Ethical AI begins with language

Prof. Dr. Karen Joisten (
Dr. Ettore Barbagallo (

Due to the ongoing advancements of AI technologies, we will have to face a totally new ethical problem that never occurred with other technologies before, that is the problem of the increasing resemblance between AI systems and biological systems, especially human beings and animals. This resemblance will gradually make it more obvious for us to attribute human or animal qualities to AI systems, even if we know that they are not self-conscious or alive. We are not able to predict the consequences on the social, psychological, educational, political, and economical level of the spread of such AI systems. In our meta-project, we want to address this problem from an ethical point of view.
In the first five months, we will base our analysis on the Ethics Guidelines for Trustworthy AI (2019) written by the High-Level Expert Group on AI (AI HLEG) set up by the European Commission. We will focus in particular on the language used by the AI HLEG for describing AI systems’ activity and the human-machine interaction. The focus on language is philosophically motivated by the close correlation existing between language, habits (see Aristotle), and practical as well as emotional relationship with the world.
Over the following three months we will try to generalize the results of our analysis. We will propose some examples of how an adequate linguistic practice can help us to make sharp terminological and conceptual distinctions and so describe and understand the human-AI interaction correctly.
These two steps (8 months) are the first phase of a larger project that only in its second phase will expand through collaboration with one partner from the HumanE AI Net community or one external partner.

Connection of Results to Work Package Objectives:
WP5 is concerned with AI ethics and responsible AI. Our project wants to address the responsibility of our linguistic practices with regard to AI. The way in which we speak about AI and the human-AI interaction creates habits, shapes our practical and emotional relationship with the machines and therefore has ethical consequences.
WP3 deals with the human-AI collaboration and interaction. Our project will address the language we use to talk about AI and to describe the interaction between us and AI systems.


1) Paper: a) that analyzes the Ethics Guidelines for Trustworthy AI paying attention to the way in which the human-AI interaction is presented; b) that develops clear-cut concepts as part of an appropriate vocabulary for the description of the human-AI interaction.
2) Discussion of the outcomes of the paper with the AI HLEG.
3) Providing the outcomes of the microproject within HumanE AI Net to find a partner for project expansion.

Project Partners

  • RPTU-Kaiserslautern, /

Primary Contact

Karen Joisten, RPTU-Kaiserslautern

A transparent and explainable dialogue system for assisting immigrants and non-profit organizations on administrative and legal matters in Italy.

Nowadays, dialogue systems are largely applied in many contexts of AI due to their capabilities of being powerful tools for interacting with users and providing assistance and information. These systems can be used both by companies and government institutions to provide support and information in an accessible way.
Some contexts, such as immigration and medicine, require that the user is provided with complete and correct answers. At the same time, such an answer often requires relying on personal and sensitive information, whose use and storage may be regulated by laws such as the E.U.'s General Data Protection Regulation (GDPR).
In a previous MP, “Ethical Chatbots”, we proposed a chatbot architecture based on a mixture of Natural Language Processing (NLP) and argumentative reasoning, with the purpose to ensure data protection while providing personalized service to the individual.
In this novel MP, we propose to implement that architecture to address a specific challenging case study: application for international protection in Italy.
For a person who immigrates to a new country, understanding the local legislation and administrative procedures is fundamental for knowing the rights, duties, and possibilities that the person has in the new Country. However, this can be tricky when international or humanitarian protection is involved, because of the intricacies of Italian immigration law. In Italy, legal and administrative issues related to evaluating asylum applications and further retaining protection are very complex, making it difficult for someone who is already troubled by the life threats they are escaping from, to handle the process alone. Therefore, many immigrants seek the help of Italian mediators, such as voluntary associations and NGOs, to understand what they need to do.
Our purpose is to develop a tool able to support such mediators with actionable intelligence. Such a tool will help them provide answers and explanations over relevant topics, evaluate options for international protection, and identify actions to be taken by protection applicants and recipients. Our primary aim is not to replace the human being who is responsible for providing the correct answer, but rather to help the helpers so as to empower their mediation effort at a scale.
The tool will rely on state-of-the-art NLP techniques and large language models, to understand the information provided by the user and match them with the knowledge in the system. The reasoning process necessary to provide the answer will be fully based on argumentation and therefore perfectly explainable and auditable. The system only consider or retain information that is strictly necessary to provide the answer to the question, thereby respecting the GDPR’s principles of data minimization.
The project will include the participation of legal experts on the topic of immigration and specifically regarding asylum requests. They will provide knowledge about Italian laws and procedures over which the system will perform reasoning. They will also interact with lawyers, judges, and NGOs to obtain feedback regarding the tool and to set up a validation of the final result.
If budget permits, an in-person meeting will be organized with domain experts and stakeholders in Naples, home to the project’s legal expert team.
The MP fits the call for “ELS evaluation projects (WP5)” since it aims to implement and test ELS principles in a real-world scenario.
The project will be divided into 3 phases. 1) Deciding which specific cases will be covered by the dialogue system: the choice will be guided by expert advice. 2) Implementation of the solution, including interaction with experts for feedback. 3) Validation of the solution, through testing with experts and real-world requests.


