AI and Education

The research theme on AI and education aims at applying some of the IIIA AI techniques to the field of education. It does not aim at completely automating some processes and replacing the human component, but supporting the human through mechanisms like team formation that allow for building more efficient teams, or peer-based assessments that support assessments in massive online courses. 

Contact: Carles Sierra

It is always challenging to make predictions about the impact of technology on an economic or social sector. However, all recent analysis make it clear that repetitive tasks, or those with little added value by the humans who perform them, are going to be redesigned to facilitate their automation through the use of Artificial Intelligence (AI) techniques. Banking and commerce are examples of sectors that are undergoing a profound transformation, partly enabled by AI techniques such as chat-bots or personalization systems, leading to a notable reduction in employment. On the contrary, the education sector will continue to need the human component, and permanently, since the school fulfils an essential socializing function for the development of people. This need does not mean that AI is not going to impact educational processes; it has; it does and will continue to do so.    

Today we have numerous AI applications, not necessarily developed specifically for education, but which are very useful in the education world. For example, automatic subtitling of videos, tutoring systems that interact in natural language, or the realistic conversion of text to human speech. 

AI, in its origins, was already applied to education, in particular personalized education. Adapting the contents to each student is a pedagogical imperative that is difficult for teachers to achieve when the groups are large or the economic resources dedicated to education are limited. Several research groups developed simple systems of personalized education in the 1960s. Today, these systems have reached a remarkable level of sophistication. For example, over the past 15 years, the ALEKS system ( developed in the United States has improved the performance of millions of students in mathematics. This system raises problems with an open response, analyses the answer and, thanks to a machine learning system, identifies errors and skills not acquired to explain the error to the student and recommend new problems that help to obtain the necessary skills. This type of system continues to be developed in different countries. The one created by Squirrel AI in Shanghai with more than three million students, and with a great improvement in individual performance is noteworthy ( We will no doubt see these systems more frequently over the next decade and covering areas increasingly distant from STEM, where they focus on today.

Collaborative Learning

Social phycology, AI and Ethics together can provide valuable models for peer feedback and teamworks

Team Formation

Global economy demands to restructure education to encourage entrepreneurship, creativity and risk-taking. Learning based on teamwork is the path to follow. Within collaborative and task-based education, one of the recurring problems is how to form teams of students. AI allows the analysis of a multitude of factors (sociological, competence, psychological, etc.) to explore the enormous space of possible combinations and find the optimal teams of students in different scenarios and contexts. 

Peer Evaluation

Progress will be made in automatic and peer evaluation processes, which will further democratize education online and throughout life. Advances in natural language processing and computer vision combined with explanation techniques will make the self-assessment that systems provide to students much more informative and useful. Likewise, peer assessment combined with AI techniques will allow the assessment of large groups of online education to be acceptable to teachers. 

Lesson Plans

There are a number of available tools that support teachers in the management of lesson plans on the web. However, none of them is task-centred and support any form of lesson plan's execution over the web. At IIIA, we are interested in the design and execution of these pedagogical workflows. Our Lesson Plans allows to coordinate interactions, ensuring the rules set by the lesson plan are followed, where lesson plans are designed with respect to a selected rubric. Once the lesson plan is defined, a specific graphical user interface (GUI) is automatically generated to allow students navigate through the lesson. Every time the tutor modifies a workflow, a new GUI is generated accordingly without any programming effort. 

Personalised Learning

Hybrid recommender systems and learning analytics allows creating custom-made contents and learning itineraries.

Based on data analytics, Artificial Intelligence algorithms can provide a learning context for the particular needs of students or group of students. We study and create models and algorithms that automatically recommend custom contents and create learning itineraries for the learning needs of students. 

Serious Games

Combine Virtual Reality, AI and gamification to promote learning by playing.

Artificial Intelligence and Virtual Reality provide a rich environment for game-based learning, also called serious games. We develop new personalisation techniques that can be integrated in virtual games to create learning environments where to study and practice several subjects in an inmersive and entretained way.

IIIA develops AI-based software components to offer schools and teachers tools to implement at classrooms. Our toolbox currently offers tools for peer assessments, team composition and lesson plans creation and execution. In what follows, you can play with and test the different demonstrators that shows some of the functionalities offered by our AI-based components.

Team Formation

Cultivation of teamwork, community building, and leadership skills are valuable classroom goals that are more and more introduced at schools. Our aim is to contribute with software technologies that provide teachers with tools to create teams that perform well at diferent levels. 

Synergetic Teams Tool

Partitioning groups of students into competence and cogenial teams for a problem-solving. Eduteams is a Webapp that support the composition of Synergetic teams of students at the classroom.

