2023, Presentazione, ITA
Gloria Bordogna (1) Giuliana Rubbia (2)
Recentemente, ChatGPT si è posto all'attenzione di addetti ai lavori, media, e società, in modo intrigante e controverso. "Offre funzionalità senza precedenti per analizzare dati, collaborare e condividere conoscenze. Tuttavia, è necessario considerare attentamente le implicazioni etiche e preservare le competenze umane" (Florindo, 2023). "Uno strumento per insegnare, non per imbrogliare" (Rose, 2023). Riguardo gli strumenti basati su Intelligenza Artificiale quali i sistemi di Natural Language Processing, pattern recognition e robotica, e quindi i sistemi come ChatGPT, sono stati già messi in evidenza i bias di genere e le problematiche di traduzione e riconoscimento automatici così come le raccomandazioni (Badaloni&Lisi 2020, Ferilli et al. 2020, O'Connor&Liu 2023, UNESCO 2020). Nello specifico, (Gross 2023) ha rilevato come ChatGPT funzioni in modo efficiente ed efficace nel sintetizzare e rigenerare informazione condivisa su Web, il che significa che senza moderazioni può perpetuare stereotipi di genere radicati nella società. Tuttavia, la natura evolutiva di tali sistemi può diventare un volano per correggere i bias e quindi per migliorare la società. Il contributo intende presentare i risultati di un esperimento con domande e risposte rivolte e ottenute da ChatGPT nell'estate 2023 su varie tematiche che presentano un'evidente dimensione di genere, per aprire la discussione su risposte afflitte o meno da pregiudizi e considerazioni di utilizzo.
2023, Presentazione, ENG
Laura Criscuolo (1), Gloria Bordogna (2), Lucia Laurenza (2) e Alba L'Astorina (2)
This contribution describes the process of designing and conducting a Citizen Science experience involving an extended research community in a study of fertility of urban soils, carried out within the BRIDGES project (Building reflexivity and response-ability involving different narratives of knowledge and science).
2023, Mostra, ITA
Daniela Stroppiana, Gloria Bordogna, Mirco Boschetti, Mariano Bresciani, Gabriele Candiani, Paola Carrara, Francesco Casu, Alberto Crema, Giacomo De Carolis, Francesca De Santi (1), Claudia Giardino, Mario Gomarasca, Alba L'Astorina, Lucia Laurenza, Simone Lella, Francesco Mastromauro, Francesco Nutini, Alessandro Oggioni, Monica Pepe, Gianluca Planamente (2), Roberta Pozzi, Paolo Tagliolato, Paolo Villa
Per celebrare il centenario dalla fondazione del CNR, l'Istituto IREA sede di Milano ha organizzato una mostra multimediale e autoguidata che, attraverso immagini spettacolari acquisite da satelliti (in particolare Sentinel-2 del programma europeo Copernicus), offre visualizzazioni inedite della superficie terrestre. Le immagini spaziano dai deserti agli oceani ed evidenziano nicchie di biodiversità e peculiarità ambientali di immenso fascino e valore. La mostra si è rivolta in particolare ai giovani con l'intento di stimolare l'interesse del pubblico ai temi ambientali e al loro studio tramite il telerilevamento da satellite. Inoltre, è stata un'occasione per diffondere e approfondire i metodi e i contributi dei ricercatori IREA-CNR alla ricerca sul telerilevamento, attraverso alcuni brevi video sulla mappatura degli ecosistemi acquatici e delle aree incendiate, la qualità delle acque, lo sviluppo delle colture agricole, l'indagine dei cambiamenti climatici. La mostra si è avvalsa della collaborazione nell'ambito di un PCTO (percorso per le competenze trasversali e l'orientamento ) di alcuni studenti del Liceo scientifico Donatelli Pascal di Milano che coordinati dal Prof. Gianluca Planamente e dalla collega Francesca De Santi hanno realizzato una mostra virtuale con interviste ai ricercatori IREA. Hanno visitato la mostra 4 classi liceali e diversi colleghi ricercatori di altri istituti , studenti del Politecnico di Milano e dell'Università Statale di Milano e Bicocca, e numerosi cittadini per un totale di circa 300 persone.
