Textual analysis or natural language parsing? A software engineering perspective
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.