The main result of this MP is a transparent and explainable interactive prototype chatbot that can be used to obtain useful information in the legal and administrative context. The software will be open source: all the code will be publicly released in a dedicated online repository.
By the end of the MP we plan to deliver a functioning demo focused on specific topics, such as asylum requests under the current Italian legislation.

Project Partners

  • University of Bologna, Andrea Galassi
  • University of Calabria, Bettina Fazzinga
  • University of Naples, Margherita Vestoso

Primary Contact

Andrea Galassi, University of Bologna

To develop a trustworthy AI model for situation awareness by using mixed reality in Police interventions.

We will address the ethical and societal elements of the ELS theme of HumanE-AI-Net, focusing on how to construct Artificial Intelligent Systems (AIS) whose functions aim to support citizen security and safety units. Citizen Security and Safety Units are those closest to the citizens, having the largest number of officers. Their tasks include to help a disoriented old person, deal with traffic and face dangerous situations, gang fights or shootings. The units training is generalist, lacking training and supporting tools to deal with certain situations, in contrast to specialized units. Units need to train situational awareness (ability to maintain a constant, clear mental picture of relevant information and tactical situation in all types of situations). We aim to provide AI tools to facilitate their work and improving their own safety, efficiency, protecting citizens’ rights and enhancing their trust. Transparency and trustworthiness are the most limiting factors regarding the development of AI solutions for public safety and security forces. Any development should be useful to citizens and officers alike. We will carry out tests using the mixed reality paradigm, i.e. HoloLens, with police officers to collect data, making and assessment of the implementation of Trustworthy AI requirements in the following police intervention scenario:

Vehicle stop. Police officers usually patrol a city in police cars facing all types of situations, that in any moment could scale from going to low risk (traffic preventive tasks) to high risk (tracking a possible suspect of a crime that is travelling at high speed). This scenario offers a pretty common activity for police officers. The project’s interest will be to address the perception and impact of the use of technology that could support the security forces to face these daily tasks, making their work safer (i.e., using drones to track suspects in case they are armed). We select this scenario due to its multiple implications, to assess the relationship of public security officers with AI, and to address possible several societal and legal challenges: -Societal: Use of AI to detect potentially life-threatening situations or vehicles related to crimes. Ensure that fundamental rights like privacy and non-discrimination are preserved, while at the same time guarantee public safety. -Legal: Personal Data Protection issues, possible fundamental rights violations related to the use of camaras, legal barriers on Aerial Robot Regulation and the use of UAVS in public spaces.


The microproject aims to address the ethical and societal elements of the ELS theme of HumanE-AI-Net. Its focus is on how to construct Artificial Intelligent Systems (AIS) whose functions aim to support citizen security and safety units.

During the micro-project, we will organize the following activities:

· Research on methods and tools for assessment and monitoring ELS in police interventions
· To address the European Trustworthy AI guidelines or AI act in AI for public security forces
· Implementation and testing of ELS principles and guidelines in police interventions
· Development and validation of metrics to evaluate ELS principles for security forces
· Dissemination and communication of project findings in journals and international conferences



· At least one international conference paper to disseminate findings, possible venues: AAAI, AAMAS, IJCAI, ECAI, etc.
· As continuation of the project findings, we aim to submit a proposal for Horizon Europe call related to Artificial Intelligence and Trustworthy AI.

To make an assessment of Trustworthy AI requirements for AI powered tools aimed at security forces and students in the European countries of the study, we estimate that results of our research and follow-up projects, could reach the following potential targets numbers:

• EU Police Officers: 21,000 in Sweden and ca 29,000 in Catalunya, Spain (Mossos d’Esquadra: 17.888 + Local police: 11.167) Total: 50,000 police officers
• EU Police Students: 9,596 in Catalunya and 4,000 in Sweden. Total of police students: 13,596 police students


For this micro-project we have planned two visits with the following schedule:


1. Barcelona and Mollet Del Valles (Spain) in October 2023
2. Umeå (Sweden) in February 2024

The length of all visits will be one week each.

