Paolo Fantozzi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Paolo Fantozzi has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
- Maurizio Naldi
Department of Law, Economics, Politics, and Modern Languages, LUMSA University, 00192 Rome, Italy
13 shared publications - Luigi Laura
Computer Engineering, Faculty of Engineering, Università Telematica Internazionale UNINETTUNO, 00186 Rome, Italy
4 shared publications - Marco Iecher
Libera Universita Internazionale degli Studi Sociali Guido Carli, Italy
2 shared publications - Paola Dalla Torre
Department of Social Sciences-Communication, Education and Psychology, LUMSA University, 00192 Rome, Italy
2 shared publications - Valerio Rughetti
Libera Università Maria Ss. Assunta, Italy
2 shared publications Caterina Falconi
Department of Agricultural, Food and Environmental Sciences University of Perugia Via S. Costanzo, n.c.n. 06126 Perugia Italy
1 shared publication
Latest Publications
- Open Access
- 22 September 2026
- Published by MDPI AG in Information
- Vol. 17 (10) , 932
Digital Archives in Europe: The Case of Italy
This paper investigates the role of digital television archives in preserving and shaping media memory, focusing on Italy’s Rai Teche. It addresses how digital archives influence collective and national identity through content selection, structuring, and accessibility. A comparative analysis with other European public broadcasters (BBC, INA, ZDF) highlights the Italian model’s strengths and limitations. Using web scraping, we extracted and analyzed metadata from Rai Teche’s catalog, focusing on fiction, variety, theater, health, and quiz shows. The findings reveal significant metadata gaps and inconsistencies, as well as curatorial emphasis on historical content under-representing contemporary genres like news. This study concludes that Rai Teche is a valuable cultural archive, but its interface and editorial choices limit accessibility. Recommendations include enhancing metadata, expanding genre representation, and improving user experience to align with European standards and democratize media memory.
- 22 September 2026
- Published by MDPI AG in Information
- Vol. 17 (10) , 932
Open AccessDigital Archives in Europe: The Case of Italy
This paper investigates the role of digital television archives in preserving and shaping media memory, focusing on Italy’s Rai Teche. It addresses how digital archives influence collective and national identity through content selection, structuring, and accessibility. A comparative analysis with other European public broadcasters (BBC, INA, ZDF) highlights the Italian model’s strengths and limitations. Using web scraping, we extracted and analyzed metadata from Rai Teche’s catalog, focusing on fiction, variety, theater, health, and quiz shows. The findings reveal significant metadata gaps and inconsistencies, as well as curatorial emphasis on historical content under-representing contemporary genres like news. This study concludes that Rai Teche is a valuable cultural archive, but its interface and editorial choices limit accessibility. Recommendations include enhancing metadata, expanding genre representation, and improving user experience to align with European standards and democratize media memory.
- Open Access
- 14 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 61-65
Performance Trade-offs in Explainability-as-a-Service Using Surrogate Linear Models
- 14 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 61-65
Open AccessPerformance Trade-offs in Explainability-as-a-Service Using Surrogate Linear Models
- Open Access
- 30 July 2025
- Published by MDPI AG in Information
- Vol. 16 (8) , 650
Electronic Voting Worldwide: The State of the Art
Electronic voting allows people to participate more easily in their country’s electoral events. Nevertheless, its adoption is still far from widespread. In this paper, we provide a detailed survey of the state of adoption worldwide and investigate which socio-economic factors may influence such an adoption. Its usage is wider in North and South America, while remaining considerably lower in Europe and Asia and practically absent in Africa. We distinguish between e-voting, which maintains the traditional polling station structure while adding technological components, and i-voting, which enables remote participation from any location using personal devices. Five factors (country’s surface and population, Gross Domestic Product, Internet Usage, and Democracy Index) are investigated to predict adoption, and an accuracy of over 79% is achieved through a machine learning random forest model. Larger, wealthier, and more democratic countries are typically associated with a larger adoption of internet voting.
- 30 July 2025
- Published by MDPI AG in Information
- Vol. 16 (8) , 650
Open AccessElectronic Voting Worldwide: The State of the Art
Electronic voting allows people to participate more easily in their country’s electoral events. Nevertheless, its adoption is still far from widespread. In this paper, we provide a detailed survey of the state of adoption worldwide and investigate which socio-economic factors may influence such an adoption. Its usage is wider in North and South America, while remaining considerably lower in Europe and Asia and practically absent in Africa. We distinguish between e-voting, which maintains the traditional polling station structure while adding technological components, and i-voting, which enables remote participation from any location using personal devices. Five factors (country’s surface and population, Gross Domestic Product, Internet Usage, and Democracy Index) are investigated to predict adoption, and an accuracy of over 79% is achieved through a machine learning random forest model. Larger, wealthier, and more democratic countries are typically associated with a larger adoption of internet voting.
- Open Access
- 16 July 2025
- Published by MDPI AG in Preprints.org
Electronic Voting Worldwide: The State of the Art
Electronic voting allows people to participate more easily in their country's electoral events. Nevertheless, its adoption is still far from widespread. In this paper, we provide a detailed survey of the state of adoption worldwide and investigate which socio-economic factors may influence such an adoption. Its usage is wider in North and South America, while remaining considerably lower in Europe and Asia and practically absent in Africa. We distinguish between e-voting, that maintains the traditional polling station structure while adding technological components, and i-voting that enables remote participation from any location using personal devices. Five factors (country's surface and population, Gross Domestic Product, Internet Usage, and Democracy Index) are investigated to predict adoption, and an accuracy of over 93% is achieved through a machine learning random forest model. Larger, more wealthy, and more democratic countries are typically associated with a larger adoption of Internet voting.
