News

Jan 15, 2020: Our paper entitled “Deep Attention-based Model for Helpfulness Prediction of Healthcare Online Reviews” has been accepted at 1st Workshop on Smart Personal Health Interfaces (SmartPhil 2020).

Nov 01, 2019: I will be involved in the European Digital UniverCity (EDUC) project, a joint initiative of the University of Potsdam (Germany), Université de Rennes 1, Université Paris-Nanterre (France), Masaryk University (Czech Republic), University of Cagliari (Italy), and University of Pécs (Hungary), selected by the European Commission to envision one of the first European Universities. Please visit the project website for more information.

Oct 03, 2019: I will be co-organizing the 1st International Workshop on Algorithmic Bias in Search and Recommendation (Bias 2020) to be held as part of the 42nd European Conference on Information Retrieval (ECIR 2020). Please visit the workshop website for more information.

Oct 02, 2019: Our paper entitled “Deep Multi-Biometric Fusion for Audio-Visual User Re-Identification and Verification” has been accepted for publication in the Springer’s book “Selected Papers from the 8th International Conference on Pattern Recognition (ICPRAM 2019)”.

Jun 17, 2019: Our paper entitled “Adversarial Optimization for Dictionary Attacks on Speaker Verification” has been accepted at The 20th Annual Conference of the International Speech Communication Association (INTERSPEECH 2019).

May 24, 2019: Our book chapter entitled “Deep Learning Adaptation with Word Embeddings for Sentiment Analysis on Online Course Reviews” has been accepted for publication in the Springer’s book “Deep Learning based Approaches for Sentiment Analysis”.

May 06, 2019: Our paper entitled “Servizi Intelligenti per il Tracciamento e l’Elaborazione di Dati Multi-Biometrici in Piattaforme di Apprendimento Digitale” has been accepted at Didamatica – Didattica e Informatica (DIDAMATICA2019).

Mar 05, 2019: Our contributions have been accepted at the Convegno Nazionale CINI sull’Intelligenza Artificiale (ITAL-IA2019). The first one is entitled “Sistemi Multi-Biometrici per l’Autenticazione Continua e Trasparente per l’Accesso a Servizi di Erogazione Contenuti”, while the second one is entitled “Analisi e Mitigazione del Pregiudizio Algoritmico nei Sistemi di Raccomandazione di Contenuti Didattici”.

Jan 09, 2019: Our paper entitled “AveRobot: An Audio-Visual Dataset for People Re-Identification and Verification in Human-Robot Interaction” has been accepted at The 8th International Conference on Pattern Recognition Applications and Methods (ICPRAM2019).

Dec 10, 2018: Our paper entitled “The Effect of Algorithmic Bias on Recommender Systems for Massive Open Online Courses” has been accepted at The 41st European Conference on Information Retrieval (ECIR2019).

Nov 29, 2018: Our paper entitled “Evaluating Neural Word Embeddings Created from Online Course Reviews for Sentiment Analysis” has been accepted at The 34th ACM/SIGAPP Symposium On Applied Computing (SAC2019).

Nov 16, 2018: Our contribution entitled “SociaLearning: Social Engagement in Online Learning through Learning-Group Creation and Course Recommendation” has got to the podium of the Call for Visionary Ideas competition at Futureland 2018.

Oct 01, 2018: I am part of the Local Organizing Committee of The 14th International Conference on Signal Image Technology & Internet-based Systems (SITIS2018). Please visit the conference website for more information.

Sep 18, 2018: Our contributions have been accepted at the GARR “Data ( R ) evolution” Conference 2018 (GARR2018). The first one is entitled “Abylia: Un Ambiente Digitale per la Scuola in Trasformazione”, while the second one is entitled “Deep Learning e Word Embeddings Creati da Reviews di Corsi Online per il Sentiment Analysis”.

