Roberta Ferrario
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Roberta Ferrario has a total of 57 co-authors. Here are the top co-authors by number of shared publications:
Marco Cristani
9 shared publications- Francesco Setti
Section of Engineering and Physics, Department of Engineering for Innovation Medicine, University of Verona, Verona, Italy
7 shared publications - Nicola Guarino
ISTC-CNR Laboratory for Applied Ontology
6 shared publications - Daniele Porello
Università di Genova
5 shared publications - Alessandro Mosca
Free University of Bozen-Bolzano
2 shared publications - Chiara Bassetti
Department of Sociology and Social Research, University of Trento, Trento, Italy
2 shared publications
Latest Publications
- 1 November 2025
- Published by SAGE Publications in Applied Ontology
- Vol. 20 (4) , 381-403
An Observational Approach to Representing Interpretation
Research in the Digital Humanities requires computer systems that can document and analyze interpretations of creative works, such as literary texts. These systems are designed to provide access to existing interpretations and identify their similarities and differences. To this end, we propose an approach to formally representing interpretations. In particular, we develop an ontology of observations aimed at capturing, through what we call observational vocabularies, what interpreters claim about the texts that they interpret. We distinguish between different types of observations, in particular, basic observations, which represent specific and domain-dependent claims (e.g., regarding the analysis of literary characters’ traits), and observations such as assertion, denial, support, and defeat to document more nuanced claims. We also introduce formal mechanisms that can be used to analyze particular (sets of) observations, texts, and so on. Throughout the article, we illustrate the discussion with examples from literary studies.
- 1 November 2025
- Published by SAGE Publications in Applied Ontology
- Vol. 20 (4) , 381-403
An Observational Approach to Representing Interpretation
Research in the Digital Humanities requires computer systems that can document and analyze interpretations of creative works, such as literary texts. These systems are designed to provide access to existing interpretations and identify their similarities and differences. To this end, we propose an approach to formally representing interpretations. In particular, we develop an ontology of observations aimed at capturing, through what we call observational vocabularies, what interpreters claim about the texts that they interpret. We distinguish between different types of observations, in particular, basic observations, which represent specific and domain-dependent claims (e.g., regarding the analysis of literary characters’ traits), and observations such as assertion, denial, support, and defeat to document more nuanced claims. We also introduce formal mechanisms that can be used to analyze particular (sets of) observations, texts, and so on. Throughout the article, we illustrate the discussion with examples from literary studies.
- Open Access
- 27 October 2025
- Published by Springer Nature in AI & SOCIETY
- Vol. 41 (2) , 825-842
Leveraging teleological explanation to support general-purpose AI assessment
AI technologies are ubiquitous, manifesting in various forms and applications. Nowadays, many of them are presented as being general purpose , though this sometimes translates into having unclear purposes . Within this landscape, establishing normative criteria for the functioning of (some of) these artefacts has grown increasingly complex. In this work, we advocate the use of teleological explanation as a suitable ally in addressing the challenges arising in this scenario. We defend the idea that teleological explanation is particularly useful in the case of artefacts in general, and we discuss how, with some adaptation, it can be leveraged to support the assessment of AI artefacts according to their purpose(s). Our contribution is thus threefold: (1) exploiting some of the assumptions adopted in teleological explanation to support the clarification of (general-purpose) AI artefacts’ purpose(s); (2) assisting in the comparison and assessment of AIs via metrics inspired by the literature concerning teleological explanation; and (3) providing insights for defining a unified framework for designing AI benchmarks.
- 27 October 2025
- Published by Springer Nature in AI & SOCIETY
- Vol. 41 (2) , 825-842
Open AccessLeveraging teleological explanation to support general-purpose AI assessment
AI technologies are ubiquitous, manifesting in various forms and applications. Nowadays, many of them are presented as being general purpose , though this sometimes translates into having unclear purposes . Within this landscape, establishing normative criteria for the functioning of (some of) these artefacts has grown increasingly complex. In this work, we advocate the use of teleological explanation as a suitable ally in addressing the challenges arising in this scenario. We defend the idea that teleological explanation is particularly useful in the case of artefacts in general, and we discuss how, with some adaptation, it can be leveraged to support the assessment of AI artefacts according to their purpose(s). Our contribution is thus threefold: (1) exploiting some of the assumptions adopted in teleological explanation to support the clarification of (general-purpose) AI artefacts’ purpose(s); (2) assisting in the comparison and assessment of AIs via metrics inspired by the literature concerning teleological explanation; and (3) providing insights for defining a unified framework for designing AI benchmarks.