Visit Objectives

A. Barcelona and Mollet Del Valles (Spain):

To organise a visit to COMET and ISPC locations, with the following objectives
1. To carry out tests using mixed reality paradigm, i.e. HoloLens with 10 police officers from the Catalan Police School (Spain), to collect data (reaction and feedback) on the use of AI in the police intervention described scenario.
2. To analyze data from these tests to elaborate a methodology to assess the implementation of the Trustworthy AI requirements in police interventions.
3. To research on possible data privacy and civil rights violation and legal framework on the use of AI powered tools in the police intervention described scenario.
4. To organize a partners’ meeting to discuss and evaluate the data collected during the tests and elaborating a methodology for the assessment of Trustworthy AI requirements in police interventions,
5. To discuss project dissemination strategy workplan.

B) Umea University and Police Education Unit

1. To carry out tests using mixed reality paradigm, i.e. HoloLens with 10 police officers from Umea Police Education Unit (Sweden), to collect data (reaction and feedback) on the use of AI in the police intervention described scenario.
2. To analyze data from these tests to elaborate a methodology to assess the implementation of the Trustworthy AI requirements in police interventions.
3. To research on possible data privacy and civil rights violation and legal framework on the use of AI powered tools in the police intervention described scenario.
4. To organize a partners’ meeting to discuss and evaluate data collected during the tests and elaborate a methodology for the assessment of Trustworthy AI requirements in police interventions.
5. To discuss dissemination actions on project findings and partners’ participation (publications, international conferences etc.)
6. To discuss the project findings and conclusions for future follow-up projects among partners.

Project Partners

  • Umeå University – Computing Science Department, Juan Carlos Nieve
  • Umeå University – Police Education Unit, Jonas Hansson
  • Comet Global Innovation-COMET, Eduardo García Laredo
  • Institut de Seguretat Pública de Catalunya -ISPC, Lola Valles Port

Primary Contact

Juan Carlos Nieves, Umeå University – Computing Science Department

Critical review and meta-analysis of existing speech datasets for affective computing in the perspective of inclusivity, transparency, and fair use

As AI-powered devices, software solutions, and other products become prevalent in everyday life, there is an urgent need to prevent the creation or perpetuation of stereotypes and biases around gender, age, race, as well as other social characteristics at risk of discrimination.

There are well-documented limitations in our practices for collecting, maintaining, and distributing the datasets used in current ML models. Moreover, these AI/ML systems, their underlying datasets, as well as the stakeholders involved in their creation, often do not reflect the diversity in human societies, thus further exacerbating structural and systemic biases. Thus, it is critical for the AI community to address this lack of diversity, acknowledge its impact on technology development, and seek solutions to ensure diversity and inclusion.

Audio is a natural way of communicating for humans and allows the expression of a wide range of information. Its analysis through AI applications can provide insights regarding the emotions and inner state of the speaker, information that cannot be captured by simply analyzing text. The analysis of the speech component is valuable in any AI application designed for tasks requiring an understanding of human users behind their explicit textual expressions, such as the research area of affective computing.

Affective computing refers to the study and development of systems and devices that can recognize, interpret, and simulate human emotions and related affective phenomena. Most of the currently available speech datasets face significant limitations, such as a lack of diversity in the speaker population, which can affect the accuracy and inclusivity of speech recognition systems for speakers with different accents, dialects, or speech patterns.

Other limitations include narrow context and small scale of recordings, data quality issues, limited representation, and limited availability of data. These issues must be carefully addressed when selecting and using speech datasets in an affective computing context, to ensure that speech recognition systems can effectively contribute to applications such as intelligent virtual assistants, mental health diagnosis, and emotion recognition in diverse populations.

In this MP, we aim to contribute towards the creation of future datasets and to facilitate a more aware use of existing ones. We propose to perform an extensive review of the literature on the topic, in particular existing speech datasets, with two main objectives.

First, we want to identify the key characteristics required in the creation of unbiased and inclusive speech datasets and how such characteristics should be pursued and validated.

Second, we want to perform a meta-analysis of the domain, focusing on the underlying limitations in the existing datasets. We want to provide a critical evaluation of the datasets themselves, but also of the scientific articles in which they were presented. Such a fine-grained analysis will allow us to elaborate on a more general and coarse-grained evaluation of the domain.

This MP would naturally fit the topic “ELS evaluation projects (WP5)”. Our purpose is the evaluation of existing speech datasets, that are used for the development of AI solutions, according to ethical and societal principles, and the formalization of best practices into a document of guidelines.

