Valentina Franzoni

Università degli Studi di Perugia | UNIPG · Department of Mathematics and Computer Science

The semantic approach to data linked in social networks uses information extracted from node attributes to quantify the similarity between nodes. In contrast, the topological approach exploits the structural information of the network, e.g., nodes degree, paths, neighbourhood breadth. For a long time, such approaches have been considered substantia...

This work concludes the first study on mouth-based emotion recognition while adopting a transfer learning approach. Transfer learning results are paramount for mouth-based emotion emotion recognition, because few datasets are available, and most of them include emotional expressions simulated by actors, instead of adopting real-world categorisation...

Crowds express emotions as a collective individual, which is evident from the sounds that a crowd produces in particular events, e.g., collective booing, laughing or cheering in sports matches, movies, theaters, concerts, political demonstrations, and riots. A critical question concerning the innovative concept of crowd emotions is whether the emot...

This position paper aims to highlight possible future directions of applications for Affective Computing (AC) and Emotion Recognition (ER) for self-aid applications, as they emerge from the experience of the ACER-EMORE Workshops Series. ER in Artificial Intelligence offers a growing number of problem-solving multidisciplinary opportunities. Most cu...

Artificial Intelligence (AI) is the motor that fuels the most profound revolution in the history of humankind. The new era of information society, even called “the Fourth Revolution”, has produced deep changes into sciences, economies, and societies. This revolution is not only about formal heuristics, or the called “algorithmic society”, but also...

p>In this paper, the innovative approach to sound classification by exploiting the potential of image processing techniques applied to spectrogram representations of audio signals is reviewed. This study shows the effectiveness of incorporating well-established image processing methodologies, such as filtering, segmentation, and pattern recognition...

Editorial on the Research Topic Ethical design of artificial intelligence-based systems for decisionmaking

This paper presents a novel approach for detecting groups of users based on observations of co-occurrences of user behavior. A Deep Neural Network is trained to encode users into a vector representation using an innovative adaptation of the word embedding architecture used in Natural Language Processing, which has been recently applied and modified...

In this study, we present a novel system for the automatic classification of text complexity in the Italian language, focusing on the phraseological dimension. This quantitative assessment of text complexity is crucial for various applications, including text readability measurement, text simplification, and support for educators during evaluation...

The rapid development of Artificial Intelligence (AI) systems has raised significant ethical concerns, particularly with the problem of transparency in their decision-making processes. As AI systems become increasingly integrated into various aspects of society, there is an urgent need to transform these ‘black box’ models into more transparent and...

Artificial Intelligence (AI) is supporting decisions in ways that increasingly affect humans in many aspects of their lives. Both autonomous and decision-support systems applying AI algorithms and data-driven models are used for decisions about justice, education, physical and psychological health, and to provide or deny access to credit, healthcar...

The study proposes and tests a technique for automated emotion recognition through mouth detection via Convolutional Neural Networks (CNN), meant to be applied for supporting people with health disorders with communication skills issues (e.g. muscle wasting, stroke, autism, or, more simply, pain) in order to recognize emotions and generate real-tim...

In this work, a re-design of the Moodledata module functionalities is presented to share learning objects between e-learning content platforms, e.g., Moodle and G-Lorep, in a linkable object format. The e-learning courses content of the Drupal-based Content Management System G-Lorep for academic learning is exchanged designing an object incorporati...

Users of web or chat social networks typically use emojis (e.g., smilies, memes, hearts) to convey in their textual interactions the emotions underlying the context of the communication, aiming for better interpretability, especially for short polysemous phrases. Semantic-based context recognition tools, employed in any chat or social network, can...

Deep learning approaches for facial Emotion Recognition (ER) obtain high accuracy on basic models, e.g., Ekman’s models, in the specific domain of facial emotional expressions. Thus, facial tracking of users’ emotions could be easily used against the right to privacy or for manipulative purposes. As recent studies have shown that deep learning mode...