- Open Access
- 5 May 2025
- Published by Springer Nature in Philosophy & Technology
- Vol. 38 (2) , 1-33
The bewitching AI: The Illusion of Communication with Large Language Models
We investigate the ‘bewitchment’ of understanding interactions between humans and systems based on large language models (LLMs) inspired by Wittgenstein’s later view on language. This framework is particularly apt for analyzing human-LLM interaction as it treats understanding as a public phenomenon manifested in observable communicative practices, rather than as a mental or computational state—an approach especially valuable given LLMs’ inherent opacity. Drawing on this perspective, we show that successful communication requires not merely regularity in language use, but constancy in maintaining reference points through agreement in both definitions and judgments. Crucially, LLMs lack the constancy needed to track negations and contradictions throughout a dialogue, thereby disrupting the reference points necessary for genuine communication. The apparent understanding in human-LLM interactions arises from what we characterize as a ‘bewitchment’: the interaction between LLMs’ statistical adherence to linguistic patterns and humans’ tendency to blindly follow familiar language games. Moreover, when interaction with LLMs is based on stereotyped contexts in which the system seems capable of identifying reference points, we humans automatically apply the practical principle that there is understanding until proven otherwise. The bewitchment becomes thus more profound as LLMs improve in modeling stereotypical aspects of human interaction. This improvement, far from addressing the highlighted limitations, can only deepen the illusion of understanding, raising significant concerns for meaningful control over such systems.
- 5 May 2025
- Published by Springer Nature in Philosophy & Technology
- Vol. 38 (2) , 1-33
Open AccessThe bewitching AI: The Illusion of Communication with Large Language Models
We investigate the ‘bewitchment’ of understanding interactions between humans and systems based on large language models (LLMs) inspired by Wittgenstein’s later view on language. This framework is particularly apt for analyzing human-LLM interaction as it treats understanding as a public phenomenon manifested in observable communicative practices, rather than as a mental or computational state—an approach especially valuable given LLMs’ inherent opacity. Drawing on this perspective, we show that successful communication requires not merely regularity in language use, but constancy in maintaining reference points through agreement in both definitions and judgments. Crucially, LLMs lack the constancy needed to track negations and contradictions throughout a dialogue, thereby disrupting the reference points necessary for genuine communication. The apparent understanding in human-LLM interactions arises from what we characterize as a ‘bewitchment’: the interaction between LLMs’ statistical adherence to linguistic patterns and humans’ tendency to blindly follow familiar language games. Moreover, when interaction with LLMs is based on stereotyped contexts in which the system seems capable of identifying reference points, we humans automatically apply the practical principle that there is understanding until proven otherwise. The bewitchment becomes thus more profound as LLMs improve in modeling stereotypical aspects of human interaction. This improvement, far from addressing the highlighted limitations, can only deepen the illusion of understanding, raising significant concerns for meaningful control over such systems.
- Open Access
- 18 June 2024
- Published by Springer Nature in Minds and Machines
- Vol. 34 (3) , 1-35
A Teleological Approach to Information Systems Design
In recent years, the design and production of information systems have seen significant growth. However, these information artefacts often exhibit characteristics that compromise their reliability. This issue appears to stem from the neglect or underestimation of certain crucial aspects in the application of Information Systems Design (ISD). For example, it is frequently difficult to prove when one of these products does not work properly or works incorrectly (falsifiability), their usage is often left to subjective experience and somewhat arbitrary choices (anecdotes), and their functions are often obscure for users as well as designers (explainability). In this paper, we propose an approach that can be used to support the analysis and re-(design) of information systems grounded on a well-known theory of information, namely, teleosemantics. This approach emphasizes the importance of grounding the design and validation process on dependencies between four core components: the producer (or designer), the produced (or used) information system, the consumer (or user), and the design (or use) purpose. We analyze the ambiguities and problems of considering these components separately. We then present some possible ways in which they can be combined through the teleological approach. Also, we debate guidelines to prevent ISD from failing to address critical issues. Finally, we discuss perspectives on applications over real existing information technologies and some implications for explainable AI and ISD.