The project will be divided into 3 phases: in-depth analysis of the domain and of existing methodologies; discussion and writing of the criteria that will be evaluated in our analysis; systematic literature review to perform the meta-analysis. Given the unique background and expertise on key aspects of this project of the different partners, we plan to meet in person after each phase to discuss the results and elaborate on the methodology to apply for the following phase.


We are planning to deliver two resources to the community:

1) A document to identify and discuss requirements, desiderata, and best practices that will cover many aspects of the creation and validation of a speech dataset, such as how to ensure that the data collection is inclusive, the pre-processing and the experimental setting do not introduce harmful biases, and the presentation of the work in a scientific publication includes all the relevant information.

2) A scientific report resulting from our meta-analysis. Depending on the result of our meta-analysis, we will select an appropriate venue (conference or journal).

Project Partners

  • University of Bologna, Andrea Galassi
  • Uppsala University, Ana Tanevska

Primary Contact

Andrea Galassi, University of Bologna

Formulating common grounds for studying explainability in the context of agent behaviour: a survey on the topic, analysis of evaluation metrics and the definition of an ontology

As Artificial Intelligence (AI) systems further integrate in our daily lives, there are growing discussions in both academic and policy settings regarding the need for explanations. If we cannot explain the algorithms, we cannot effectively predict their outcomes, dispute their decisions, verify them, improve them, or maximise any learning from them, negatively impacting trustworthiness and raising ethical concerns. These issues led to the emergence of the field of eXplainable Artificial Intelligence (XAI) and of multiple approaches and methodologies for producing explanations.

However, there are many elements to take into account in order to decide what explanations to produce and how to produce them:
* Who is the explainee and what is their perspective, i.e. what knowledge do they have from the system and what are the questions they want addressed?
* How should the reliability of an explanation be defined? How can we assess whether explanations produced are in line with agent behaviour or just plausible falsehoods? Should explanations refer to specific situations or just to general cases? What metrics can be defined and what is needed for reliable explanations to be feasible?
* What explanations are actually demanded by each use case? Not all aspects of the agent or its behaviour are equally necessary.
* What demands on explainability pertains to continually interactive agents in particular, over other types of systems?
* In case more than one agent is present in the environment, should the explanations be given in terms of a single agent or of the system as a whole? When can these perspectives be meaningfully separated, and when not?
* Can technical demands for XAI be translated into implementation agnostic architectural, structural or behavioural constraints?
* What information about the agent’s context/the socio-technical system is necessary in the explanation? How does privacy and other ethical values impact the demands for explainability?

We focus on agents due to the unique complexities involved in their emerging behaviour; particularly, in multi-agent systems.
From a bottom-up perspective, taking into account the potentially complex behaviour of an interactive agent, the problem of explainability becomes hard to manage and seemingly only solvable in an implementation-specific manner. Many such implementation-specific approaches exist, often building from particular agent architectures, e.g. BDI.

We propose to adopt a top-down perspective on the topic, by 1) undergoing a comprehensive analysis of the State-of-the-Art on explainability of agent behaviour, 2) elaborating an exhaustive definition of relevant terms and their interpretation, 3) studying relevant evaluation metrics and proposing new ones, and 4) producing a comprehensive taxonomy of behaviour explainability. In this context, we aim at integrating diverse perspectives regarding where and how artificial agents are used in socio-technical systems through real-world representative examples.

Top-down views on the topic of explainable AI are not widely represented in the literature so our proposal should entail a strong contribution to the state of the art. The outcome of this microproject should allow the definition of explainable AI systems under common grounds, cutting down on complexity and driving towards generalization while always taking into account the needs of the audience of the explanations.

This project is strongly supporting at least WP1-2, WP3 and WP5 and possibly assisting the goals of WP4.
The main focus however is a framework for understanding and evaluating agent Explainability and fits within WP5.



1. (At least) two publications targeting venues such as the IJCAI, AAMAS, ECAI, AAAI conferences, or topic-related workshops:
* The first publication will be a survey of literature in agent explainability
* The second publication will be a definition of a conceptual framework for explainability in agent behaviour, and grounding as an ontology or data model

2. A grounding of the conceptual framework in the form of an ontology and/or a data model for its use in socio-technical systems.