2023, Articolo in rivista, ENG
Troels Andreasen and Gloria Bordogna and Guy De Trè and Janusz Kacprzyk and Henrik Legind Larsen and Slawomir Zadrozny
The popularity of chatbots, such as ChatGPT, has brought research attention to question answering systems, capable to generate natural language answers to user's natural language queries. However, also in other kinds of systems, flexibility of querying, including but also going beyond the use of natural language, is an important feature. With this consideration in mind the paper presents a critical and comprehensive analysis of recent developments, trends and challenges of Flexible Query Answering Systems (FQASs). Flexible query answering is a multidisciplinary research field that is not limited to question answering in natural language, but comprises other query forms and interaction modalities, which aim to provide powerful means and techniques for better reflecting human preferences and intentions to retrieve relevant information. It adopts methods at the crossroad of several disciplines among which Information Retrieval (IR), databases, knowledge based systems, knowledge and data engineering, Natural Language Processing (NLP) and the semantic web may be mentioned. The analysis principles are inspired by the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) framework, characterized by a top-down process, starting with relevant keywords for the topic of interest to retrieve relevant articles from meta-sources And complementing these articles with other relevant articles from seed sources Identified by a bottom-up process. to mine the retrieved publication data a network analysis is performed Which allows to present in a synthetic way intrinsic topics of the selected publications. issues dealt with are related to query answering methods Both model-based and data-driven (the latter based on either machine learning or deep learning) And to their needs for explainability and fairness to deal with big data Notably by taking into account data veracity. conclusions point out trends and challenges to help better shaping the future of the FQAS field.
2023, Curatela di atti di convegno (conference proceedings), ENG
Henrik Legind Larsen (1) Maria J. Martin-Bautista (2) M. Dolores Ruiz (2) Troels Andreasen (3) Gloria Bordogna (4) Guy De Tré (5)
This volume constitutes the Proceedings of the 15th International Conference on Flexible Query Answering Systems, FQAS 2023, held in Palma de Mallorca, Spain, 5-7 September 2023, collocated with EUSFLAT 2023. The biennial FQAS conference series has been running since 1994, starting in Roskilde, Denmark, where it also was held in 1996, 1998 and 2009; in 2000 it was held in Warsaw, Poland; in 2002 in Copenhagen, Denmark; in 2004 in Lyon, France; in 2006 in Milan, Italy; in 2011 in Ghent, Belgium; in 2013 in Granada, Spain; in 2015 in Cracow, Poland; in 2017 in London, UK; in 2019 in Amantea, Italy; and in 2021 in Bratislava, Slovakia. FQASis the premier conference concerned with the very important issue of providing users of information systems with flexible querying capabilities, and with easy and intuitive access to information. More specifically, the overall theme of the FQAS conferences is the modelling and design of innovative and flexible modalities for accessing information systems. The main objective is to achievemore expressive, informative, cooperative, and productive systems which facilitate retrieval from information repositories such as databases, libraries, heterogeneous archives, and the web.
2023, Articolo in rivista, ENG
Bordogna, Gloria and Carrara, Paola and Frigerio, Luca and Lella, Simone
The current practice of users searching for different types of geo-resources in a geographic area and wishing to identify the most convenient routes for visiting the most relevant ones, requires the iterative formulation of several queries: first to identify the more interesting resources and then to select the best route to visit them. In order to simplify this process, in this paper a novel functionality for a geographic information retrieval (GIR) system is proposed, which retrieves and ranks several routes for visiting a number of relevant georeferenced resources as a result of a single query, named flexible trip-planning query. An original retrieval model is defined to identify the relevant resources and to rank the most convenient routes by taking into account personal user preferences. To this end, a graph-based algorithm is defined, exploiting prioritized aggregation to optimize the routes’ identification and ranking. The proposed algorithm is applied in the proof-of-concept of a Smart cOmmunity-based Geographic infoRmation rEtrievAl SysTem (SO-GREAT) designed to strengthen local communities: it collects and manages open data from regional authorities describing categories of authoritative territorial resources and services, such as schools, hospitals, etc., and from volunteered geographic services (VGSs) created by citizens to offer services in their neighbourhood.