- 18 June 2024
- Published by Springer Nature in Minds and Machines
- Vol. 34 (3) , 1-35
Open AccessA Teleological Approach to Information Systems Design
In recent years, the design and production of information systems have seen significant growth. However, these information artefacts often exhibit characteristics that compromise their reliability. This issue appears to stem from the neglect or underestimation of certain crucial aspects in the application of Information Systems Design (ISD). For example, it is frequently difficult to prove when one of these products does not work properly or works incorrectly (falsifiability), their usage is often left to subjective experience and somewhat arbitrary choices (anecdotes), and their functions are often obscure for users as well as designers (explainability). In this paper, we propose an approach that can be used to support the analysis and re-(design) of information systems grounded on a well-known theory of information, namely, teleosemantics. This approach emphasizes the importance of grounding the design and validation process on dependencies between four core components: the producer (or designer), the produced (or used) information system, the consumer (or user), and the design (or use) purpose. We analyze the ambiguities and problems of considering these components separately. We then present some possible ways in which they can be combined through the teleological approach. Also, we debate guidelines to prevent ISD from failing to address critical issues. Finally, we discuss perspectives on applications over real existing information technologies and some implications for explainable AI and ISD.
- Open Access
- 30 September 2023
- Published by Association for Computing Machinery (ACM) in Journal on Computing and Cultural Heritage
- Vol. 16 (3) , 1-5
Editorial: Special Issue on Semantic Web and Ontology Design for Cultural Heritage
- 30 September 2023
- Published by Association for Computing Machinery (ACM) in Journal on Computing and Cultural Heritage
- Vol. 16 (3) , 1-5
Open AccessEditorial: Special Issue on Semantic Web and Ontology Design for Cultural Heritage
- Open Access
- 29 April 2021
- Published by MDPI AG in Brain Sciences
- Vol. 11 (5) , 572
Expect the Worst! Expectations and Social Interactive Decision Making
Psychological studies have demonstrated that expectations can have substantial effects on choice behavior, although the role of expectations on social decision making in particular has been relatively unexplored. To broaden our knowledge, we examined the role of expectations on decision making when interacting with new game partners and then also in a subsequent interaction with the same partners. To perform this, 38 participants played an Ultimatum Game (UG) in the role of responders and were primed to expect to play with two different groups of proposers, either those that were relatively fair (a tendency to propose an equal split—the high expectation condition) or unfair (with a history of offering unequal splits—the low expectation condition). After playing these 40 UG rounds, they then played 40 Dictator Games (DG) as allocator with the same set of partners. The results showed that expectations affect UG decisions, with a greater proportion of unfair offers rejected from the high as compared to the low expectation group, suggesting that players utilize specific expectations of social interaction as a behavioral reference point. Importantly, this was evident within subjects. Interestingly, we also demonstrated that these expectation effects carried over to the subsequent DG. Participants allocated more money to the recipients of the high expectation group as well to those who made equal offers and, in particular, when the latter were expected to behave unfairly, suggesting that people tend to forgive negative violations and appreciate and reward positive violations. Therefore, both the expectations of others’ behavior and their violations play an important role in subsequent allocation decisions. Together, these two studies extend our knowledge of the role of expectations in social decision making.
