Enriching the Semantic Representation of the Source Code with Natural Language-Based Features from Comments for Improving the Performance of Software Defect Prediction.
Anamaria BriciuMihaiela LupeaGabriela CzibulaIstván Gergely CzibulaPublished in: ENASE (2024)
Keyphrases
- semantic representation
- source code
- natural language
- open source
- software systems
- conceptual graphs
- software defect prediction
- feature extraction
- feature vectors
- knowledge representation
- written in natural language
- ensemble learning
- text categorization
- feature set
- natural language processing
- information retrieval
- classification accuracy
- case study
- data sets