Aug 03, 2018: Erasmus+ PlaceDoc and GlobusDoc scholarships has been assigned by the University of Cagliari. The Erasmus+ PlaceDoc scholaship has been received to spend 3 months at the Universidad de Las Palmas de Gran Canaria (Spain), while the GlobusDoc scholarship has been received to spend 2 months at the New York University: Tandon School of Engineering (USA).

Aug 01, 2018: Our paper entitled “Iris Quality Assessment: a Statistical Approach for Biometric Security Applications” has been accepted at The 10th International Symposium on Cyberspace Safety and Security (CSS2018).

Selected Publications

Most recommender systems are evaluated on how they accu- rately predict user ratings. However, individuals use them for more than an anticipation of their preferences. The literature demonstrated that some recommendation algorithms achieve good prediction accuracy, but suffer from popularity bias. Other algorithms generate an item category bias due to unbalanced rating distributions across categories. These ef- fects have been widely analyzed in the context of books, movies, music, and tourism, but contrasting conclusions have…
Proceedings of the 41st European Conference on Information Retrieval (ECIR2019). Springer. Class 2. A Level, 2019

Cloud-connected mobile applications are becoming a popular solution for ubiquitous access to online services, such as cloud data storage platforms. The adoption of such applications has brought security and privacy implications that are making individuals hesitant to migrate sensitive data to the Cloud; thus, new secure authentication protocols are needed. In this paper, we propose a continuous authentication approach integrating physical (face) and behavioral (touch and hand movements) biometrics to control user access…
IEEE Cloud Computing, 5(4), 47-57. IEEE. Q1 Level, 2018

Moving towards the next generation of personalized learning environments requires intelligent approaches powered by analytics for advanced learning contexts with enriched digital content. Micro-Learning through Massive Open Online Courses is riding the wave of popularity as a novel paradigm for delivering short educational videos in small pre-organized chunks over time, so that learners can get knowledge in a manageable way. However, with the ever-increasing number of videos, it has become challenging to arrange and…
Computers in Human Behavior. Elsevier. Q1 Level, 2018

In recent years, online courses have emerged as a new way to educate students in distance learning settings. However, as the demand increases, educational institutions are facing the challenge of how to prove that online students are who they claim to be during e-learning activities, especially exams. Human proctoring is a non-scalable approach which requires a person to monitor each student remotely. On the other hand, automated proctors tend to target a specific type of device and verify the students’ presence without considering…
Pattern Recognition Letters, 113, 83-92. Elsevier. Q1 Level, 2017

Publications

More Publications

(2020). Deep Attention-based Model for Helpfulness Prediction of Healthcare Online Reviews. Proceedings of the 1st Workshop on Smart Personal Health Interfaces (SmartPhil2020). CEUR-WS.

(2019). Adversarial Optimization for Dictionary Attacks in Speaker Verification. Proceedings of the 20th Annual Conference of the International Speech Communication Association (INTERSPEECH 2019). ISCA. Class 2. A Level.

Abstract Pre Print ISCA Scopus Poster

(2019). Servizi Intelligenti per il Tracciamento e l’Elaborazione di Dati Multi-Biometrici in Piattaforme di Apprendimento Digitale. Proceedings of the Italian Conference DIDAttica e inforMATICA – Informatica per la Didattica (DIDAMATICA2019). AICA.

Abstract Pre Print AICA

(2019). AveRobot: An Audio-visual Dataset for People Re-identification and Verification in Human-Robot Interaction. Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods (ICPRAM2019). Scitepress.

Abstract Pre Print SciTePress Link Scopus Dataset

(2019). The Effect of Algorithmic Bias on Recommender Systems for Massive Open Online Courses. Proceedings of the 41st European Conference on Information Retrieval (ECIR2019). Springer. Class 2. A Level.

Abstract Pre Print Springer Link Scopus Slides Code Dataset

(2019). Evaluating Neural Word Embeddings Created from Online Course Reviews for Sentiment Analysis. Proceedings of the 34th ACM/SIGAPP Symposium On Applied Computing (SAC2019). Springer. Class 2. A- Level.

