Write a Blog >>
MSR 2018
Mon 28 - Tue 29 May 2018 Gothenburg, Sweden
co-located with * ICSE 2018 *
Tue 29 May 2018 17:08 - 17:15 at E4 room - Modeling and Prediction Chair(s): Abram Hindle

Software is highly contextual. While there are cross-cutting ‘global’ lessons, individual software projects exhibit many ‘local’ properties. This data heterogeneity makes drawing local conclusions from global data dangerous. A key research challenge is to construct locally accurate prediction models that are informed by global characteristics and data volumes. Previous work has tackled this problem using clustering and transfer learning approaches, which identify locally similar characteristics. This paper applies a simpler approach known as Bayesian hierarchical modeling. We show that hierarchical modeling supports cross-project comparisons, while preserving local context. To demonstrate the approach, we conduct a conceptual replication of an existing study on setting software metrics thresholds. Our emerging results show our hierarchical model reduces model prediction error compared to a global approach by up to 50%.

I am open to random chats at any time.

Neil is an assistant professor in the software engineering group.

Neil serves on the steering committee for the International Working Conference on Source Code Analysis and Manipulation (SCAM), is program co-chair, International Conference on Software Architecture, 2018, and associate editor, Journal of Systems and Software.

Neil has worked as a postdoc in software engineering at UBC with Gail Murphy, completed his PhD in Computer Science at the University of Toronto, and received his masters and undergraduate degrees at the University of Victoria. Learn more at neilernst.net.

Tue 29 May

Displayed time zone: Amsterdam, Berlin, Bern, Rome, Stockholm, Vienna change

16:00 - 17:30
Modeling and PredictionTechnical Papers at E4 room
Chair(s): Abram Hindle University of Alberta
Deep Learning Similarities from Different Representations of Source Code
Technical Papers
A: Michele Tufano College of William and Mary, A: Cody Watson , A: Gabriele Bavota Università della Svizzera italiana (USI), A: Massimiliano Di Penta University of Sannio, A: Martin White , A: Denys Poshyvanyk William and Mary
500+ Times Faster Than Deep Learning (A Case Study Exploring Faster Methods for Text Mining StackOverflow)
Technical Papers
A: Suvodeep Majumder , A: Tim Menzies North Carolina State University, A: Nikhila Balaji , A: Katie Brey , A: Wei Fu
Studying the relationship between exception handling practices and post-release defects
Technical Papers
A: Guilherme B. de Pádua Concordia University, Canada, A: Weiyi Shang Concordia University, Canada
Pre-print Media Attached
Analyzing Conflict Predictors in Open-Source Java Projects from GitHub and Travis CI
Technical Papers
A: Paola Accioly Federal University of Pernambuco, Brazil, A: Paulo Borba Federal University of Pernambuco, Brazil, A: Leuson Da Silva Federal University of Pernambuco, A: Guilherme Cavalcanti Federal University of Pernambuco, Brazil
Bayesian Hierarchical Modelling for Tailoring Metric Thresholds
Technical Papers
A: Neil Ernst University of Victoria
DOI Pre-print Media Attached
Discussion phase
Technical Papers