Francesca Fallucchi
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
Francesca Fallucchi has a total of 100 co-authors. Here are the top co-authors by number of shared publications:
- Ernesto William De Luca
Computer Science, Otto-von-Guericke University, Magdeburg, Germany
16 shared publications - Fabio Massimo Zanzotto
University of Rome “Tor Vergata”, Rome, Italy
9 shared publications - Romeo Giuliano
Department of Engineering Science, Guglielmo Marconi University, Rome, Italy
9 shared publications - Leonardo Ranaldi
University of Edinburgh, Edinburgh, United Kingdom and Human-centric ART, University of Rome Tor Vergata, Rome, Italy
5 shared publications - Noemi Scarpato
San Raffaele Rome University
5 shared publications Ernesto William De Luca
Guglielmo Marconi University, Rome, Italy
4 shared publications
Latest Publications
- 3 October 2026
- Published by Springer Nature
- p. 241-254
Optimizing Input Representations for Word-in-Context: A Controlled Ablation Study
- 3 October 2026
- Published by Springer Nature
- p. 241-254
Optimizing Input Representations for Word-in-Context: A Controlled Ablation Study
- Open Access
- 29 June 2026
- Published by MDPI AG in Future Internet
- Vol. 18 (7) , 342
Advances in Smart Environments and Digital Twin: Current Trends and Future Directions
Ubiquitous miniaturisation and increasing computer performance allow technical solutions to be used more often in everyday life to support end users
- 29 June 2026
- Published by MDPI AG in Future Internet
- Vol. 18 (7) , 342
Open AccessAdvances in Smart Environments and Digital Twin: Current Trends and Future Directions
Ubiquitous miniaturisation and increasing computer performance allow technical solutions to be used more often in everyday life to support end users
- Open Access
- 24 March 2026
- Published by MDPI AG in Big Data and Cognitive Computing
- Vol. 10 (4) , 102
Emotional Framing in Prompts Modulates Large Language Model Performance
Large Language Models (LLMs) demonstrate remarkable performance across a variety of natural language understanding tasks, yet their sensitivity to emotional framing in user prompts remains underexplored. This paper presents an empirical study investigating how four emotional tones—joy, apathy, anger, and fear—affect LLM performance on the SuperGLUE benchmark. We evaluate five instruction-tuned, open-weight models across eight diverse tasks, systematically modulating input prompts with affective cues while keeping semantic content constant. Results reveal that prompts framed with joy and apathy lead to consistently higher accuracy, with gains of up to 4.5 percentage points compared to fear-framed inputs, which yield the lowest performance. These findings demonstrate that affective modulation in user prompts measurably impacts LLM reasoning and task outcomes, suggesting that emotional framing is not merely stylistic but functionally relevant to model behavior. Our study provides a reproducible experimental framework and an open-source prompt set, offering a foundation for future research on affect-aware prompting strategies and their implications in human–AI interaction.
- 24 March 2026
- Published by MDPI AG in Big Data and Cognitive Computing
- Vol. 10 (4) , 102
Open AccessEmotional Framing in Prompts Modulates Large Language Model Performance
Large Language Models (LLMs) demonstrate remarkable performance across a variety of natural language understanding tasks, yet their sensitivity to emotional framing in user prompts remains underexplored. This paper presents an empirical study investigating how four emotional tones—joy, apathy, anger, and fear—affect LLM performance on the SuperGLUE benchmark. We evaluate five instruction-tuned, open-weight models across eight diverse tasks, systematically modulating input prompts with affective cues while keeping semantic content constant. Results reveal that prompts framed with joy and apathy lead to consistently higher accuracy, with gains of up to 4.5 percentage points compared to fear-framed inputs, which yield the lowest performance. These findings demonstrate that affective modulation in user prompts measurably impacts LLM reasoning and task outcomes, suggesting that emotional framing is not merely stylistic but functionally relevant to model behavior. Our study provides a reproducible experimental framework and an open-source prompt set, offering a foundation for future research on affect-aware prompting strategies and their implications in human–AI interaction.