Learning Management Systems (LMSs) enable teachers and educational institutions to manage the organization of the courses offered and deliver courses in blended form, with LMSs offering support to in-person teaching, or fully online. LMSs, despite having been used for a long time, saw a dramatic increase in usage due to the Covid-19 pandemic; the p...

Information technology is ubiquitously integrated into all areas of human and social life. It becomes progressively critical to build trust in systems while exposing their limitations along with utility and values. The harmonic integration of applications into society will promote the ability of the individuals to positively adapt to change (resili...

In online interactions, users frequently add emojis (e.g., smileys, hearts, angry faces) to text for expressing the emotions behind the communication context, aiming at a better interpretation to text especially of polysemous short expressions. Emotion recognition refers to the automated process of identifying and classifying human emotions. If tex...

From 20 March to 10 May 2020, the “stay at home” countermeasures for the Covid-19 emergency lockdown were defined in the United Kingdom (UK) as leaving home for only the following reasons: “Key worker travelling to work”, “Shopping for basic necessities”, “Any medical need” or “Exercise once a day”. Data collected from the UK Office for National St...

Phraseological complexity plays a critical role in assessing the language competence level necessary to understand or produce text by a language learner and automated tools supporting international certifications for second languages. Appropriate syntactic-based parsing tools for pos/tagging texts are required to efficiently and correctly identify...

Several pathogenic yeast species are resistant to pharmaceutical agents and have evolved so quickly over time that often they cannot be stopped with antifungal treatments. In particular, Candida species can cause yeast infections in patients’ blood or organs, and Candida outbreaks are particularly troublesome, often found in hospitals and healthcar...

ABSTRACT Crowds express emotions as a collective individual, which is evident from the sounds that a crowd produces in particular events, e.g., collective booing, laughing or cheering in sports matches, movies, theaters, concerts, political demonstrations, and riots. Crowd sounds can be characterized by frequency-amplitude features, using analysis...

Binary correlation indices are crucial for forecasting and modelling tasks in different areas of scientific research. The setting of sound binary correlations and similarity measures is a long and mostly empirical interactive process, in which researchers start from experimental correlations in one domain, which usually prove to be effective in oth...

This work proposes an innovative visual tool for real-time continuous learners analytics. The purpose of the work is to improve the design, functionality, and usability of learning management systems to monitor user activity to allow educators to make informed decisions on e-learning design, usually limited to dashboards graphs, tables, and low-usa...

In this work, we present a multi-agent robotic system which explores the use of unpleasant emotions triggered by visual, sound and behavioural affordances of autonomous agents to interact with humans for preserving social distance in public spaces in a context of a pandemic emergency. The idea was born in the context of the Covid-19 pandemic, where...

E-Studium has been a long-running project of blended e-learning for higher education based on the learning management system Moodle, implemented at University of Perugia, Italy from 2005 to 2015. The capstone culminated in a refined final product, at the basis of the actual academic platform Unistudium. In its ten-years activity, e-Studium has been...

The paper concludes the first research on mouth-based Emotion Recognition (ER), adopting a Transfer Learning (TL) approach. Transfer Learning results paramount for mouth-based emotion ER, because a few data sets are available, and most of them include emotional expressions simulated by actors, instead of adopting a real-world categorization. Using...

Humans react to animal emotions, and animals react to human emotions because we share similar emotional and neurological mirroring systems. Mirror neurons fire both when an animal performs an action and when the animal observes the same action performed by another individual. This neurological system has been linked to social behaviors and abilitie...

With the diffusion and successful new implementation of several machine learning techniques, together with the substantial cost decrease of sensors, also included in mobile devices, the field of emotional analysis and modeling has boosted. Apps, web apps, brain-scanning devices, and Artificial Intelligence assistants often include emotion recogniti...

The study proposes and tests a technique for automated emotion recognition through mouth detection via Convolutional Neural Networks (CNN), meant to be applied for supporting people with health disorders with communication skills issues (e.g. muscle wasting, stroke, autism, or, more simply, pain) in order to recognize emotions and generate real-tim...

