@inproceedings{41430a1e5b704314937e3a99f8a52eb7,
title = "Toward a token-based approach to concern detection in MATLAB sources",
abstract = "Matrix and data manipulation programming languages are an essential tool for data analysts. However, these languages are often unstructured and lack modularity mechanisms. This paper presents a business intelligence approach for studying the manifestations of lack of modularity support in that kind of languages. The study is focused on MATLAB as a well established representative of those languages. We present a technique for the automatic detection and quantification of concerns in MATLAB, as well as their exploration in a code base. Ubiquitous Self Organizing Map (UbiSOM) is used based on direct usage of indicators representing different sets of tokens in the code. UbiSOM is quite effective to detect patterns of co-occurrence between multiple concerns. To illustrate, a repository comprising over 35, 000 MATLAB files is analyzed using the technique and relevant conclusions are drawn.",
keywords = "Business intelligence, Concern metrics, Concern mining, MATLAB, Modularity, Self-organizing maps, Token-based technique",
author = "Monteiro, {Miguel P.} and Marques, {Nuno C.} and Bruno Silva and Bruno Palma and Jo{\~a}o Cardoso",
year = "2017",
doi = "10.1007/978-3-319-65340-2_47",
language = "English",
isbn = "978-331965339-6",
volume = "10423 LNAI",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer Verlag",
pages = "573--584",
editor = "Z. Vale and E. Oliveira and J. Gama and Cardoso, {H. Lopes }",
booktitle = "Progress in Artificial Intelligence - 18th EPIA Conference on Artificial Intelligence, EPIA 2017, Proceedings",
address = "Germany",
note = "18th EPIA Conference on Artificial Intelligence, EPIA 2017 ; Conference date: 05-09-2017 Through 08-09-2017",
}