- Open Access
- 16 February 2026
- Published by MDPI AG in Future Internet
- Vol. 18 (2) , 105
A Hybrid LoRa/ZigBee IoT Mesh Architecture for Real-Time Performance Monitoring in Orienteering Sport Competitions: A Measurement Campaign on Different Environments
The sport of orienteering requires athletes to reach specific points marked on a map (called “punching stations”) in the shortest possible time. Currently, the recording of athletes’ passages through the stations is performed offline. In addition to delays in generating intermediate and final rankings, this approach often leads to detection errors and potential cheating related to the lack of authentication of an athlete’s actual passage at a given station. This paper aims to define and design a system enabling three main functionalities: 1. real-time monitoring of athletes’ trajectories through a sensor network connected to control stations; 2. multi-modal authentication of athletes at each station; and 3. immutable certification of each athlete’s passage through blockchain-based recording. System performance is evaluated in terms of wireless network coverage and data collection efficiency across three representative environments: urban, rural, and forested areas. Results are obtained through a measurement campaign for two dedicated wireless technologies: ZigBee for local mesh network and LoRa for long-range links to connect local mesh networks to the cloud over the Internet, which is then accessed by the race organizers. Furthermore, two supporting subsystems are described, addressing athlete authentication and data integrity assurance, as well as a blockchain recording for the overall event management framework. Results are in terms of coverage distances for both technologies, proving highly effective across varied terrains. Field tests demonstrated significant communication capabilities, achieving distances of up to 1800 m in open spaces. Even in challenging, dense wooded environments, the system maintained reliable coverage, reaching transmission distances of up to 600 m. Local ZigBee links between punching stations achieved ranges between 70 and 150 m in forested areas. These findings validate the use of a wireless multi-hop network designed to minimize packet loss and ensure reliable data delivery in competitive scenarios. The feasibility is also investigated in terms of WSN performance, delay analysis and power consumption evaluation.
- 16 February 2026
- Published by MDPI AG in Future Internet
- Vol. 18 (2) , 105
Open AccessA Hybrid LoRa/ZigBee IoT Mesh Architecture for Real-Time Performance Monitoring in Orienteering Sport Competitions: A Measurement Campaign on Different Environments
The sport of orienteering requires athletes to reach specific points marked on a map (called “punching stations”) in the shortest possible time. Currently, the recording of athletes’ passages through the stations is performed offline. In addition to delays in generating intermediate and final rankings, this approach often leads to detection errors and potential cheating related to the lack of authentication of an athlete’s actual passage at a given station. This paper aims to define and design a system enabling three main functionalities: 1. real-time monitoring of athletes’ trajectories through a sensor network connected to control stations; 2. multi-modal authentication of athletes at each station; and 3. immutable certification of each athlete’s passage through blockchain-based recording. System performance is evaluated in terms of wireless network coverage and data collection efficiency across three representative environments: urban, rural, and forested areas. Results are obtained through a measurement campaign for two dedicated wireless technologies: ZigBee for local mesh network and LoRa for long-range links to connect local mesh networks to the cloud over the Internet, which is then accessed by the race organizers. Furthermore, two supporting subsystems are described, addressing athlete authentication and data integrity assurance, as well as a blockchain recording for the overall event management framework. Results are in terms of coverage distances for both technologies, proving highly effective across varied terrains. Field tests demonstrated significant communication capabilities, achieving distances of up to 1800 m in open spaces. Even in challenging, dense wooded environments, the system maintained reliable coverage, reaching transmission distances of up to 600 m. Local ZigBee links between punching stations achieved ranges between 70 and 150 m in forested areas. These findings validate the use of a wireless multi-hop network designed to minimize packet loss and ensure reliable data delivery in competitive scenarios. The feasibility is also investigated in terms of WSN performance, delay analysis and power consumption evaluation.
- Open Access
- 13 February 2026
- Published by MDPI AG in Forecasting
- Vol. 8 (1) , 17
Satellite Data and Artificial Intelligence for FINtech
The SAIFIN project (Satellite data and Artificial Intelligence for FINtech) develops a novel algorithmic trading system that integrates satellite imagery, financial data, and advanced artificial intelligence to enhance decision-making, particularly in commodity and agricultural markets. This paper presents the motivation, design, implementation, and validation of the SAIFIN framework. Leveraging alternative data and modular multi-agent architectures, SAIFIN aims to deliver robust, context-aware trading signals in diverse market conditions.
- 13 February 2026
- Published by MDPI AG in Forecasting
- Vol. 8 (1) , 17
Open AccessSatellite Data and Artificial Intelligence for FINtech
The SAIFIN project (Satellite data and Artificial Intelligence for FINtech) develops a novel algorithmic trading system that integrates satellite imagery, financial data, and advanced artificial intelligence to enhance decision-making, particularly in commodity and agricultural markets. This paper presents the motivation, design, implementation, and validation of the SAIFIN framework. Leveraging alternative data and modular multi-agent architectures, SAIFIN aims to deliver robust, context-aware trading signals in diverse market conditions.
