Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

An Overview of User Feedback Classification Approaches

: Santos, Rubens; Groen, Eduard C.; Villela, Karina

Fulltext ()

Spoletini, P.:
REFSQ-2019. REFSQ Workshops, Doctoral Symposium, Live Studies Track, and Poster Track. Online resource : Joint Proceedings of REFSQ-2019 Workshops, Doctoral Symposium, Live Studies Track, and Poster Track co-located with the 25th International Conference on Requirements Engineering: Foundation for Software Quality (REFSQ 2019), Essen, Germany, March 18th, 2019
La Clusaz: CEUR, 2019 (CEUR Workshop Proceedings 2376)
Art. 11, 10 pp.
International Conference on Requirements Engineering - Foundation for Software Quality (REFSQ) <25, 2019, Essen>
Conference Paper, Electronic Publication
Fraunhofer IESE ()
Computer software selection and evaluation; Learning algorithms; Machine learning; Natural language processing systems; Requirements engineering

Online user feedback about software products is a promising source of user requirements. To allow scaling analyses to large amounts of user feedback, research on Crowd-based Requirements Engineering (CrowdRE) seeks to tailor natural language processing (NLP) techniques to Requirements Engineering (RE). Various frameworks have been proposed, but it remains largely unclear why particular NLP techniques are better suited for CrowdRE than others, which makes it hard to make a well-founded choice for a technique. We found that CrowdRE research most often uses machine learning (ML) and has so far applied twelve clusters of ML algorithms and seven clusters of ML features. The prevalent algorithm–feature pair is Na¨ıve Bayes with Bag of Words – Term Frequency (BOW-TF), followed by Support Vector Machines (SVM) with BOW-TF. An initial comparison of the reported precision and recall suggests that classifications in RE need further improvement. Our research presents a preliminary overview of the current landscape of automated classification techniques for RE whose results may inspire researchers to apply new strategies to advance research in this field, or to include ML models they had not considered previously in their benchmarks.