Article published in the Journal of Systems and Software
Software Engineering experts from COSMOS project partners Zurich University of Applied Sciences and University of Sannio had an article titled "How to Identify Class Comment Types? - A Multi-language Approach for Class Comment Classification" accepted for publication in the Journal of Systems and Software, which is published by Elsevier and also available online.
The article investigates the different language-specific class commenting practices of three programming languages: Python, Java, and Smalltalk. In particular, it describes the systematic analysis of the similarities and differences of the information types found in class comments of projects developed in these languages. The paper proposes an approach that leverages two techniques — Natural Language Processing and Text Analysis— to automatically identify class comment types.