Legal and administrative sources typically describe procedural steps that are not recorded in structured data, which makes the application of process-oriented analysis particularly challenging. In this work, we present an approach that uses Large Language Models (LLMs) to extract events and dates from unstructured legal texts. The methodology is applied to a dataset of Italian procurement notices published since 2022 on the official EU platform, Tenders Electronic Daily (TED), demonstrating how LLMs can extract valuable information, such as administrative decisions adopted prior to tender publication. These elements are incorporated into existing event logs, thereby enhancing the quality of process analysis. A sample of the extracted data has been manually reviewed by legal experts to assess the relevance and correctness of the automated detection. The results suggest that this approach can help identify procedural steps hidden in free text, thereby supporting more complete and accurate representations of legal workflows.

Abstract The rise of e-learning systems has revolutionized education, enabling the collection of valuable students’ activity data for continuous improvement. While existing studies have predominantly focused on prolonged learning paths, short-term tutorials offer a flexible and efficient alternative that is recently gaining increasing popularity. This article presents a methodology for investigating e-learning systems for short-term tutorials leveraging user behavior tracking and process mining techniques. A case study involving a web-based tutorial with approximately one hour of learning explores the learning processes of 250 students in Italy. The study analyzes learning outcomes and investigates the impact of different learning paths on student progress. The research questions concern i) the extraction of activity flows in short-term tutorials; ii) the prediction of outcomes in the early stages of short-term learning process. The proposed approach provides descriptive insights into the learning process which can also be used to offer prescriptive guidance.

With the proliferation of e-procurement systems in the public sector, valuable and open information sources can be jointly accessed. Our research aims to explore different legal Open Data; in particular, we explored the data set of the National Anti-Corruption Authority in Italy on public procurement and the judges’ sentences related to public procurement, published on the website of the Italian Administrative Justice from 2007 to 2022. Our first goal was to train machine learning models capable of automatically recognizing which procurement has led to disputes and consequently complaints to the Administrative Justice, identifying the relevant features of procurement that correspond to certain anomalies. Our second goal was to develop a recommender system on procurement to return similar procurement to a given one and find companies for bidders, depending on the procurement requirements.