Textual analysis or natural language parsing? A software engineering perspective
- Published
- Accepted
- Subject Areas
- Natural Language and Speech, Software Engineering
- Keywords
- Unstructured Data Mining, Natural Language Parsing, Empirical Study.
- Copyright
- © 2015 Panichella
- Licence
- This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, reproduction and adaptation in any medium and for any purpose provided that it is properly attributed. For attribution, the original author(s), title, publication source (PeerJ PrePrints) and either DOI or URL of the article must be cited.
- Cite this article
- 2015. Textual analysis or natural language parsing? A software engineering perspective. PeerJ PrePrints 3:e1534v1 https://doi.org/10.7287/peerj.preprints.1534v1
Abstract
The problem of designing effective methodology to summarize, and analyze the amount of textual information produced by developers remains particularly challenging especially when the goal is to help developers in making better development/maintenance decisions. Moreover, contrasting results might be obtained depending on the communication channel being mined and the technique adopted for its analysis. In our work we investigate the usage of Natural Language Parsing (NLP) and Textual Analysis (TA) techniques to automatically classify development content. Results of our study highlight the superiority of NLP techniques over the traditional TA techniques when used to analyze the textual data produced in software development. We also show the benefits of NLP when used to enhance software engineering recommenders.
Author Comment
This paper has been under peer review at the European Open Symposium on Empirical Software Engineering: EOSESE'2015.