- 29 April 2021
- Published by MDPI AG in Brain Sciences
- Vol. 11 (5) , 572
Open AccessExpect the Worst! Expectations and Social Interactive Decision Making
Psychological studies have demonstrated that expectations can have substantial effects on choice behavior, although the role of expectations on social decision making in particular has been relatively unexplored. To broaden our knowledge, we examined the role of expectations on decision making when interacting with new game partners and then also in a subsequent interaction with the same partners. To perform this, 38 participants played an Ultimatum Game (UG) in the role of responders and were primed to expect to play with two different groups of proposers, either those that were relatively fair (a tendency to propose an equal split—the high expectation condition) or unfair (with a history of offering unequal splits—the low expectation condition). After playing these 40 UG rounds, they then played 40 Dictator Games (DG) as allocator with the same set of partners. The results showed that expectations affect UG decisions, with a greater proportion of unfair offers rejected from the high as compared to the low expectation group, suggesting that players utilize specific expectations of social interaction as a behavioral reference point. Importantly, this was evident within subjects. Interestingly, we also demonstrated that these expectation effects carried over to the subsequent DG. Participants allocated more money to the recipients of the high expectation group as well to those who made equal offers and, in particular, when the latter were expected to behave unfairly, suggesting that people tend to forgive negative violations and appreciate and reward positive violations. Therefore, both the expectations of others’ behavior and their violations play an important role in subsequent allocation decisions. Together, these two studies extend our knowledge of the role of expectations in social decision making.
- Open Access
- 22 November 2020
- Published by Springer Nature in Synthese
- Vol. 199 (1-2) , 3367-3403
Hybrid collective intentionality
The theory of collective agency and intentionality is a flourishing field of research, and our understanding of these phenomena has arguably increased greatly in recent years. Extant theories, however, are still ill-equipped to explain certain aspects of collective intentionality. In this article we draw attention to two such underappreciated (and intertwined) aspects: the failure of the intentional states of collectives to supervene on the intentional states of their members, and the role of non-human factors in collective agency and intentionality (‘hybrid’ collective intentionality). We propose a theory of collective intentionality which builds on the ‘interpretationist’ tradition in metasemantics and the philosophy of mind as initiated by David Lewis and recently developed further by Robbie Williams. The collective-level analogue of interpretationism turns out to look different in some ways from the individual-level theory, but is well-suited to accommodating phenomena such as hybrid collective intentionality. Complemented with Kit Fine’s theory of variable embodiment, such a theory also provides a diachronic account of intentional collectives.
- 22 November 2020
- Published by Springer Nature in Synthese
- Vol. 199 (1-2) , 3367-3403
Open AccessHybrid collective intentionality
The theory of collective agency and intentionality is a flourishing field of research, and our understanding of these phenomena has arguably increased greatly in recent years. Extant theories, however, are still ill-equipped to explain certain aspects of collective intentionality. In this article we draw attention to two such underappreciated (and intertwined) aspects: the failure of the intentional states of collectives to supervene on the intentional states of their members, and the role of non-human factors in collective agency and intentionality (‘hybrid’ collective intentionality). We propose a theory of collective intentionality which builds on the ‘interpretationist’ tradition in metasemantics and the philosophy of mind as initiated by David Lewis and recently developed further by Robbie Williams. The collective-level analogue of interpretationism turns out to look different in some ways from the individual-level theory, but is well-suited to accommodating phenomena such as hybrid collective intentionality. Complemented with Kit Fine’s theory of variable embodiment, such a theory also provides a diachronic account of intentional collectives.
- 20 February 2018
- Published by SAGE Publications in Applied Ontology
- Vol. 13 (1) , 1
Editorial announcement: Editorial Board changes
- 20 February 2018
- Published by SAGE Publications in Applied Ontology
- Vol. 13 (1) , 1
Editorial announcement: Editorial Board changes
- 13 March 2017
- Published by SAGE Publications in Applied Ontology
- Vol. 12 (1) , 1-4
Applied Ontology: A foreword by the new Editors-in-Chief
- 13 March 2017
- Published by SAGE Publications in Applied Ontology
- Vol. 12 (1) , 1-4
Applied Ontology: A foreword by the new Editors-in-Chief
- 15 December 2015
- Published by Springer Nature
- p. 32-46
Towards a Conceptualization of Sociomaterial Entanglement
- 15 December 2015
- Published by Springer Nature
- p. 32-46
Towards a Conceptualization of Sociomaterial Entanglement