Concept information can be expressed by text, images or general objects which semantic meaning is clear to a human in a specific cultural context. For a computer, when available, text with its semantics (e.g., metadata, comments, captions) can convey more precise meaning than images or general objects with low-level features (e.g., color distributi...

The G-Lorep project of the European Chemistry Thematic Network (ECTN), based on a federation of distributed repositories of Molecular Science Learning Objects, leverages at present a “hybrid” centralized/distributed architecture in which the central node hosts a shared database. The shared database deals only with the task of managing metadata to t...

In this work, a re-design of the Moodledata module functionalities is presented to share learning objects between e-learning content platforms, e.g., Moodle and G-Lorep, in a linkable object format. The e-learning courses content of the Drupal-based Content Management System G-Lorep for academic learning is exchanged designing an object incorporati...

The work described in this paper attempts to contribute to one of the most stimulating and promising sectors in the field of emotion recognition, which is health care. Multidisciplinary studies in artificial intelligence, augmented reality, and psychology stressed out the importance of emotions in communication and awareness. The intent is the reco...

Purpose The purpose of this paper is to propose and experiment a framework for analysing the tweets to find the basis of popularity of a person and extract the reasons supporting the popularity. Although the problem of analysing tweets to detect popular events and trends has recently attracted extensive research efforts, not much emphasis has been...

In this work we investigate the applicability of binary similarity and distance measures in the context of Link Prediction. Neighbourhood-based similarity measures to assess the similarity of nodes in a network have been long available. They boast the main advantage of low calculation complexity, because only a local view of the network is required...

The robot gAItano is an intelligent hexapod robot, able to move in an environment of unknown size and perform some autonomous actions. It uses the RoboRealm software in order to filter and recognize color blobs in its artificial vision stream, activate a script (VBScript in our case, or C or Python scripts) to compute decisions based on perception,...

Purpose: This paper aims to propose an approach for the analysis of user interest based on tweets, which can be used in the design of user recommendation systems. The extract topics are seen positively by the user. Design/methodology/approach: The proposed approach is based on the combination of sentiment extraction and classification analysis of t...

A soft modelling approach for describing behaviour in on-line user communities is introduced in this work. Behaviour models of individual users in dynamic virtual environments have been described in the literature in terms of timed transition automata; they have various drawbacks. Soft multi/agent behaviour automata are defined and proposed to desc...

Topological link prediction is the task of assessing the likelihood of new future links based on topological properties of entities in a network at a given time. In this paper, we introduce a multistrain bacterial diffusion model for link prediction, where the ranking of candidate links is based on the mutual transfer of bacteria strains via physic...

Each term in a short text can potentially convey emotional meaning. Facebook comments and shared posts often convey human biases, which play a pivotal role in information spreading and content consumption. Such bias is at the basis of human-generated content, and capable of conveying contexts which shape the opinion of users through the social medi...

Knowing and predicting opinions of people is considered a strategic added value, interpreting the qualia i.e., the subjective nature of emotional content. The aim of this work is to study the feasibility of an emotion recognition and automated classification of books according to emotional tags, by means of a lexical and semantic analysis of book b...

In this work, we present SEMO, a Semantic Model for Emotion Recognition, which enables users to detect and quantify the emotional load related to basic emotions hidden in short, emotionally rich sentences (e.g. news titles, tweets, captions). The idea of assessing the semantic similarity of concepts by looking at the occurrences and co-occurrences...

Emotional affordances represent a recently introduced concept which model all the mechanisms used to collect/transmit emotional meaning in the context of human machine interaction. In this work, we introduce and formally define the cognitive role of emotional affordances in a collaboration human-machine dialogue as tools for triggering or recognizi...

This research includes the investigation, design and experimentation of models and measures of semantic and structural proximity for knowledge extraction and link prediction. The aim is to measure, predict and elicit, in particular, data from social or collaborative sources of heterogeneous information. The general idea is to use the information ab...

Sentiment analysis and emotion recognition are emerging research fields of research that aim to build intelligent systems able to recognize and interpret human emotions. Due to the applicability of these systems to almost all kinds of markets, also the interest of companies and industries is grown in an exponential way in the last years and a lot o...

