Publications

A User Evaluation of Process Discovery Algorithms in a Software Engineering Company

Published in The 23rd IEEE Int. Conference on Enterprise Computing (EDOC’19). Paris, France, 28-31 October, 2019

This paper provides a systematic comparative evaluation of existing implementations of automated process discovery methods with domain experts by using a real-life event log extracted from an international software engineering company and four quality metrics: understandability, correctness, precision, and usefulness. The evaluation results highlight gaps and unexplored trade-offs in the field and allow researchers to improve the lacks in the automated process discovery methods in terms of usability of process discovery techniques in industry.

Verifying Petri Net-Based Process Models using Automated Planning

Published in Workshop on Strategic Modeling and Reasoning meets Process Mining (SMRPM’19), held in conjuction with the 23rd IEEE Int. Conference on Enterprise Computing (EDOC’19). Paris, France, 28-31 October, 2019

In this paper, starting from a Petri net-based representation of a BP model, we show how instances of the verification problem can be represented as planning problems in PDDL (Planning Domain Definition Language) for which planners can find a correct solution in a finite amount of time. If verification problems are converted into planning problems, one can seamlessly leverage the best performing automated planners, with evident advantages in terms of versatility and customization.

Generating Personalized Narrative Experiences in Interactive Storytelling through Automated Planning

Published in The 13th Biannual Conference of the Italian SIGCHI Chapter (CHItaly’19). Padova, Italy, 23-25 September, 2019

In this paper, we discussed how the use of automated planning techniques in Artificial Intelligence can be employed to generate personalized narrative experiences in interactive storytelling. We showed the feasibility of our approach through a mobile application for cultural heritage based on mini games, whose order of presentation is dynamically determined to increase the user engagement in museum like spaces.

Research Challenges for Intelligent Robotic Process Automation

Published in Workshop on Artificial Intelligence for Business Process Management (AI4BPM’19), held in conjuction with the 17th Int. Conference on Business Process Management (BPM'19). Vienna, Austria 1-6 September, 2019

In this paper, after an in-depth experimentation of the RPA tools available in the market, we developed a classification framework to categorize them on the basis of some key dimensions. Then, starting from this analysis, we derived four research challenges necessary to inject intelligence into current RPA technology.

Synthesis of Strategies for Robotic Process Automation

Published in The 27th Italian Symposium on Advanced Database System (SEBD’19). Castiglione della Pescaia, Italy, 16-19 June, 2019

This PhD paper presents my research proposal: Robotic Process Automation is an umbrella term for tools that run on an end user’s computer, emulating tasks previously executed through a user interface by means of a software robot. Nowadays, only simple, predictable tasks can be automated in situations where there is no room for interpretation, while more sophisticated work is still left to human experts. The here proposed research aims at tackling this issue through a paradigm shift in conceiving software robots that are able to behave intelligently and flexibly in many dynamic and knowledge-intensive situations that are common in today’s application scenarios.

Download here

Achieving GDPR Compliance of BPMN Process Models

Published in The 31st Int. Conference on Advanced Information Systems Engineering (CAiSE’19). Rome, Italy, 3-7 June, 2019

This paper provides an analysis of the main privacy constraints in GDPR and propose a set of design patterns to capturing and integrating such constraints in BP models. Using BPMN (Business Process Modeling Notation) as modeling notation, our approach allows us to achieve full transparency of privacy constraints in BPs making it possible to ensure their compliance with GDPR.