Welcome to The First International Workshop on Evaluation and Analysis of Recommender Systems in Software Engineering (WEARS 2021)

This year WEARS will be co-located with The International Conference on Evaluation and Assessment in Software Engineering (EASE).

Recommender systems in software engineering (RSSE) have gained momentum in recent years. Such systems assist developers in navigating large information spaces and getting instant recommendations that might be helpful to solve their development tasks. Though a lot of improvements have been obtained so far, there is still the need to make RSSE more effective and efficient. Furthermore, while several attempts have been made to improve the recommendation accuracy, little attention has been paid to make such systems robust and resilient to malicious data. In fact, by manipulating training data available in open source software platforms, a hostile user may render recommender systems vulnerable to adversarial attacks, putting software clients at risk. The First International Workshop on Evaluation and Analysis of Recommender Systems in Software Engineering (WEARS 2021) brings in a forum for researchers and practitioners to share, discuss and explore the opportunities and challenges raised by the evaluation and in-depth investigation of RSSE. We solicit research work from the Software Engineering community as well as related fields such as Machine Learning and Recommender Systems.

The topics of interest include, but are by no means limited to:

• Development and evaluation of RSSE.
• Case studies of real-world implementations; Replication of empirical studies on RSSE. – User studies and benchmark for RSSE.
• Machine learning and deep learning for software engineering.
• Use of artificial intelligence techniques for data processing and data augmentation.
• Techniques and tools to curate data for evaluation.
• RSSE for mining open source software repositories.
• Dealing with bias during the evaluation of RSSE.
• Dealing with anonymized and partial data when evaluating RSSE.
• Reusing existing recommender systems that have not been developed for SE tasks.
• Adversarial Machine Learning: Threats, attacks and countermeasures.
• Quantitative versus qualitative analysis of RSSE.

We plan to organize a special issue on an international journal featuring extended, revised paper from the workshop

Tommaso Di Noia is Full Professor of Information and Data Management with the Polytechnic University of Bari, Italy. Currently, his research activity focuses mainly on the themes that revolve around Artificial Intelligence and Data Management with reference to techniques and applications of machine learning and recommender systems. Recently, his attention has shifted to how to exploit the information encoded within Big Data datasets, such as those available thanks to the Linking Open Data initiative, in order to create content-based recommendation engines (content-based) or hybrid ones. On the issue of personalized information access and the modeling of user preferences, innovative solutions have recently been proposed that combine and integrate different aspects, solutions and techniques from Artificial Intelligence. Of great interest to his research is the security of Artificial Intelligence systems with particular reference to Adversarial Machine Learning.