2023, Contributo in volume, ENM
Gloria Bordogna
Human intelligence has been an object of investigation since the beginning of the research on information science to provide artificial agents with human-like decision making skills. This research field has led to the development of algorithms that try to simulate human reasoning. Several theories have been defined to model decisions in the presence of uncer-tain, imprecise and vague information, based on both subjective and qualitative criteria, expressed linguistically. Today, we are at an epochal turning point in which there are no longer at-tempts to reproduce human reasoning by machines, but algorithms are de-signed as networks of interconnected simple computational units learning to take decisions from examples. This data-driven paradigm simulates children learning from observations, so that their behavior evolves by accumulation of experience. Nevertheless, are we sure that purely learning from data is an effective sufficient method, not affected by bias, and that it can lead to fair systems that we can trust? Are we satisfied with completing a task without know-ing "how" it was performed? Are we sure that children don't have, a priori, more complex and structured mechanisms regulating as well as directing their learning ability? The chapter discusses how decison support systems models have changed and what are future perspectives.
2023, Contributo in volume, ENG
Robert Laurini, Peter Nijkamp, Gloria Bordogna, Karima Kourtit, Fabien Duchateau, Antonio Rinaldi, Louafi Bouzouina, Michael E. Mehaffy & Bokolo Anthony
The goal of this paper is twofold, first to clarify the proper definitions and boundaries of regional knowledge and technology, and second, to identify the ways of using this technology effectively for governance and decision-making.
2023, Contributo in atti di convegno, ENG
Gabriella Pasi, Gloria Bordogna
The definition and development of IIARS is nowadays facing new challenges given both to the availability of big data on the Web and to the recent advances and application of machine learning and deep learning methods for Natural Language Processing and Information Retrieval. The minitrack has been conceived as a forum to present and discuss recent proposals and applications in the field of IIARS to trace novel emerging approaches and promising case studies.
2023, Editoriale in rivista, ENG
Gloria Bordogna, Cristiano Fugazza
2022, Materiale didattico, ITA
Gloria Bordogna, Alba L'Astorina
Poster illustrativo di vari indicatori definiti per caratterizzare diverse proprietà del suolo creato nell'ambito del progetto BRIDGES .
2022, Banca dati, ITA
Gloria Bordogna, Laura Criscuolo, Lucia Laurenza, Alba L'Astorina
Database con le segnalazioni georiferite create dalle reti del progetto BRIDGES durante lo svolgimento dell'esperimento urbano IN TERRA mediante l'uso dell'applicazione Web Soil_mAPP.
2022, Software, ITA
Gloria Bordogna, Laura Criscuolo, Lucia Laurenza, Alba L'Astorina
Applicazione Web multipiattaforma (Windows, Android, IOS) sviluppata con Kobo toolkit per inviare e raccogliere le segnalazioni georiferite (VGI) relative all'interramento, incubazione e dissotterramento delle litterbag dell'esperimento urbano IN TERRA nell'ambito del progetto BRIDGES e relativo manuale d'uso.
2022, Contributo in atti di convegno, ENG
Stroppiana D.; Boschetti M.; Brivio P.A.; Bordogna G.
