SEmotion 2020

Keynote

Neural Information Processing in Experts’ Program Comprehension Takatomi Kubo, Nara Institute of Science and Technology, Japan

Abstract Software engineering has long been investigating what and how programmers perceive, recognize, and execute in their daily activities of software development and maintenance. In these activities, program comprehension is a dominant cognitive process that consumes a considerable amount of time. Previous studies on program comprehension have revealed that expert programmers exhibit remarkable differences from novices in behavioral performance, knowledge structure, and selective attention. However, the neural processing underlying program comprehension is still poorly understood due to its complexity. We have been tackling this challenging issue by capturing experts’ program comprehension processes using eye tracking and functional magnetic resonance imaging (fMRI). In addition, we have employed advanced analysis methods developed in the field of computational neuroscience and machine learning. In this talk, I will introduce our studies on brain decoding of source code categories and gaze behavior analysis using a deep learning model with several future directions.

Bio Takatomi Kubo is currently an associate professor in the Division of Information Science at Nara Institute of Science and Technology, Japan. He received his B.M. degree from Osaka University, Japan, in 2002 and his Ph.D. degree in engineering from Nara Institute of Science and Technology, Japan, in 2012. He has work experience as a medical doctor in neurology. His research interests include biomedical engineering, neuroscience, and machine learning.

To Label or Not? Advances and Open Challenges in SE-specific Sentiment Analysis Nicole Novielli, University of Bari

Abstract What makes developers happy? What makes them upset? Is it possible to monitor the mood of a developer to determine when and where additional help is needed? How are emotions conveyed in developers’ communication channels and how they affect collaboration? Answering these questions involves being able to reliably implement sentiment analysis, which is the automatic processing of texts to map and capture the polarity of emotions and opinions. In this talk, I will provide an overview of recent research about sentiment analysis in software engineering (SE), address the open challenges, and provide empirically-based guidelines for safe (re)use of SE-specific tools in order to obtain meaningful results.

Bio Nicole Novielli is an Assistant Professor at the University of Bari, where she received a Ph.D. in Computer Science in 2010. Her research interests lie at the intersection of software engineering and affective computing with a specific focus on emotion mining from software repositories, natural language processing of developers’ communication traces, and biometric recognition of developers’ emotions. In 2016, she started the ICSE workshop series on Emotion Awareness in Software Engineering.