Using IR methods for labeling source code artifacts: Is it worthwhile?
- 1 June 2012
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10928138,p. 193-202
Abstract
Information Retrieval (IR) techniques have been used for various software engineering tasks, including the labeling of software artifacts by extracting “keywords” from them. Such techniques include Vector Space Models, Latent Semantic Indexing, Latent Dirichlet Allocation, as well as customized heuristics extracting words from specific source code elements. This paper investigates how source code artifact labeling performed by IR techniques would overlap (and differ) from labeling performed by humans. This has been done by asking a group of subjects to label 20 classes from two Java software systems, JHotDraw and eXVantage. Results indicate that, in most cases, automatic labeling would be more similar to human-based labeling if using simpler techniques - e.g., using words from class and method names - that better reflect how humans behave. Instead, clustering-based approaches (LSI and LDA) are much more worthwhile to be used on source code artifacts having a high verbosity, as well as for artifacts requiring more effort to be manually labeled.Keywords
This publication has 35 references indexed in Scilit:
- CodeTopics2011
- Modeling the evolution of topics in source code histories2011
- Validating the Use of Topic Models for Software Evolution2010
- Supporting program comprehension with source code summarization2010
- Summarizing software artifacts2010
- Hierarchical relational models for document networksThe Annals of Applied Statistics, 2010
- A theory of aspects as latent topics2008
- Using the Conceptual Cohesion of Classes for Fault Prediction in Object-Oriented SystemsIEEE Transactions on Software Engineering, 2008
- An Application of Latent Dirichlet Allocation to Analyzing Software Evolution2008
- 10.1162/jmlr.2003.3.4-5.993Applied Physics Letters, 2000