Parameterizing and Assembling IR-Based Solutions for SE Tasks Using Genetic Algorithms

A. Panichella, Bogdan Dit, Rocco Oliveto, Massimiliano Di Penta, Denys Poshyvanyk, Andrea De Lucia

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

Abstract

Information Retrieval (IR) approaches are nowadays used to support various software engineering tasks, such as feature location, traceability link recovery, clone detection, or refactoring. However, previous studies showed that inadequate instantiation of an IR technique and underlying process could significantly affect the performance of such approaches in terms of precision and recall. This paper proposes the use of Genetic Algorithms (GAs) to automatically configure and assemble an IR process for software engineering tasks. The approach (named GA-IR) determines the (near) optimal solution to be used for each stage of the IR process, i.e., term extraction, stop word removal, stemming, indexing and an IR algebraic method calibration. We applied GA-IR on two different software engineering tasks, namely traceability link recovery and identification of duplicate bug reports. The results of the study indicate that GA-IR outperforms approaches previously published in the literature, and that it does not significantly differ from an ideal upper bound that could be achieved by a supervised and combinatorial approach.
Original languageEnglish
Title of host publicationIEEE 23rd International Conference on Software Analysis, Evolution, and Reengineering
PublisherIEEE
Pages314-325
Number of pages12
ISBN (Electronic)978-1-5090-1855-0
DOIs
Publication statusPublished - 23 May 2016
EventSANER 2016: 23rd IEEE International Conference on Software Analysis, Evolution, and Reengineering - Osaka, Japan
Duration: 14 Mar 201618 Mar 2016

Conference

ConferenceSANER 2016
CountryJapan
CityOsaka
Period14/03/1618/03/16

Keywords

  • Text-based software engineering
  • Search-based software engineering
  • Information Retrieval
  • Parameter tuning

Fingerprint Dive into the research topics of 'Parameterizing and Assembling IR-Based Solutions for SE Tasks Using Genetic Algorithms'. Together they form a unique fingerprint.

Cite this