Activities that will be funded, include but are not limited to:
* Doing a comprehensive survey of the literature, classifying different types of explainability and approaches to it,
* Producing a taxonomy of terms related to the topic and provide a definition for them (this might be hard but necessary as sometimes words are used in conflicting ways), Give a definition of what this “explainability box” should account for, probably as an architecture (component view),
* Analysing possible metrics that can be used for evaluating explainable systems, proposing new ones if necessary.
* Mapping different already existing approaches for explainability to our proposed architecture, in order to validate its expressiveness,
* Defining a methodology for grounding the conceptual framework to particular scenarios e.g. Overcooked-AI, COVID Social Simulator, Privacy-enforcement in a home network (these are just examples, the methodology will be general).

Project Partners

  • Umeå University (UMU), Mattias Brännström
  • UiB, John Lindqvist
  • Universitat Politècnica de Catalunya (UPC), Sergio Alvarez-Napagao

Primary Contact

Mattias Brännström, Umeå University (UMU)

Ensuring that decisions made by systems adhere to human socio-ethical principles.

The right to contest a decision that has consequences on individuals or the society is a well-established democratic right. In the European Union, the General Data Protection Regulation explicitly requires the means of contesting decisions made by algorithmic systems. Contesting a decision is not a matter of simply providing explanation, but rather of assessing whether the decision and the explanation are permissible against an externally provided policy. Albeit its importance, little fundamental work has been done on developing the means for effectively contesting decisions. In this micro-project, we will develop the foundations needed to integrate the contestability of decisions based on socio-ethical policy (e.g. Guidelines for Trustworthy Artificial Intelligence (AI)) into the decision-making system. This microproject will lay the basis for a line of research in contestability of algorithmic decision making by considering the overall ethical socio-legal aspects discussed in WP5 of the HumanE-AI-Net project. During the course of this microproject, we will achieve 3 objectives: 1) extend our work on formal language for socio-ethical values, concretised as norms and requirements; 2) conceptualise our feedback architecture which will monitor the predictions and decisions made by an AI system, check the predictions against a policy; and 3) a logic to evaluate black-box prediction based on formal socio-technical requirements by extending our previous work on monitoring and assessing decisions made by autonomous agents. The end result will be an agent architecture which contains 4 core components: i) a predictor component, e.g. a neural network, able to produce recommendations for a course of action; ii) a decision-making component, which decides if and which action the agent should take; iii) a utility component, influencing the decision-making component by ascribing a utility value to a potential action to be taken; and iv) a ‘governor’ component; able to reason and suggest the acceptance or rejection of recommendations made by a predictor component. During the microproject, we plan to first focus on compliance checking but ensure our architecture is flexible and modular enough to facilitate extensions such as the governor component offering feedback for ‘retraining’ to the predictor component.

For the successful implementation of the project, we have devised the following working plan: we will first review relevant literature on government agents, and then proceed with the formalisation of ethical socio-legal policies. In parallel, we will start working towards a case example implementation to deliver a practical demo at the end. During the microproject, we have planned two research visits: one in Uni. of Berghem in June and one in Open University of Cyprus in October. Online weekly meetings take place between those visits.


1. Use-case demo consisting of an agent making recommendations on a to-be-defined topic. The agent will be built using the architecture conceptualised in this micro project.
2. We plan 2 papers, one focusing on the theoretical implementation and one on the use-case implementation, targeting the following venues: AAAI, AAMAS, IJCAI, KR, ECAI, AIES, HHAI.

Project Partners

  • Umeå University (UmU), Andreas Theodorou
  • University of Bergen (UiB), Marija Slavkovik
  • Open University of Cyprus (OUC), Loizos Michael

Primary Contact

Andreas Theodorou, Umeå University (UmU)

Determining the trustworthiness of public information on ethical, legal, and societal issues caused by the migration of Ukrainians to European countries through AI-driven analysis of social media content

