no code implementations • 29 Jan 2021 • Jil Klünder, Regina Hebig, Paolo Tell, Marco Kuhrmann, Joyce Nakatumba-Nabende, Rogardt Heldal, Stephan Krusche, Masud Fazal-Baqaie, Michael Felderer, Marcela Fabiana Genero Bocco, Steffen Küpper, Sherlock A. Licorish, Gustavo Lòpez, Fergal McCaffery, Özden Özcan Top, Christian R. Prause, Rafael Prikladnicki, Eray Tüzün, Dietmar Pfahl, Kurt Schneider, Stephen G. MacDonell
Our results show that 76. 8% of the companies implement hybrid methods.
In our research in this area, with data from open source projects as well as an industrial partner, we noticed several shortcomings of conventional data mining approaches for classification problems: (1) Domain experts' acceptance is of critical importance, and domain experts can provide valuable input, but it is hard to use this feedback.
To determine the importance of change parts, we extract data from software repositories and build prediction models for review remarks based on this data.