Massimilano Di Penta, University of Sannio, Italy
BSR lecture: Wednesday July 4th, 9:00-10:30
Title: (Big) Text Analytics to Support Software Development Projects
Abstract: Software development is a very human-intensive activity, in which developers and other stakeholders collaborate by using several unstructured communication channels. While the content of such communication channels constitutes a previous source to support software development, processing it can be challenging. The amount of available data is impressive, just to make an example Stack Overflow has received over 5 million posts per year during the last three years, and popular mobile apps have received a total of several million reviews. As it is not enough, the presence of technical terms and the interleave of source code and natural language make out-of-the-box natural language processing approaches unsuitable (or at least not ideal) to analyze such data.
This talk will outline achievements, challenges, and open problems in the analysis of unstructured software data. More specifically, the talk will overview applications related to mobile app review analytics, extraction of patterns from developers' communication, and the mining of opinion and emotions from software artifacts. Upon discussing the different applications, we will discuss the (in)applicability of standard techniques, and the challenges for customizing them to the software engineering domain.
Last, but not least, the talk will overview the applicability of text mining approaches for the analysis of runtime data, for example in the area of concept location.
Short bio: Massimiliano Di Penta is an associate professor at the University of Sannio, Italy. His research interests include software maintenance and evolution, mining software repositories, empirical software engineering, software testing search-based software engineering, and service-centric software engineering. He authored over 250 papers appeared in international journals, conferences, and workshops, and has received ACM SIGSOFT Distinguished Paper Awards at ICSE, FSE, and ASE, and best/distinguished papers in other conferences, including ICSME, ICPC, CSMR, and WCRE.
He serves and has served the organizing and program committees of more than 100 conferences, including ICSE, FSE, ASE, ICSME. He is member of the steering committee of ASE and MSR, and has previously served the steering committee of ICSME, PROMISE, SSBSE, WCRE, CSMR, SCAM, and IWPSE. He is in the editorial board of the Empirical Software Engineering Journal edited by Springer, and of the Journal of Software: Evolution and Processes edited by Wiley, and has served the editorial board of the IEEE Transactions on Software Engineering.