Currently, almost all government, commercial, and non-profit organizations actively use social media for the dissemination of information and communication with citizens. Social media should serve to enhance citizen engagement and trust, contribute to the improvement of government institutions' transparency, and guarantee freedom of speech and expression. However, the government needs to be aware of and mitigate the risks associated with the use of social media. One of the most significant is the risk of spreading misinformation that has become increasingly prevalent and easily accessible to the global social media audience.
In general, the government and public officials' social media accounts are trustworthy and aim to disseminate high-quality and timely information to the public ensuring its reliability, integrity, accessibility, and validity. However, non-compliance with the rules of effective and trusted two-way communication on public officials' accounts, untimely updating of the communication channel, and incomplete responses to user comments could lead to a tendency of citizens to search (or check) the information in other social media sources. Such information sources include traditional news outlets, professional or casual journalists, or ordinary users. Wherein the risk of misinformation being disseminated could undermine citizens' trust in the government, as well as threaten the security and privacy of both official government data and personal data. Moreover, the sharing of inaccurate and misleading information could lead to significant social consequences, such as the exacerbation of social inequalities, the creation of social divisions between different social groups, and the manipulation of their opinions.
In our microproject, we strive to develop an actionable AI-based approach to objectively assess information trustworthiness on social media based on the combination of AI algorithms such as unsupervised machine learning, text analytics, and event argument extraction. We plan to apply our approach to the analysis of textual information in Polish, Ukrainian, and English thematically related to the main ethical, legal, and societal issues caused by the migration of Ukrainians to European countries as a result of the ongoing Russian invasion. The choice of migration crisis domain to assess the reliability of social media Information is due to the following reasons. First, as recent research demonstrates, migration issues are among the most hotly debated on social media and can be especially subjected to attempts of various kinds of disinformation. Second, the migration problem includes a lot of associated issues such as Ethical Issues (e.g., vulnerable to exploitation by employers, low wages, work in unsafe conditions, discrimination, and marginalization); Legal Issues (e.g., immigration laws and policies, visa regulations and border controls, limited access to justice); Social security (e.g., social protection, mental support, integration, language barriers, and cultural differences, social isolation); and the problems of reporting to the public the appropriate policies to support Ukrainian migrants in their countries of destination and to address the root causes of migration in Ukraine itself. The official and unofficial information on social media that covers all these issues are supposed to be considered in the microproject.
Therefore, the development of an actionable AI-based approach for determining information trustworthiness (i) will serve to expand understanding of the core information needs of citizens in communication with the government in the context of migration issues in the last year; and potential causes and nature of that information untrustworthiness in social media; and (ii) can support the government to develop relevant guidelines to oversee social media, and instruments to assess, analyze and monitor implementation and compliance with ELS principles in social media.


The main tangible results of the mini project at each task of its implementation are as follows:
Task 1. Corpus building.
For building the Corpus, it is planned to use the following assumption: information is annotated as Trustworthy (TIC) if published on a government digital platform, news channels operated by governments, or on social media accounts (e.g., Twitter) of government officials. The trustworthiness of the rest of the government-related information disseminated on social media is Uncertain (UIC) and needs additional verification. A special list of keywords relevant to ELS issues caused by the Ukrainian migration context will be developed.
The main tangible result:
(1) A dataset of social media content related to Ukrainian migration, annotated with Ukrainian trustworthiness labels (TIC or UIC).

Task 2. Argument event extraction and texts classification
Tackling the text classification problem to automatically detect whether certain textual information is trustworthy or not, is based on a supervised ML classification that applies extended semantic features (participants, arguments, and arguments' roles) for the classification model. For extraction of these semantic features, we are going to use the NLP pipeline and the Open-domain Information Extraction approach enriched by the semantic knowledge.
Expected tangible results:
(2) An AI-driven algorithm that can analyze social media content to determine its trustworthiness.
(3) The open linguistic resources, such as specialized dictionaries and events patterns, especially for Low-Resource Polish and Ukrainian Languages and for ELS migration-related issues domains, can be used in the follow-up studies.

Task 3. Trustworthiness of public information detection
We attempt to identify the degree and nature of the untrustworthiness of core topics in the context of the Ukrainian migration. The method of detection of public information Trustworthiness is based on the Enriched Event semantic annotation approach and classification rules for the Disinformation class when the facts presented in posts/comments are distorted); and the Omission class, when critical information is excluded from posts/comments disseminated in social media.
Expected tangible result:
(4) A dataset of social media content related to Ukrainian migration, annotated with trustworthiness scores.
(5) An AI-driven algorithm that identifies the degree and nature of social media information of untrustworthiness.

Task 4. Exploratory Text Analysis.
At this, we aim to identify the main topics discussed in social media in the context of the Ukrainian migration and their sentiment (separately for Trustworthy and Untrustworthy Corpus parts). Based on the degree of discussion activity of each topic (topic proportion), and the topics' negative effect (sentiment score), we intend to provide a ranking of the topic's importance.
Expected tangible result:
(6) Ranking the importance of core topics discussed on social media by three categories – ELS issues regarding the Ukrainian migration. These insights can be used by the government for policymaking toward Ukrainian migrants’ inclusion.
(7) An analytical framework for analysis of the degree and nature of trustworthiness of social media content, which can be used in future studies or applications related to assessment, analysis, and monitoring of the implementation and compliance with ELS principles in social media space

Project Partners

  • Umea University, Nina Khairova
  • Gdansk University of Technology, Nina Rizun
  • University of the Aegean, Charalampos Alexopoulos

Primary Contact

Nina Khairova, Umea University

Formalization of values preferences for AI agents to address simultaneous multiple layered contexts in which they are situated.