Congenial Teams Tool 

Partitioning groups of students into gender and psychologically balanced problem-solving teams. Eduteams is a Webapp that support the composition of congenial teams of students at the classroom.

Educational Teams to Companies

Desicion support component to help assign group of students to a Intership project or task. Edu2Com is an Artificial Intelligence component for allocating teams to tasks or projects based on competencies and preferences.

Peer Evaluation

Involving students into accessing others supports teachers but also increase students skills and knowledge. Our aim is to offers computational tools that support the peer assessment in and out of classrooms.

Collaborative Assessment [demo]

Combines teacher and peer assessments to reduce the number of evaluations to make.

Lesson Plans

Our aim is to allow teachers and students to participate into a more flexible, open and collaborative online learning environment. We build tools to support flexible ways to build, share and use collaborative Lesson Plans.

Lesson Plan Editor [demo]

Lesson plan editor to create peer to peer lessons.

Lesson Plan Online Execution [demo]

An online learning environment where executing peer to peer lesson plans.

Filippo Bistaffa
Contract Researcher
Phone Ext. 209

Christian Blum
Scientific Researcher
Phone Ext. 214

Athina Georgara
Industrial PhD Student
Phone Ext. 234

Lissette Lemus del Cueto
Contract Engineer
Phone Ext. 259

Alejandra Lopez de Aberasturi Gómez
Contract Engineer
Phone Ext. 266

Nardine Osman
Tenured Scientist
Phone Ext. 245

Juan A. Rodríguez-Aguilar
Research Professor
Phone Ext. 218

Jordi Sabater-Mir
Tenured Scientist
Phone Ext. 261

Carles Sierra
Research Professor
Phone Ext. 231

In Press
Filippo Bistaffa,  Georgios Chalkiadakis,  & Alessandro Farinelli (In Press). Efficient Coalition Structure Generation via Approximately Equivalent Induced Subgraph Games. IEEE Transactions on Cybernetics. [BibTeX]  [PDF]
Nardine Osman,  Ronald Chenu-Abente,  Qiang Shen,  Carles Sierra,  & Fausto Giunchiglia (In Press). Empowering Users in Online Open Communities. SN Computer Science. [BibTeX]  [PDF]
Pablo Noriega,  Harko Verhagen,  Julian Padget,  & Mark d'Inverno (In Press). Ethical Online AI Systems through Conscientious Design. IEEE Internet Computing. [BibTeX]  [PDF]
Marc Serramia,  Maite López-Sánchez,  & Juan A. Rodríguez-Aguilar (In Press). Value-aligned AI: Lessons learnt from value-aligned norm selection. Philosophy and Technology. [BibTeX]  [PDF]
Dimitra Bourou,  Marco Schorlemmer,  & Enric Plaza (2021). A Cognitively-Inspired Model for Making Sense of Hasse Diagrams. Proc. of the 23rd International Conference of the Catalan Association for Artificial Intelligence (CCIA 2021), October 20-22, Lleida, Catalonia, Spain . [BibTeX]
Filippo Bistaffa,  Christian Blum,  Jesús Cerquides,  Alessandro Farinelli,  & Juan A. Rodríguez-Aguilar (2021). A Computational Approach to Quantify the Benefits of Ridesharing for Policy Makers and Travellers. IEEE Transactions on Intelligent Transportation Systems, 22, 119-130. [BibTeX]  [PDF]
Filippo Bistaffa (2021). A Concise Function Representation for Faster Exact {MPE}and Constrained Optimisation in Graphical Models. CoRR, abs/2108.03899. [BibTeX]  [PDF]
Jaume Agustí-Cullell,  & Marco Schorlemmer (2021). A Humanist Perspective on Artificial Intelligence. Comprendre, 23, 99--125. [BibTeX]
Ángeles Manjarrés,  Celia Fernández-Aller,  Maite López-Sánchez,  Juan A. Rodríguez-Aguilar,  & Manuel Sierra Castañer (2021). Artificial Intelligence for a Fair, Just, and Equitable World. IEEE Technology and Society Magazine, 40, 19-24. [BibTeX]  [PDF]
Marco Schorlemmer,  & Enric Plaza (2021). A Uniform Model of Computational Conceptual Blending. Cognitive Systems Research, 65, 118--137. [BibTeX]  [PDF]
Nieves Montes,  Nardine Osman,  & Carles Sierra (2021). Enabling Game-Theoretical Analysis of Social Rules. IOS Press. [BibTeX]  [PDF]