The work described in this paper represents the study and the attempt to make a contribution to one of the most stimulating and promising sectors in the field of emotion recognition, which is health care management. Multidisciplinary studies in artificial intelligence, augmented reality and psychology stressed out the importance of emotions in comm...

The ability of assessing the affective information content is of increasing interest in applications of computer science, e.g. in human machine interfaces, recommender systems, social robots. In this project, the architecture of a semantic system of emotions is designed and implemented, to quantify the emotional content of short sentences by evalua...

Facebook comments and shared posts often convey human biases, which play a pivotal role in information spreading and content consumption, where short information can be quickly consumed, and later ruminated. Such bias is nevertheless at the basis of human-generated content, and being able to extract contexts that does not amplify but represent such...

One of the main problems that emerges in the classic approach to semantics is the difficulty in acquisition and maintenance of ontologies and semantic annotations. On the other hand, the Internet explosion and the massive diffusion of mobile smart devices lead to the creation of a worldwide system, which information is daily checked and fueled by t...

One of the main problems that emerges in the classic approach to semantics is the difficulty in acquisition and maintenance of ontologies and semantic annotations. On the other hand, the Internet explosion and the massive diffusion of mobile smart devices lead to the creation of a worldwide system, which information is daily checked and fueled by t...

In this project we propose a new approach for emotion recognition using web-based similarity (e.g. confidence, PMI and PMING). We aim to extract basic emotions from short sentences with emotional content (e.g. news titles, tweets, captions), performing a web-based quantitative evaluation of semantic proximity between each word of the analyzed sente...

The Internet explosion and the massive diffusion of mobile devices lead to the creation of a worldwide collaborative system, daily used by millions of users through search engines and application interfaces. New paradigms permit to calculate the similarity of terms using only the statistical information returned by a query, or from additional featu...

presentation to the 5th International Workshop on Web-based Collective Evolutionary Systems: models, measures, applications WCES16 July 4-7, 2016, in Beijing, China Held in conjunction with ICCSA 2016

The extraction of semantic contexts is a relevant issue in information retrieval to provide high quality query results. This paper introduces the semantic context underlying a set of given input concepts as defined by the relevant multiple explanation paths connecting the input concepts in a collaborative network. A pheromone-like model based on th...

For link prediction, Common Neighbours (CN) ranking measures allow to discover quality links between nodes in a social network, assessing the likelihood of a new link based on the neighbours frontier of the already existing nodes. A zero rank value is often given to a large number of pairs of nodes, which have no common neighbours, that instead can...

An online collaborative semantic network is explored basing on multi-path traces for extracting latent contextual knowledge. Semantic proximity measures based on search engines are used as heuristics to navigate the collaborative network, in order to find multiple random paths representing traces between seed concepts. The exploration is driven by...

In this paper we introduce a novel model for link prediction in social networks based on a quantitative growth and diffusion model of node features, which are used to compute candidate links ranking. The model is inspired by the biological mechanisms which regulate bacteria reproduction and their transfer among subjects through physical contact. Th...

To measure the semantic similarity among image concepts, we exploit several proximity measurements and different concept ontology similarities: WordNet Distance, Wikipedia Distance, Flickr Distance, Confidence, Normalized Google Distance, Pointwise Mutual Information and PMING. In order to evaluate image similarity in terms of the associated groups...

This research investigates models and algorithms for automatic extraction of the semantics embedded in large collaborative multimedia information sources. An increasing quantity of etherogeneous data are available about multimedia objects. A large amount of users collaboratively chooses, uploads, shares, tags, geotags, comments and links the inform...

This work presents a method based on multi-path traces for eliciting latent contextu-al knowledge from collaborative semantic graphs. The method explores an unknown Web-based collaborative network in order to find multiple random paths, which rep-resent traces between seed concepts. The exploration is driven by an online random-ized walk informed b...