This project aims at developing an explicit representation and interpretation of stakeholders’ socio-ethical values, conventions, and norms, and to incorporate them in AIS component reasoning and decision-making processes. By doing so, we can enable ethics-by-design approaches in which the agents take into consideration the wider socio-ethical values that they are meant to fulfil as part of the socio-ethical systems that they belong to.

There is extensive literature on the formalisation of value systems, norms, and conventions, but most works cover only one level of abstraction at one end of the spectrum – either abstract and universal or concrete and specific to a particular scenario – and in a single interaction context. However, the real social world is much more complex with multiple overlapping contexts that comprise extended sequences of events within contexts, while events can individually and severally have effects across contexts. There are multiple – not fully compatible – value theories, such as Self-Determination Theory or the Schwartz Value System. These are also abstract in nature and not directly applicable to an agent’s behaviour. A key factor in understanding how values affect actions is that preferences over values are context-dependent, so certain values are more important than others according to the circumstances. This becomes more complicated when we consider that an agent can be in more than one context at the same time and thus have to handle different, possibly conflicting, preference orderings. Lastly, there is the mutual interaction of values with context to address: the context affects the value preferences, but also value preferences affect the context. Consequently, to formalise value preferences for agents, we need to identify and define a suitable approximation of a context for the purposes of this microproject.

In this microproject, we will develop: 1) A novel agent architecture that allows agents to be aware of the values/norms/conventions for each of the social contexts related to their interactions by creating separate explicit representations for each context, and then utilising these context representations in reasoning and decision making to align the resulting behaviour to the social values of the contexts in which the agent is situated. 2) A methodology to develop a multi-level, multi-contextual model to formalise a connection from abstract, universal social values to concrete behaviour of agents in a particular social context. More concretely, we aim to create a computational representation of nested, overlapping (eventually contradictory) social contexts, where the set of values and the preference function over them (and their respective norms and conventions) of a given context are properly derived from abstract values in higher-level, more general (super) contexts, up to universal, abstract values.
We will demonstrate the practical feasibility of the above two contributions by developing a proof-of-concept demonstrator in the second of the 2 planned papers (the first, will focus on the conceptualisation).


The foundation for addressing the problems outlined above is a novel agent architecture that we sketch in the project description. However, this needs to be tied to an agent-based simulation platform, within which we will apply the methodology and test the agent architecture.

Evaluation of the methodology and the architecture will form the primary technical outputs and provide the core content for the publications discussed below. Our approach to evaluation will rely upon artificial scenarios that show how the methodology delivers a value preference model that reflects stakeholder requirements and then how that model functions in the agent architecture. Our aim in using artificial testing scenarios rather than simplified real-world scenarios is to: (i) de-risk the project by focusing on function rather than scenario modelling (ii) concentrate on correct coverage of value-preference determined behaviour (iii) provide confidence in the overall capability of the model and its implementation (iv) facilitate reproducibility of methodology and architecture.

We are going to implement our agents in a simulation of an artificial population as a proof-of-concept demonstrator.

We plan 2 publications, one focusing on the principles and conceptualisation targeted at AAMAS 2024 and one on the demonstrator targeted at ECAI 2024. These additional venues are identified as back-ups: AAAI, AAMAS, IJCAI, KR, ECAI, AIES, HHAI, and workshops like MABS, COINE.

Project Partners

  • Instituto Superior Técnico (IST), Rui Prada
  • Umeå University (UMU), Juan Carlos Nieves
  • Umeå University (UMU), Andreas Theodorou
  • Umeå University (UMU), Virginia Dignum
  • Universitat Politècnica de Catalunya (UPC), Javier Vázquez-Salceda
  • Universitat Politècnica de Catalunya (UPC), Sergio Álvarez-Napagao
  • University of Bath, Marina De Vos
  • University of Bath, Julian Padget

Primary Contact

Rui Prada, Instituto Superior Técnico (IST)

The project focuses on the development of a framework for multimodal and multilingual conversational agent. This framework is composed with 5 levels of abilities:

– Reactive(sensori-motor) Interaction: Interaction is tightly-coupled perception-action where actions of one agent are immediately sensed and interpreted as actions of the other. Examples include greetings, polite conversation and emotional mirroring

– Situated (Spatio-temporal) Interaction Interactions are mediated by a shared model of objects and relations (states) and shared models for roles and interaction protocols.

– Operational Interaction Collective performance of tasks.