Dave Jonge,  & Dongmo Zhang (2021). GDL as a unifying domain description language for declarative automated negotiation. Autonomous Agents and Multi-Agent Systems, 35. [BibTeX]
Manel Rodríguez Soto,  Maite López-Sánchez,  & Juan A. Rodríguez-Aguilar (2021). Guaranteeing the Learning of Ethical Behaviour through Multi-Objective Reinforcement Learning. . Adaptive and Learning Agents Workshop at AAMAS 2021 (ALA 2021). [BibTeX]  [PDF]
Dimitra Bourou,  Marco Schorlemmer,  & Enric Plaza (2021). Image Schemas and Conceptual Blending in Diagrammatic Reasoning: the Case of Hasse Diagrams. Amrita Basu, Gem Stapleton, Sven Linker, Catherine Legg, Emmanuel Manalo, & Petrucio Viana (Eds.), Diagrammatic Representation and Inference. 12th International Conference, Diagrams 2021, Virtual, September 28–30, 2021, Proceedings (pp. 297-314). [BibTeX]
Maite Lopez-Sanchez,  Marc Serramia,  & Juan A Rodríguez-Aguilar (2021). Improving on-line debates by aggregating citizen support. Artificial Intelligence Research and Development. IOS Press. [BibTeX]  [PDF]
Thiago Freitas Dos Santos,  Nardine Osman,  & Marco Schorlemmer (2021). Learning for Detecting Norm Violation in Online Communities. International Workshop on Coordination, Organizations, Institutions, Norms and Ethics for Governance of Multi-Agent Systems (COINE), co-located with AAMAS 2021 . [BibTeX]
Antoni Perello-Moragues,  Manel Poch,  David Sauri,  Lucia Alexandra Popartan,  & Pablo Noriega (2021). Modelling Domestic Water Use in Metropolitan Areas Using Socio-Cognitive Agents. Water, 13. [BibTeX]  [PDF]
Dimitra Bourou,  Marco Schorlemmer,  & Enric Plaza (2021). Modelling the Sense-Making of Diagrams Using Image Schemas. Proc. of the 43rd Annual Meeting of the Cognitive Science Society (CogSci 2021), 26--29 July 2021, Vienna, Austria (pp. 1105-1111). [BibTeX]  [PDF]
Manel Rodríguez Soto,  Maite López-Sánchez,  & Juan A. Rodríguez-Aguilar (2021). Multi-Objective Reinforcement Learning for Designing Ethical Environments. Proceedings of the 30th International Joint Conference on Artificial Intelligence, (IJCAI-21) (pp. in-press). [BibTeX]  [PDF]
Marc Serramia,  Maite López-Sánchez,  Stefano Moretti,  & Juan A. Rodríguez-Aguilar (2021). On the dominant set selection problem and its application to value alignment. Autonomous Agents and Multi-agent Systems, 35. [BibTeX]  [PDF]
Francisco Salas-Molina,  Juan A. Rodríguez-Aguilar,  David Pla-Santamaria,  & Ana García-Bernabeu (2021). On the formal foundations of cash management systems. Operational Research, 1081--1095. [BibTeX]  [PDF]
Antoni Perello-Moragues,  Pablo Noriega,  Lucia Alexandra Popartan,  & Manel Poch (2021). On Three Ethical Aspects Involved in Using Agent-Based Social Simulation for Policy-Making. Petra Ahrweiler, & Martin Neumann (Eds.), Advances in Social Simulation (pp. 415--427). Springer International Publishing. [BibTeX]  [PDF]
Josep Puyol-Gruart,  Pere Garcia Calvés,  Jesús Vega,  Maria Teresa Ceballos,  Bea Cobo,  & Francisco J. Carrera (2021). Pulse Identification Using SVM. Artificial Intelligence Research and Development, 339 (pp. 221--224). [BibTeX]  [PDF]
Jesús Cerquides,  Juan A. Rodríguez-Aguilar,  Rémi Emonet,  & Gauthier Picard (2021). Solving Highly Cyclic Distributed Optimization Problems Without Busting the Bank: A Decimation-based Approach. Logic Journal of the IGPL, 29, 72-95. [BibTeX]
Athina Georgara,  Juan A. Rodríguez-Aguilar,  & Carles Sierra (2021). Towards a Competence-Based Approach to Allocate Teams to Tasks. Proceedings of the 20th International Conference on Autonomous Agents and MultiAgent Systems (pp. 1504–1506). International Foundation for Autonomous Agents and Multiagent Systems. [BibTeX]  [PDF]
Nieves Montes,  & Carles Sierra (2021). Value-Alignment Equilibrium in Multiagent Systems. Fredrik Heintz, Michela Milano, & Barry O'Sullivan (Eds.), Trustworthy AI - Integrating Learning, Optimization and Reasoning (pp 189--204). Springer International Publishing. [BibTeX]  [PDF]
