The research field of Explainable Artificial Intelligence provides approaches to automate the generation of explanations for decisions made by Artificial Intelligence (AI). In order to be able to design and use explanations effectively, it is essential to understand how explanations affect the users' interaction with AI. In the German-Israeli project "Guess The City / explAIn - lehAsbIr", we are investigating what roles explanations of modern XAI methods can play in the context of AI-supported learning - "Lehasbir" means "explain" in Hebrew.

Not many scientific studies have looked at how XAI can support users in learning so far. In practice, too, XAI is not yet frequently used in learning contexts, despite its great potential. The purpose of this project is to develop a learning app that generates explanations for its users based on the current state of XAI research and to assess its effectiveness. Users are presented with a learning game in which they correlate Google Streetview images from four cities in Germany and Israel – Berlin, Hamburg, Tel Aviv and Jerusalem – with the respective city. The AI is given the same task. Users are shown how the AI arrived at each decision by highlighting the image components that are essential for the correlation (highlighting the "feature relevance"). The app has a user-friendly interface and can be accessed easily either via smartphone or via a web browser on a computer. Users receive a score for their answers which they can use to compare their performance to that of the AI.

Cooperation partner: Prof. Dr. Lior Fink from the Behavioral Information Technology (BIT) Lab at Ben Gurion University in Beer Sheva, Israel

Project period: September 2021 – September 2022