This work introduces a new class of group similarity where different measures are parameterized with respect to a basic similarity defined on the elements of the sets. Group similarity measures are of great interest for many application domains, since they can be used to evaluate similarity of objects in term of the similarity of the associated set...

Most of the best performing link prediction ranking measures evaluate the common neighbourhood of a pair of nodes in a network, in order to assess the likelihood of a new link. On the other hand, the same zero rank value is given to node pairs with no common neighbourhood, which usually are a large number of potentially new links, thus resulting in...

A novel method for the automatic online extraction of contexts from a collaborative explanation network is introduced. The method explores an unknown online collaborative network in order to find multiple explanatory paths between seed concepts. The exploration is driven by an online randomized walk informed by heuristics based on semantic proximit...

Relating, connecting and navigating between concepts represent a major challenge for machine intelligence. On the other hand, collaborative repositories provide a large base of knowledge already filtered, structured, linked and meaningful from a human semantic point of view. Although these repositories are machine accessible, they have no formal ex...

In this paper an approach based on Heuristic Semantic Walk (HSW) is pre-sented, where semantic proximity measures among concepts are used as heu-ristics in order to guide the concept chain search in the collaborative network of Wikipedia, encoding problem-specific knowledge in a problem-independent way. Collaborative information and multimedia repo...

Purpose - In this work, a new general framework is proposed to guide navigation over a collaborative concept network, in order to discover paths between concepts. Finding semantic chains between concepts over a semantic network is an issue of great interest for many applications, such as explanation generation and query expansion. Collaborative con...

The aim of this work is to study the feasibility of an auto- mated classification of books in the social network Zazie by means of the lexical analysis of book blurbs. A supervised learning approach is used to determine if a correlation between the characteristics of a book blurb and the emotional icons associated to the book by the Zazie’s users e...

Sentiment Analysis and Opinion Mining are receiving in- creasing attention in many sectors because knowing and predicting opin- ions of people is considered a strategic added value. In the last years an increasing attention has also been devoted to Emotion Recognition, of- ten by developing automated systems that can associate user's emotions to te...

Path search between concepts over a semantic network is an issue of great interest for many applications, such as explanation generation and query expansion. In this study a new approach is proposed, to guide navigation over a collaborative concept network, in order to discover paths between concepts. The method uses a semantic heuristic based on p...

In this work several semantic approaches to concept-based query expansion and re-ranking schemes are studied and compared with different ontology-based expansion methods in web document search and retrieval. In particular, we focus on concept-based query expansion schemes where, in order to effectively increase the precision of web document retriev...

Path search between concepts over a semantic network is an issue of great interest for many applications, such as explanation generation and query expansion. In this study a new approach is proposed, to guide navigation over a collaborative concept network, in order to discover path between concepts. The method uses a semantic heuristic based on pr...

In this work several semantic approaches to concept-based query expansion and re-ranking schemes are studied and compared with different ontology-based expansion methods in web document search and retrieval. In particular, we focus on concept-based query expansion schemes where, in order to effectively increase the precision of web document retriev...

One of the main problems that emerges in the classic approach to semantics is the difficulty in acquisition and maintenance of ontologies and semantic annotations. On the other hand, the flow of data and documents which are accessible from the Web is continuously fueled by the contribution of millions of users who interact digitally in a collaborat...

One of the main problems that emerges in the classic approach to semantics is the difficulty in acquisition and maintenance of ontologies and semantic annotations. On the other hand, the flow of data and documents which are accessible from the Web is continuously fuelled by the contribution of millions of users who interact digitally in a collabora...

The aim of the present study is to propose a set of guidelines for designing Internet web sites usable and accessible with the Nintendo Wii console. After an accurate analysis of usability issues and of the typical Wii Internet users, twelve usability guidelines will be proposed. These guidelines are focused on visibility, understandability, clicka...

The aim of the present study is to propose a set of guidelines for designing Internet web sites usable and accessible with the Nintendo Wii console. After an accurate analysis of usability issues and the definition of the typical Wii Internet user, twelve usability guidelines will be described. The named guidelines are focused on the visibility, un...