Nieves Montes (2021). Value Engineering for Autonomous Agents -- Position Paper. [BibTeX]  [PDF]
Nieves Montes,  & Carles Sierra (2021). Value-Guided Synthesis of Parametric Normative Systems. Proceedings of the 20th International Conference on Autonomous Agents and MultiAgent Systems (pp. 907–915). International Foundation for Autonomous Agents and Multiagent Systems. [BibTeX]  [PDF]
Jordi Ganzer,  Natalia Criado,  Maite Lopez-Sanchez,  Simon Parsons,  & Juan A. Rodríguez-Aguilar (2020). A model to support collective reasoning: Formalization, analysis and computational assessment. arXiv preprint arXiv:2007.06850. [BibTeX]  [PDF]
Marc Serramia,  Maite Lopez-Sanchez,  & Juan A. Rodríguez-Aguilar (2020). A Qualitative Approach to Composing Value-Aligned Norm Systems. Proceedings of the 19th International Conference on Autonomous Agents and MultiAgent Systems (pp. 1233--1241). [BibTeX]  [PDF]
Francisco Salas-Molina,  Juan A. Rodríguez-Aguilar,  & David Pla-Santamaria (2020). A stochastic goal programming model to derive stable cash management policies. Journal of Global Optimization, 76, 333--346. [BibTeX]  [PDF]
Manel Rodríguez Soto,  Maite López-Sánchez,  & Juan A. Rodríguez-Aguilar (2020). A Structural Solution to Sequential Moral Dilemmas. Proceedings of the 19th International Conference on Autonomous Agents and MultiAgent Systems (pp. 1152--1160). [BibTeX]  [PDF]
Anna Puig,  Inmaculada Rodríguez,  Josep Ll Arcos,  Juan A. Rodríguez-Aguilar,  Sergi Cebrián,  Anton Bogdanovych,  Núria Morera,  Antoni Palomo,  & Raquel Piqué (2020). Lessons learned from supplementing archaeological museum exhibitions with virtual reality. Virtual Reality, 24, 343--358. [BibTeX]  [PDF]
Antoni Perello-Moragues,  Pablo Noriega,  Lucia Alexandra Popartan,  & Manel Poch (2020). Modelling Policy Shift Advocacy. Mario Paolucci, Jaime Simão Sichman, & Harko Verhagen (Eds.), Multi-Agent-Based Simulation XX (pp. 55--68). Springer International Publishing. [BibTeX]  [PDF]
Nardine Osman,  Carles Sierra,  Ronald Chenu-Abente,  Qiang Shen,  & Fausto Giunchiglia (2020). Open Social Systems. Nick Bassiliades, Georgios Chalkiadakis, & Dave Jonge (Eds.), Multi-Agent Systems and Agreement Technologies (pp. 132--142). Springer International Publishing. [BibTeX]  [PDF]
Filippo Bistaffa,  Juan A. Rodríguez-Aguilar,  & Jesús Cerquides (2020). Predicting Requests in Large-Scale Online P2P Ridesharing. arXiv preprint arXiv:2009.02997. [BibTeX]  [PDF]
Dave de Jonge,  & Dongmo Zhang (2020). Strategic negotiations for extensive-form games. Autonomous Agents and Multi-Agent Systems, 34. [BibTeX]  [PDF]
Athina Georgara,  Carles Sierra,  & Juan A. Rodríguez-Aguilar (2020). TAIP: an anytime algorithm for allocating student teams to internship programs. arXiv preprint arXiv:2005.09331. [BibTeX]  [PDF]
Jesús Vega,  M. Ceballos,  Josep Puyol-Gruart,  Pere García,  B. Cobo,  & F. J. Carrera (2020). TES X-ray pulse identification using CNNs. ADASS XXX . [BibTeX]  [PDF]
Marta Poblet,  & Carles Sierra (2020). Understanding Help as a Commons. International Journal of the Commons, 14, 281--493. [BibTeX]  [PDF]
  • UNESCO Declaration. In May 2019, around 100 UNESCO member states made a series of recommendations that mark the way forward in the coming years. The first and most relevant is that AI has to be integrated into the education system. AI must be taught and at the same time used to strengthen student learning. This integration and use must be based on scrupulous respect for human rights. It must serve to train students with a critical spirit regarding the use of this technology that allows them to understand the risks and take advantage of the opportunities it offers us. The future of AI in the educational world is fascinating.  
  • SQUIRREL AI. An online education company specialising in intelligent adaptive education.