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 language | English |
---|---|
Title of host publication | IEEE 23rd International Conference on Software Analysis, Evolution, and Reengineering |
Publisher | IEEE |
Pages | 314-325 |
Number of pages | 12 |
ISBN (Electronic) | 978-1-5090-1855-0 |
DOIs | |
Publication status | Published - 23 May 2016 |
Event | SANER 2016: 23rd IEEE International Conference on Software Analysis, Evolution, and Reengineering - Osaka, Japan Duration: 14 Mar 2016 → 18 Mar 2016 |
Conference
Conference | SANER 2016 |
---|---|
Country/Territory | Japan |
City | Osaka |
Period | 14/03/16 → 18/03/16 |
Keywords
- Text-based software engineering
- Search-based software engineering
- Information Retrieval
- Parameter tuning