Praxical Interaction Sharing of knowledge about entitles, relations, actions and tasks.

– Creative Interaction Collective construction of theories and models that predict and explain phenomena.

This mini-project focuses on the 2 first levels. To demonstrate it, a demonstrator arround services for citizens will be developped.


Open Source Library covering focus on reactive and stiutated level

Demonstrator focus on services for citizen

Project Partners:

  • Università di Bologna (UNIBO), Paolo Torrini


Primary Contact: Eric Blaudez, THALES

Vertigo can have many underlying causes and is a common reason for visiting the emergency department. In this project we extend an existing decision tree and random forest (RF) model for classifying patients into high and low probability groups, with CNN model and we will experiment a variety of explainability methods available in literature including those developed by the KDD Lab-CNR-Pisa group within the ERC project XAI. In particular, we will concentrate on post-hoc explanations experimenting methods that are local, global and/or based on medical ontology as Doctor XAI. The existing RF model and the CNN model are developed at UMU. A comparison between RF and CNN will support a better understanding of model accuracy whereas accompanying CNN with XAI methods will give insights on the usability for the medical specialist.


vertigo dataset

conference paper (submitted to e.g. FAccT or IJCAI)

journal paper



Project Partners:

  • Umeå University (UMU), Virginia Dignum
  • Consiglio Nazionale delle Ricerche (CNR), Fosca Giannotti


Primary Contact: Virginia Dignum, UMU

In this project, which we work with a Ukrainian academic refugee, to combine methods for semantic text similarity with expert human knowledge in a participatory way to develop a training corpus that includes news articles containing information on extremism and terrorism.


  1. Collection and curation of two event-based datasets of news about Russian-Ukrainian war. The datasets support analysis of information alteration among news outlets (agency and media) with a particular focus on Russian, Ukrainian, Western (EU and USA), and international news sources, over the period from February to September 2022. 21 We manually selected some critical events of the Russian-Ukrainian war. Then, for each event, we created a short list of language-specific keywords. The chosen languages for the keywords are Ukrainian, Russian, and English. Finally, besides the scraping operation over the selected sources, we also gather articles using an external news intelligence platform, named Event Registry which keeps track of world events and analyzes media in real-time. Using this platform we were able to collect more articles from a larger number of news outlets and expand the dataset with two distinct article sets. The final version of the RUWA Dataset is thus composed of two distinct partitions.
  2. Development of an unsupervised methodology to establish whether news from the various parties are similar enough to say they reflect each other or, instead, they are completely divergent and therefore one is likely not trustworthy. We focused on textual and semantic similarity (sentence embeddings methods such as Sentence-BERT), comparing the news and assess if they have a similar meaning. Another contribution of the proposed methodology is a comparative analysis of the different media sources in terms of sentiments and emotions, extracting subjective points of view as they are reported in texts, combining a variety of NLP-based AI techniques and sentence embeddings techniques. Finally, we applied NLP techniques to detect propaganda in news article, relying on selfsupervised NLP systems such as RoBERTa and existing adequate propaganda datasets.
  3. Working on a conference and journal papers.
  4. Github repository of datasets and software:
Preliminary Qualitative results: 
When the events concern civilians all sources are very dissimilar. But Ukraine and Western are more similar. When the event is military targets, Russian and Ukraine sources are very dissimilar from other sources, there is more propaganda in Ukraine and Russian ones.

Project Partners:

  • Umeå University (UMU), Nina Khairova, (6 PM)
  • Consiglio Nazionale delle Ricerche (CNR), Carmela Comito,
  • Università di Bologna (UNIBO), Andrea Galassi,

Primary Contact:

  • Carmela Comito


The goal is to devise a data generation methodology that, given a data sample, can approximate the stochastic process that generated it. The methodology can be useful in many contexts where we need to share data while preserving user privacy.

There are known literature for data generation based on Bayesian neural networks/hidden Markov models that are restricted to static and propositional data. We focus on time-evolving data and preference data.

We will study essentially two aspects: (1) the generator to produce realistic data, having the same properties of the original one. (2) we want to investigate how to inject drift within the data generation process in a controlled manner. The idea is to model the stochastic process through a dependency graph among random variables so that the drift can be simply modeled by changing the structure of the underlying graph through a morphing process.


1 Conference/Journal Paper

1 Prototype

Dataset Samples

Project Partners:

  • INESC TEC, Joao Gama
  • Universiteit Leiden (ULEI), Holger Hoos
  • Consiglio Nazionale delle Ricerche (CNR), Giuseppe Manco

Primary Contact: Joao Gama, INESC TEC, University of Porto