- 26 February 2025
- Published by Springer Nature
- p. 197-213
The Convergence of Open Data, Linked Data, Ontologies, and Large Language Models: Enabling Next-Generation Knowledge Systems
- 26 February 2025
- Published by Springer Nature
- p. 197-213
The Convergence of Open Data, Linked Data, Ontologies, and Large Language Models: Enabling Next-Generation Knowledge Systems
- Open Access
- 12 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 158207-158214
Using Distributional Models for Studying the Influence of School Textbooks in Children Bias
School textbooks have a profound influence on shaping the thoughts of young individuals. Reducing sex, gender, and race bias in these educational materials is then an imperative social goal. Despite efforts to address bias, historical and contemporary textbooks have been found to perpetuate stereotyped associations: efficient techniques like word embeddings can be used to analyze a wide range of school textbooks to assess the presence of stereotyped biases. In this paper, we use Artificial Intelligence to test what happens if people are exposed to some textbooks or others. Our procedure can be used for in-silico testing of the persuasive power of textbooks. For this purpose, we introduce ChildDM, a model constructed from a corpus of children’s free-produced language, and its domain-adapted version, ChildDM-School, trained on a collection of school textbooks. Leveraging the Word Embedding Association Test (WEAT) framework, we investigate how biases evolve in the language of children after exposition to historical textbooks. While historical textbooks tend to avoid explicit gender-based stereotypes in the scientific and artistic domains, they still conceal biases. Specifically, women are associated with caregiving and family-related activities.
- 12 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 158207-158214
Open AccessUsing Distributional Models for Studying the Influence of School Textbooks in Children Bias
School textbooks have a profound influence on shaping the thoughts of young individuals. Reducing sex, gender, and race bias in these educational materials is then an imperative social goal. Despite efforts to address bias, historical and contemporary textbooks have been found to perpetuate stereotyped associations: efficient techniques like word embeddings can be used to analyze a wide range of school textbooks to assess the presence of stereotyped biases. In this paper, we use Artificial Intelligence to test what happens if people are exposed to some textbooks or others. Our procedure can be used for in-silico testing of the persuasive power of textbooks. For this purpose, we introduce ChildDM, a model constructed from a corpus of children’s free-produced language, and its domain-adapted version, ChildDM-School, trained on a collection of school textbooks. Leveraging the Word Embedding Association Test (WEAT) framework, we investigate how biases evolve in the language of children after exposition to historical textbooks. While historical textbooks tend to avoid explicit gender-based stereotypes in the scientific and artistic domains, they still conceal biases. Specifically, women are associated with caregiving and family-related activities.
- Open Access
- 11 June 2024
- Published by MDPI AG in Applied Sciences
- Vol. 14 (12) , 5083
Puzzle Pattern, a Systematic Approach to Multiple Behavioral Inheritance Implementation in Object-Oriented Programming
Object-oriented programming (OOP) has long been a dominant paradigm in software development, but it is not without its challenges. One major issue is the problem of tight coupling between objects, which can hinder flexibility and make it difficult to modify or extend code. Additionally, the complexity of managing inheritance hierarchies can lead to rigid and fragile designs, making it hard to maintain and evolve the software over time. This paper introduces a software development pattern that seeks to offer a renewed approach to writing code in object-oriented (OO) environments. Addressing some of the limitations of the traditional approach, the Puzzle Pattern focuses on extreme modularity, favoring writing code exclusively in building blocks that do not possess a state (e.g., Java interfaces that support concrete methods definitions in interfaces starting from version 8). Concrete classes are subsequently assembled through the implementation of those interfaces, reducing coupling and introducing a new level of flexibility and adaptability in software construction. The highlighted pattern offers significant benefits in software development, promoting extreme modularity through interface-based coding, enhancing adaptability via multiple inheritance, and upholding the SOLID principles, though it may pose challenges such as complexity and a learning curve for teams.
- 11 June 2024
- Published by MDPI AG in Applied Sciences
- Vol. 14 (12) , 5083
Open AccessPuzzle Pattern, a Systematic Approach to Multiple Behavioral Inheritance Implementation in Object-Oriented Programming
Object-oriented programming (OOP) has long been a dominant paradigm in software development, but it is not without its challenges. One major issue is the problem of tight coupling between objects, which can hinder flexibility and make it difficult to modify or extend code. Additionally, the complexity of managing inheritance hierarchies can lead to rigid and fragile designs, making it hard to maintain and evolve the software over time. This paper introduces a software development pattern that seeks to offer a renewed approach to writing code in object-oriented (OO) environments. Addressing some of the limitations of the traditional approach, the Puzzle Pattern focuses on extreme modularity, favoring writing code exclusively in building blocks that do not possess a state (e.g., Java interfaces that support concrete methods definitions in interfaces starting from version 8). Concrete classes are subsequently assembled through the implementation of those interfaces, reducing coupling and introducing a new level of flexibility and adaptability in software construction. The highlighted pattern offers significant benefits in software development, promoting extreme modularity through interface-based coding, enhancing adaptability via multiple inheritance, and upholding the SOLID principles, though it may pose challenges such as complexity and a learning curve for teams.