The paper proposes a multi-criteria and data driven fusion approach whose semantics can be explained in terms of attitude towards decisions. It is exemplified to assess environmental status from remote sensing images in order to identify hot spot of critical situations and anomalies induced by wildfires, floods, desertification, erosion etc. by fusing multiple factors defined by experts knowledge. The fusion function is an Ordered Weighted Averaging (OWA) operator, whose behaviour is here characterized by degrees of pessimism and democracy. The paper proposes to explain the semantics of the fusion function learnt from few ground truth data available, i.e., the OWA operator, by computing its degrees of pessimism/optimism and democracy/monarchy, which are defined as semantic interpretations of both orness and dispersions respectively. Pessimism indicates if the fused map is more prone to commission (overestimation) or omission (underestimation) errors, while democracy indicates how many factors contribute to the generation of the map. The approach is exemplified to map the flooded areas from remote sensing by considering different models based on distinct spectral indexes and domain experts.
2022, Abstract in atti di convegno, ENG
Gloria Bordogna, Luca Braglia, Luca Frigerio, Floriana Gavazzi, Silvia Gianì, Laura Morello, Anna Rampini, and Diego Breviario
An original decision support Web service is described, designed to aid biologists in identifying the animal and plant species of raw materials present in food products, based on the automatic analysis of their DNA bar-codes. This service allows to speed up a rather burden and meticulous task of biologists as well as standardizing the recognition so as to increase their confidence on the results whose objectives are assessing the quality of food products.
2022, Curatela di numero monografico (di rivista o di collana), CPE
Gloria Bordogna; Cristiano Fugazza
Special issue of the Int. Journal of Geoinformation entitled "Artificial Intelligence for Multisource Geospatial Information" collecting ten contributions focused on the definition and application of artificial intelligence methods for acquisition, filtering, management, analysis, discovery, and visualization of geospatial information from multiple sources, i.e., geospatial big data.
2022, Contributo in atti di convegno, ENG
Gloria Bordogna , Gabriella Pasi
Editoriale della track intitolata "Information Access and Retrieval" organizzata nell'ambito dell'International Symposium on Applied Computing dell'ACM
2022, Contributo in volume, ENM
Gloria Bordogna
The contribution analyses the forms of regional knowledge, its sources, the characteristics of information that can be collected, filtered, represented and managed to extract knowledge to benefit territorial decision makers. Regional knowledge emerges and develops over long periods of time, shaping types of regional activities, vocations and industry structures. Thus, main aspects of the definition of regional knowledge are the geographic and temporal dimensions. Starting from a categorization of regional knowledge into conscious knowledge, that is explicit knowledge held by individuals; objectified knowledge, that is explicit knowledge held by organizations and experts; preconscious knowledge, that is automatic knowledge held by individuals expressed unintentionally; and collective knowledge, implicit knowledge expressed in the practice of organizations, three frameworks for representing and managing information of different nature are indicated as suitable to extract different forms of knowledge, namely: non classical logics, and specifically fuzzy logic, to represent and reason on imprecise conscious and collective knowledge; machine learning to extract preconscious knowledge implicit in geo big data and created by both IoT and within social networks; Petri Nets to formalize objectified knowledge in the form of laws and regulations. For each form of knowledge case studies are illustrated and discussed highlighting the benefits of the adopted formal frameworks. Conclusions summarize the main message and open issues.
2021, Articolo in rivista, ENG
Gloria Bordogna
The paper analyses the characteristics of Volunteer Geographic Information (VGI) and the need to assure and assess its quality for a possible use and re-use. Ontologies and soft ontologies are presented as means to support quality assurance and assessment of VGI by highlighting their limitations. A proposal of a possibilistic approach using fuzzy ontology is finally illustrated that allows to model both imprecision and vagueness of domain knowledge and epistemic uncertainty affecting observations. A case study example is illustrated.
2021, Curatela di atti di convegno (conference proceedings), ENG
Troels Andreasen, Guy De Trè, Janusz Kacprzyk, Henrik Legind Larsen, Gloria Bordogna, Slawomir Zadrozny
Proceedings of the 14th International Conference, FQAS 2021, Bratislava, Slovakia, September 19-24, 2021.