Graphy Publications
Inspiring Innovations & Discoveries
International Journal of Computer & Software Engineering Volume 1 (2016), Article ID 1:IJCSE-104, 9 pages
https://doi.org/10.15344/2456-4451/2016/104
Research Article
Can Opinion Mining Techniques Help to Select Open Source Software?

Davide Taibi

Faculty of Computer Science, Free University of Bozen, 1, Bolzano BZ, Italy
Dr. Davide Taibi, Faculty of Computer Science, Free University of Bozen, 1, Bolzano BZ, Italy; E-mail: davide.taibi@unibz.it
20 January 2016; 08 June 2016; 10 June 2016
Taibi D (2016) Can Opinion Mining Techniques Help to Select Open Source Software? Int J Comput Softw Eng 1: 104. doi: https://doi.org/10.15344/2456-4451/2016/104

Abstract

People and organizations that are considering the adoption of Open-Source Software (OSS), or that need to choose among different OSS products are interested in knowing the user community’s opinion, since this can provide useful indications about the strengths and limits of the software being evaluated. While several methods for the evaluation of the community size are available, there is no automated support to the extraction of the opinions of the community. In this paper we explore whether it is possible to support the OSS selection process by means of automated sentiment analysis techniques. Our goal is to understand if the actual opinion mining techniques, can be applied to get valuable opinions on OSS software. Our goal will be achieved first developing a web crawler to extract user generated content on OSS, building a data-set of relevant user generated then we apply the opinion mining process the OSS blogs data-set. We collected more than 88K user generated content and we compared the performance of our opinion mining technique with a set of existing opinion mining tools. Results of the application of our technique show that opinion mining can help to evaluate the opinions of OSS products. However, the existing opinion mining tools, even if applicable in different domains, are still not reliable in the domain of OSS, mainly because they are trained on different data-sets, opening new research directions for future work in the opinion mining domain.