- Open Access
- 2 May 2024
- Published by MDPI AG in Preprints.org
Puzzle Pattern, a Systematic Approach to Multiple Behavioral Inheritance Implementation in OOP
Object-Oriented Programming (OOP) has long been a dominant paradigm in software development, but it's not without its challenges. One major issue is the problem of tight coupling between objects, which can hinder flexibility and make it difficult to modify or extend code. Additionally, the complexity of managing inheritance hierarchies can lead to rigid and fragile designs, making it hard to maintain and evolve the software over time. This paper introduces a software development pattern that seeks to offer a renewed approach to writing code in Object-Oriented (OO) environments. Addressing some of the limitations of the traditional approach, the Puzzle Pattern focuses on extreme modularity, favoring writing code exclusively in interfaces. Concrete classes are subsequently assembled through the implementation of those interfaces, reducing coupling and introducing a new level of flexibility and adaptability in software construction. The highlighted pattern offers significant benefits in software development, promoting extreme modularity through interface-based coding, enhancing adaptability via multiple inheritance, and upholding the SOLID principles, though it may pose challenges such as complexity and a learning curve for teams.
- 2 May 2024
- Published by MDPI AG in Preprints.org
Open AccessPuzzle Pattern, a Systematic Approach to Multiple Behavioral Inheritance Implementation in OOP
Object-Oriented Programming (OOP) has long been a dominant paradigm in software development, but it's not without its challenges. One major issue is the problem of tight coupling between objects, which can hinder flexibility and make it difficult to modify or extend code. Additionally, the complexity of managing inheritance hierarchies can lead to rigid and fragile designs, making it hard to maintain and evolve the software over time. This paper introduces a software development pattern that seeks to offer a renewed approach to writing code in Object-Oriented (OO) environments. Addressing some of the limitations of the traditional approach, the Puzzle Pattern focuses on extreme modularity, favoring writing code exclusively in interfaces. Concrete classes are subsequently assembled through the implementation of those interfaces, reducing coupling and introducing a new level of flexibility and adaptability in software construction. The highlighted pattern offers significant benefits in software development, promoting extreme modularity through interface-based coding, enhancing adaptability via multiple inheritance, and upholding the SOLID principles, though it may pose challenges such as complexity and a learning curve for teams.
- 24 November 2023
- Published by Emerald Publishing in Journal of Documentation
- Vol. 80 (2) , 378-391
The digital transformation processes for supporting digital humanities researchers in text analysis
Purpose: This article aims to explore how the mapping strategies between user requirements expressed by the humanities researchers lead to a better customization of user-driven digital humanities tools and to the creation of innovative functionalities, which can directly affect the way of doing research in a digital context.Design/methodology/approach: It describes the user-driven development of a tool that helps researchers in the quantitative and qualitative analysis of large textbook collections.Findings: This article presents an exemplary user journey map, which shows the different steps of the digital transformation process and how the humanities researchers are involved for (1) producing innovative research solutions, comprehensive and personalized reports, and (2) customizing access to content data used for the analysis of digital documents. The article is based on a case study on a German textbooks collection and content analysis functionalities.Originality/value: The focus of this article is the reiterative research process, in which humanists (from the human centred point of view) starts from an initial research question, using quantitative and qualitative data and develops both the research question and the answers to it by with the aim to find patterns in the content and structure of educational media. Thus, from the viewpoint of digital transformation the humanist is part of the interaction between digitization and digitalization processes, where he/she uses digital data, metadata, reports and findings created and supported by the digital tools for research analysis.
- 24 November 2023
- Published by Emerald Publishing in Journal of Documentation
- Vol. 80 (2) , 378-391
The digital transformation processes for supporting digital humanities researchers in text analysis
Purpose: This article aims to explore how the mapping strategies between user requirements expressed by the humanities researchers lead to a better customization of user-driven digital humanities tools and to the creation of innovative functionalities, which can directly affect the way of doing research in a digital context.Design/methodology/approach: It describes the user-driven development of a tool that helps researchers in the quantitative and qualitative analysis of large textbook collections.Findings: This article presents an exemplary user journey map, which shows the different steps of the digital transformation process and how the humanities researchers are involved for (1) producing innovative research solutions, comprehensive and personalized reports, and (2) customizing access to content data used for the analysis of digital documents. The article is based on a case study on a German textbooks collection and content analysis functionalities.Originality/value: The focus of this article is the reiterative research process, in which humanists (from the human centred point of view) starts from an initial research question, using quantitative and qualitative data and develops both the research question and the answers to it by with the aim to find patterns in the content and structure of educational media. Thus, from the viewpoint of digital transformation the humanist is part of the interaction between digitization and digitalization processes, where he/she uses digital data, metadata, reports and findings created and supported by the digital tools for research analysis.