The paper reports and discusses the results of the PRIN project entitled ‘Active Online Assessment in Higher Education’ (AcOnHE), which focused on the design and implementation of a university assessment framework that integrates Generative Artificial Intelligence (GenAI). The main objective of the project is to develop an AI-based automated system to support the formative and summative assessment of students in traditional, online and blended university courses. The research included an experimental phase with the automated assessment of 397 student e-tivities in a course on Docimology at eCampus University. Initial results indicate substantial consistency between AI-generated assessments and those assigned by lecturers, suggesting that AI can work as a support tool for providing formative feedback, although there are limits when it comes to assessing complex e-tivities such as concept maps. The paper highlights the need to promote AI literacy among both lecturers and students for a transition to hybrid assessment models.
Active Online Assessment in Higher Education: Integrating Generative AI into Formative and Summative Evaluation
Matteo Adamoli;Federica Emanuel
;Marco Rondonotti;Paolo Raviolo
2026-01-01
Abstract
The paper reports and discusses the results of the PRIN project entitled ‘Active Online Assessment in Higher Education’ (AcOnHE), which focused on the design and implementation of a university assessment framework that integrates Generative Artificial Intelligence (GenAI). The main objective of the project is to develop an AI-based automated system to support the formative and summative assessment of students in traditional, online and blended university courses. The research included an experimental phase with the automated assessment of 397 student e-tivities in a course on Docimology at eCampus University. Initial results indicate substantial consistency between AI-generated assessments and those assigned by lecturers, suggesting that AI can work as a support tool for providing formative feedback, although there are limits when it comes to assessing complex e-tivities such as concept maps. The paper highlights the need to promote AI literacy among both lecturers and students for a transition to hybrid assessment models.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