Abstract Pre Print ACM Digital Library Scopus Poster

(2018). Continuous Authentication on Smartphone by Means of Periocular and Virtual Keystroke. Proceedings of the 12th International Conference on Network and System Security 2018 (NSS2018), 212-220. Springer. Class 3. WiP Level.

Abstract Pre Print Springer Link Scopus Dataset

(2018). Iris Quality Assessment: A Statistical Approach for Biometric Security Applications. Proceedings of the 10th International Symposium on Cyberspace Safety and Security 2018 (CSS2018), 270-278. Springer. Class 3. WiP Level.

Abstract Pre Print Springer Link Scopus Dataset

(2018). BarcelonaNow: Empowering Citizens with Interactive Dashboards for Urban Data Exploration. Companion of The Web Conference 2018 (WWW2018), 219-222. ACM. Class 1. A++ Level. Demo Honorable Mention.

Abstract Pre Print ACM Digital Library Poster Video Demo Code

Talks

Adversarial Optimization for Dictionary Attacks in Speaker Verification
Sep 16, 2019 9:30 AM
The Effect of Algorithmic Bias on Recommender Systems for Massive Open Online Courses
Apr 16, 2019 4:40 PM
Sistemi Multi-Biometrici per l’Autenticazione Continua e Trasparente per l'Accesso a Servizi di Erogazione Contenuti
Mar 18, 2019 2:15 PM
ILEARNTV: Un Ecosistema di Conoscenza Condivisa e Produzione Collaborativa per Innovare la Formazione
Apr 19, 2018 6:40 PM
COCO: Semantic-Enriched Collection of Online Courses at Scale with Experimental Use Cases
Mar 28, 2018 6:00 PM
Leveraging Continuous Multi-Modal Authentication for Access Control in Mobile Cloud Environments
Sep 12, 2017 9:40 AM

Activities

Section 1: Organization and Participation as a Speaker at National and International Events

Section 2: Research Collaborations and Exchanges at National and International Level

Section 3: Reviewing Activities for National and International Conferences and Journals

Section 4: Research Awards, Grants and Memberships at National and International Level

Projects

EDUC - European Digital UniverCity (EU, 5 ME)

EDUC aims to establish a collaborative, inclusive, integrated and efficient governance that will build on and contribute to the mutual trust between, and the involvement of, our six universities in all areas, from bottom to top. Thematic working groups involving all stakeholder groups at all organisational levels of our European Digital UniverCity will address topics such as Mobility and Exchange Scenarios, European Skills and Competencies Sustainability and Outreach. EDUC will also establish new communication and coordination flows which will allow the different university services to collaborate horizontally and, ultimately, harmonize work flows. Structures will be brought together in order to establish direct communication between the different services inside the universities – such as international offices, student and research administration offices, and centers for students with special needs.

ILEARNTV Anywhere Anytime (MIUR, 10 ME)

ILEARNTV will promote the evolution of school communities towards a new paradigm based on shared knowledge and collaborative production. In order to support the current transition phase experienced by over 700,000 teachers in Italy, ILEARNTV will define new models for their training inside an innovative platform as well as new methods for providing multi-channel digital learning content via PCs, tablets and smartphones. Within an advanced Software-as-a-Service Learning Content Management System (LCMS), the Cloud infrastructure will be responsible of managing hardware resources, while the software infrastructure will provide the platform’s application functions to end users. Learning material will be indexed into a digital repository and made available for re-use. Collaborative creation of multi-format and multi-media training content will be based on predefined and customizable templates. In this way, ILEARNTV will support teachers in facing the current technological changes, reducing costs and time generally required for their traditional training.