- 16 July 2025
- Published by MDPI AG in Preprints.org
Open AccessElectronic Voting Worldwide: The State of the Art
Electronic voting allows people to participate more easily in their country's electoral events. Nevertheless, its adoption is still far from widespread. In this paper, we provide a detailed survey of the state of adoption worldwide and investigate which socio-economic factors may influence such an adoption. Its usage is wider in North and South America, while remaining considerably lower in Europe and Asia and practically absent in Africa. We distinguish between e-voting, that maintains the traditional polling station structure while adding technological components, and i-voting that enables remote participation from any location using personal devices. Five factors (country's surface and population, Gross Domestic Product, Internet Usage, and Democracy Index) are investigated to predict adoption, and an accuracy of over 93% is achieved through a machine learning random forest model. Larger, more wealthy, and more democratic countries are typically associated with a larger adoption of Internet voting.
- 27 February 2025
- Published by Springer Nature in Scientometrics
- Vol. 130 (3) , 1617-1658
The university research assessment dilemma: a decision support system for the next evaluation campaigns
- 27 February 2025
- Published by Springer Nature in Scientometrics
- Vol. 130 (3) , 1617-1658
The university research assessment dilemma: a decision support system for the next evaluation campaigns
- 6 February 2025
- Published by Springer Nature
- p. 244-253
Machine Learning Explainability as a Service: Service Description and Economics
- 6 February 2025
- Published by Springer Nature
- p. 244-253
Machine Learning Explainability as a Service: Service Description and Economics
- 28 December 2024
- Published by Springer Nature
- p. 211-220
Teaching Dataset Creation in a Classroom Environment
- 28 December 2024
- Published by Springer Nature
- p. 211-220
Teaching Dataset Creation in a Classroom Environment
- Open Access
- 28 November 2024
- Published by Springer Nature in Artificial Intelligence and Law
- Vol. 34 (1) , 267-304
Mining EU consultations through AI
- 28 November 2024
- Published by Springer Nature in Artificial Intelligence and Law
- Vol. 34 (1) , 267-304
Open AccessMining EU consultations through AI
- Open Access
- 30 September 2024
- Published by MDPI AG in Information
- Vol. 15 (10) , 603
Uncovering Tourist Visit Intentions on Social Media through Sentence Transformers
The problem of understanding and predicting tourist behavior in choosing their destinations is a long-standing one. The first step in the process is to understand users’ intention to visit a country, which may later translate into an actual visit. Would-be tourists may express their intention to visit a destination on social media. Being able to predict their intention may be useful for targeted promotion campaigns. In this paper, we propose an algorithm to predict visit (or revisit) intentions based on the texts in posts on social media. The algorithm relies on a neural network sentence-transformer architecture using optimized embedding and a logistic classifier. Employing two real labeled datasets from Twitter (now X) for training, the algorithm achieved 90% accuracy and balanced performances over the two classes (visit intention vs. no-visit intention). The algorithm was capable of predicting intentions to visit with high accuracy, even when fed with very imbalanced datasets, where the posts showing the intention to visit were an extremely small minority.
- 30 September 2024
- Published by MDPI AG in Information
- Vol. 15 (10) , 603
Open AccessUncovering Tourist Visit Intentions on Social Media through Sentence Transformers
The problem of understanding and predicting tourist behavior in choosing their destinations is a long-standing one. The first step in the process is to understand users’ intention to visit a country, which may later translate into an actual visit. Would-be tourists may express their intention to visit a destination on social media. Being able to predict their intention may be useful for targeted promotion campaigns. In this paper, we propose an algorithm to predict visit (or revisit) intentions based on the texts in posts on social media. The algorithm relies on a neural network sentence-transformer architecture using optimized embedding and a logistic classifier. Employing two real labeled datasets from Twitter (now X) for training, the algorithm achieved 90% accuracy and balanced performances over the two classes (visit intention vs. no-visit intention). The algorithm was capable of predicting intentions to visit with high accuracy, even when fed with very imbalanced datasets, where the posts showing the intention to visit were an extremely small minority.
- Top Cited PapersOpen Access
The Explainability of Transformers: Current Status and Directions
An increasing demand for model explainability has accompanied the widespread adoption of transformers in various fields of applications. In this paper, we conduct a survey of the existing literature on the explainability of transformers. We provide a taxonomy of methods based on the combination of transformer components that are leveraged to arrive at the explanation. For each method, we describe its mechanism and survey its applications. We find out that attention-based methods, both alone and in conjunction with activation-based and gradient-based methods, are the most employed ones. A growing attention is also devoted to the deployment of visualization techniques to help the explanation process.
Top Cited PapersOpen AccessThe Explainability of Transformers: Current Status and Directions
An increasing demand for model explainability has accompanied the widespread adoption of transformers in various fields of applications. In this paper, we conduct a survey of the existing literature on the explainability of transformers. We provide a taxonomy of methods based on the combination of transformer components that are leveraged to arrive at the explanation. For each method, we describe its mechanism and survey its applications. We find out that attention-based methods, both alone and in conjunction with activation-based and gradient-based methods, are the most employed ones. A growing attention is also devoted to the deployment of visualization techniques to help the explanation process.