CIMPLE: Countering Creative Information Manipulation with Explainable AI
What’s the role that Artificial Intelligence can play in fighting misinformation?
CIMPLE project aims to research and develop innovative social and knowledge driven creative AI
explanations, and testing it in the domain of detection and tracking of manipulated information, while
taking into account social, psychological, and technical explainability needs and requirements.
“Our domain is the manipulation of information that we see on social media, in the news… it is about
the dissemination of information or news that is factually wrong because it does not tell the truth or it has been manipulated, misleading the public”, mentioned Sofia Pinto, the INESC-ID Researcher involved in the project.
The CIMPLE project is all about Explainable Artificial Intelligence (XAI) requirements related to AI-driven misinformation detection, XAI by design using Knowledge Graphs and XAI models for detecting
information manipulation. The Researchers involved aim to be able to generate creative and engaging
explainability visualisations and personalize XAI to end-users skills and topic affinity.
“INESC-ID’s role is to look for ways to explain the manipulation of information, in a way that the interlocutor has the ability to listen and to question himself. It is more than just presenting facts, as it is very difficult to convince someone else who believes something otherwise. And this is where creativity comes in. We are going to work on this explanation of manipulation using computational creativity to attract people’s attention, so that they can visualize where there was manipulation and so that they can reach to their own conclusions”, adds the researcher.
Explainability is of significant importance in the move towards trusted, responsible and ethical AI, yet
remains in its infancy. Most relevant efforts focus on the increased transparency of AI model design and
training data, and on statistics-based interpretations of resulting decisions (interpretability).
Explainability considers how AI can be understood by human users. The understandability of such
explanations and their suitability to particular users and application domains received very little
attention so far. Hence there is a need for an interdisciplinary and drastic evolution in XAI methods.
CIMPLE will draw on models of human creativity, both in manipulating and understanding information,
to design more understandable, reconfigurable and personalisable explanations. Human factors are key
determinants of the success of relevant AI models. In some contexts, such as misinformation detection,
existing XAI technical explainability methods do not suffice as the complexity of the domain and the
variety of relevant social and psychological factors can heavily influence users’ trust in derived
explanations.
Past research has shown that presenting users with true / false credibility decisions is inadequate and
ineffective, particularly when a black-box algorithm is used. Knowledge Graphs offer significant potential to better structure the core of AI models, using semantic representations when producing explanations for their decisions. By capturing the context and application domain in a granular manner, such graphs offer a much needed semantic layer that is currently missing from typical brute-force machine learning approaches.
To this end, CIMPLE aims to experiment with innovative social and knowledge driven AI explanations,
and to use computational creativity techniques to generate powerful, engaging, and easily and quickly
understandable explanations of rather complex AI decisions and behavior. These explanations will be tested in the domain of detection and tracking of manipulated information, taking into account social,
psychological and technical explainability needs and requirements.
The Project is a Partnership between INESC-ID, EUROCOM (Paris, France), The Open University (UK),
University of Economics and Business (Prague, Czech Republic) and WebLyzard technology, WLT
(Vienna, Austria).
CIMPLE was one of the CHIST-ERA projects approved under the 2019 call “Explainable Machine
Learning-based Artificial Intelligence”.
CHIST-ERA is a network of funding organisations in Europe and beyond supporting long term research on digital technologies with a high potential impact. It selects every year two new topics of emerging
importance and launches a call for transnational research projects on these topics.
Upcoming Events
OLISSIPO Workshop: “How to design a graphical abstract” with Dr. Rita Félix (CNC-UC)
On April 19, the OLISSIPO project will host an 8-hour workshop titled “How to design a graphical abstract” with Dr. Rita Félix, a science communicator, illustrator and designer from CNC Center for Neuroscience and Cell Biology (Coimbra, Portugal). Registration is free and seating is limited.
Registration Deadline: April 5 | Register here (free but mandatory)
Date & Time: April 19, 09h00-18h00 ( 8-hours)
Where: INESC-ID, R. Alves Redol 9, 1000-029 Lisboa | Room 9 (Auditorium), Ground Floor
Summary: “How to design a graphical abstract” Workshop aims to explain what a graphical abstract is, and give you design tools and tips on how to create a better, clear and engaging graphical abstract. This workshop is tailored to give you tools and improve your graphical abstract, without having to learn how to use a new software program (like Adobe Illustrator). Bring your graphical abstract, share it with the class, work on it and take home a new version.
Short Bio: Rita Félix is a science communicator, illustrator and designer, with life sciences research experience. Currently working as the Institutional Communication Manager and Designer at CNC-UC. She completed her PhD in Neuroscience in 2020, in the Champalimaud Neuroscience Programme. After that, she enrolled in a Digital Illustration Specialization Course to further develop her visualization and design skills. Worked as a Scientific Graphic Designer at Science Crunchers, a science communication company, where she developed multiple graphical abstracts, article figures, infographics, diagrams, illustrations, visual identity, logos and webdesign for companies, scientific institutions and Horizon 2020 consortia. More information at https://ritallfelix.wixsite.com/portfolio .
INESC-ID talk: “Rise of the AI-Empowered End User Software Engineer” by Ed Ayers and Andy Gordon (Cogna)
On April 19, INESC-ID will host a talk by Ed Ayers and Andy Gordon from the startup Cogna. The talk is titled “Rise of the AI-Empowered End User Software Engineer” and is organised by INESC-ID researcher Nuno Lopes.
Date & Time: April 19, 15h00 -16h00
Where: INESC-ID, Rua Alves Redol, 9, 1000-029 Lisboa | Room 9 (Auditorium), Ground Floor
Summary:
“What if natural language really is the new programming language? Inspired by the transformation of professional software engineering by generative AI, let’s take the next step: empowering end users. We can boost their productivity with hyper-customized software generated from natural language. This challenge needs research right across software engineering: requirements, architecture, coding, testing, verification, repair, and maintenance. We will survey current progress and open research questions in this exciting new area of programming language research.”
(Photo: Cogna website)