DECODE – DEcentralised Citizens Owned Data Ecosystem (EU, 5 ME)

DECODE will increase digital sovereignty of European citizens by enabling them to produce, access and control their data and exchange contextualised information in real-time, and in a confidential, and scalable manner. DECODE will develop a modular privacy-aware IoT hub with a free and open source operating system backed by a state of the art blockchain infrastructure supporting smart-contracts and privacy protections.The architecture will be demonstrated through four pilots in Barcelona and Amsterdam, in the field of digital democracy, citizen sensing, and collaborative economy. The pilots will be run with the active involvement of social entrepreneurs, hackers, and makers. Innovators will be able to build solutions on top of the platform through hackathons and open challenges, while ensuring their security, resilience and privacy preserving qualities. This aims to create a decentralised innovation ecosystem that will attract a critical mass able to shift the current centralised data-driven economy towards a decentralised, sustainable and commons-based economy. DECODE puts agency and data control in the hands of citizens, to improve citizens’ well-being and society for the collective benefit of all.

ELIOS – E-Learning Interactive OpportunitieS (MIUR, 1.2 ME)

ELIOS will promote the adoption of e-learning within the University of Cagliari. With ELIOS, students will be able to attend one of the following degree programmes in blended-learning settings: (i) Administration and Organization, (ii) Cultural Heritage and Entraitainment, (iii) Economics and Business Administration, (iv) Electrical Electronic and Computer Engineering. Students enrolled within ELIOS will share the same study programmes and final exams taken by traditionally-enrolled students. Moreover, they will receive the same qualification at the end of the programme. Large part of the courses will be available online through a dedicated Learning Management Systems (LMS), anywhere, any time. The LMS will also provide both asynchronous and synchronous learning tools. Students within ELIOS will benefit from a multi-channel technical assistance service aimed at supporting them during distance learning activites.

Teaching

Teaching Assistance

Thesis Assistance, University of Cagliari (Italy)

  • 2020 Galici Roberta: Robust Data Processing for Audio-visual Speaker Verification in Unconstrained Environments.
  • 2020 Lafhouli Hicham: Measuring and Treating Unfairness in Speaker Recognition Systems.
  • 2019 Corda Davide: Evaluating Fusion Rules for Deep Audio-Visual Biometric Systems.
  • 2019 Ariu Giulia: Algorithmic Fairness in Recommender Systems.
  • 2019 Corrias Francesco: A Survey on Continuous Authentication.
  • 2018 Medda Giacomo: An Architecture for Multi-Device Continuous Biometric Authentication.
  • 2018 Meloni Marco: An Architecture for Multi-Device Continuous Biometric Authentication.
  • 2018 Piras Fabio: Enabling Multi-Biometric Sign-In on Web-based E-Learning Platforms.
  • 2015 Pes Alberto: A Mobile Application to Support E-Learning Courses.

Final Project Assistance, Ney York University (U.S.A.)

  • 2019 Pareek Karan: Generative Adversarial Networks for Dictionary Attacks on Speaker Verification.

People

EURECAT - Technology Center of Catalonia (Spain)

  • Boratto Ludovico
  • Laniado David
  • Manca Matteo

Fondazione Bruno Kessler (Italy)

  • Dragoni Mauro

Joint Research Centre European Commission (Italy)

  • Consoli Sergio

Lattanzio Advisory (Italy)

  • Chesi Filippo

Lattanzio Learning (Italy)

  • Giorgini Fabrizio
  • Zucchetti Davide

New York University (U.S.A.)

  • Korus Pawel
  • Memon Nasir

University of Cagliari (Italy)

  • Barra Silvio
  • Casanova Andrea
  • Dessì Danilo
  • Fenu Gianni
  • Meles Massimiliano
  • Reforgiato Recupero Diego

University of Las Palmas de Gran Canaria (Spain)

  • Castrillon-Santana Modesto
  • Lorenzo-Navarro Javier
  • Marin-Reyes Pedro A.

University of Salerno (Italy)

  • Abate Andrea Francesco

Contact