline. In this paper, we suggest an automatic approach to recommend source code changes using four data mining algorithms, Apriori, FP-Growth, Eclat and Relim. We consider Apriori, the widely-adopted data mining algorithm, as our baseline. We not only recommend source code changes using these four data mining algorithms, but we also provide an empirical evaluation of their performances using different configurations and explore how these different configurations affect the relevance of the produced recommendations. Our empirical study involves seven open-source projects from which we have extracted source change history at the file level. We have compared the results in terms of precision, recall, and F-measure by considering as our baseline, the Apriori algorithm. Our findings bring empirical evidence on the fact that although some advanced algorithms may, in some cases, perform better than basic algorithms such as Apriori, the results depend on the change history, type of applied data mining techniques, the nature and characteristics of the projects including total number of transactions. We believe the research community working in this area can leverage these findings when selecting data mining algorithms to build their recommenders for source code changes.

Degree

thesis:*
Name thesis:degree_name
Mémoire de maîtrise électronique
Level thesis:degree_level
masters
Grantor dc:publisher
École de technologie supérieure
Year dc:date
2022

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Khalilazar, Saeed

Subjects

dc:subject × 1

Rights

Language dc:language
en

Identifiers

dc:identifier.*
Identifier
INSERT-YOUR-LIBRARY-ID-HERE2997

Chain of custody

source
Harvested from
ETS (Quebec)
Base URL
espace.etsmtl.ca/cgi/oai2
Last updated
2026-11-18
Source record
OAI-PMH GetRecord
citation

Khalilazar, Saeed. On the effect of data mining techniques on recommending source code changes. masters thesis, École de technologie supérieure, 2022.