Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313142332> ?p ?o ?g. }
- W4313142332 endingPage "2458" @default.
- W4313142332 startingPage "2440" @default.
- W4313142332 abstract "Software Defect Prediction (SDP) is one of the most vital and cost-efficient operations to ensure the software quality. However, there exists the phenomenon of class overlap in the SDP datasets (i.e., defective and non-defective modules are similar in terms of values of metrics), which hinders the performance as well as the use of SDP models. Even though efforts have been made to investigate the impact of removing overlapping technique on the performance of SDP, many open issues are still challenging yet unknown. Therefore, we conduct an empirical study to comprehensively investigate the impact of class overlap on SDP. Specifically, we first propose an overlapping instances identification approach by analyzing the class distribution in the local neighborhood of a given instance. We then investigate the impact of class overlap and two common overlapping instance handling techniques on the performance and the interpretation of seven representative SDP models. Through an extensive case study on 230 diversity datasets, we observe that: i) 70.0% of SDP datasets contain overlapping instances; ii) different levels of class overlap have different impacts on the performance of SDP models; iii) class overlap affects the rank of the important feature list of SDP models, particularly the feature lists at the top 2 and top 3 ranks; IV) Class overlap handling techniques could statistically significantly improve the performance of SDP models trained on datasets with over 12.5% overlap ratios. We suggest that future work should apply our KNN method to identify the overlap ratios of datasets before building SDP models." @default.
- W4313142332 created "2023-01-06" @default.
- W4313142332 creator A5005439960 @default.
- W4313142332 creator A5006038775 @default.
- W4313142332 creator A5025184050 @default.
- W4313142332 creator A5027202117 @default.
- W4313142332 creator A5051555459 @default.
- W4313142332 date "2023-04-01" @default.
- W4313142332 modified "2023-10-16" @default.
- W4313142332 title "A Comprehensive Investigation of the Impact of Class Overlap on Software Defect Prediction" @default.
- W4313142332 cites W102369970 @default.
- W4313142332 cites W150336312 @default.
- W4313142332 cites W1541033774 @default.
- W4313142332 cites W1596515083 @default.
- W4313142332 cites W1887734902 @default.
- W4313142332 cites W1971654961 @default.
- W4313142332 cites W1974601952 @default.
- W4313142332 cites W1975040830 @default.
- W4313142332 cites W1982105191 @default.
- W4313142332 cites W1989354793 @default.
- W4313142332 cites W2042699031 @default.
- W4313142332 cites W2045116160 @default.
- W4313142332 cites W2046830558 @default.
- W4313142332 cites W2048456683 @default.
- W4313142332 cites W2069395014 @default.
- W4313142332 cites W2073294644 @default.
- W4313142332 cites W2097883090 @default.
- W4313142332 cites W2099919734 @default.
- W4313142332 cites W2101227285 @default.
- W4313142332 cites W2102636708 @default.
- W4313142332 cites W2105776892 @default.
- W4313142332 cites W2112658968 @default.
- W4313142332 cites W2118283821 @default.
- W4313142332 cites W2125847307 @default.
- W4313142332 cites W2126326838 @default.
- W4313142332 cites W2132887549 @default.
- W4313142332 cites W2135198476 @default.
- W4313142332 cites W2142481192 @default.
- W4313142332 cites W2146338950 @default.
- W4313142332 cites W2147386665 @default.
- W4313142332 cites W2148143831 @default.
- W4313142332 cites W2149014999 @default.
- W4313142332 cites W2151666086 @default.
- W4313142332 cites W2172232422 @default.
- W4313142332 cites W2242800359 @default.
- W4313142332 cites W2276400542 @default.
- W4313142332 cites W2281037394 @default.
- W4313142332 cites W2367798545 @default.
- W4313142332 cites W2408574027 @default.
- W4313142332 cites W2474835145 @default.
- W4313142332 cites W2510620627 @default.
- W4313142332 cites W2516809705 @default.
- W4313142332 cites W2523268328 @default.
- W4313142332 cites W2548915941 @default.
- W4313142332 cites W2587676558 @default.
- W4313142332 cites W2599212561 @default.
- W4313142332 cites W2729440153 @default.
- W4313142332 cites W2731935965 @default.
- W4313142332 cites W2735995639 @default.
- W4313142332 cites W2766521509 @default.
- W4313142332 cites W2783908707 @default.
- W4313142332 cites W2795013017 @default.
- W4313142332 cites W2805001156 @default.
- W4313142332 cites W2808113972 @default.
- W4313142332 cites W2867335562 @default.
- W4313142332 cites W2909172538 @default.
- W4313142332 cites W2954276596 @default.
- W4313142332 cites W2963520355 @default.
- W4313142332 cites W2963548617 @default.
- W4313142332 cites W2981328759 @default.
- W4313142332 cites W2999752750 @default.
- W4313142332 cites W3013745307 @default.
- W4313142332 cites W3034708533 @default.
- W4313142332 cites W3099242135 @default.
- W4313142332 cites W3109072952 @default.
- W4313142332 cites W3127971289 @default.
- W4313142332 cites W420228460 @default.
- W4313142332 cites W4243562335 @default.
- W4313142332 cites W4245807786 @default.
- W4313142332 cites W4250023757 @default.
- W4313142332 cites W752888290 @default.
- W4313142332 doi "https://doi.org/10.1109/tse.2022.3220740" @default.
- W4313142332 hasPublicationYear "2023" @default.
- W4313142332 type Work @default.
- W4313142332 citedByCount "2" @default.
- W4313142332 countsByYear W43131423322023 @default.
- W4313142332 crossrefType "journal-article" @default.
- W4313142332 hasAuthorship W4313142332A5005439960 @default.
- W4313142332 hasAuthorship W4313142332A5006038775 @default.
- W4313142332 hasAuthorship W4313142332A5025184050 @default.
- W4313142332 hasAuthorship W4313142332A5027202117 @default.
- W4313142332 hasAuthorship W4313142332A5051555459 @default.
- W4313142332 hasConcept C114614502 @default.
- W4313142332 hasConcept C116834253 @default.
- W4313142332 hasConcept C119857082 @default.
- W4313142332 hasConcept C124101348 @default.
- W4313142332 hasConcept C138885662 @default.
- W4313142332 hasConcept C154945302 @default.