Maria Rauschenberger started her research by defining and integrating Usability and User Experience into different contexts in 2010. Her Ph.D. topic focuses on the early screening of dyslexia using a language-independent content game and machine learning. Her thesis supervisors are Prof. Dr. Ricardo Baeza-Yates and Prof. Dr. Luz Rello. Since January 2016, Maria is a member of the Web Science and Social Computing Group at the Universitat Pompeu Fabra in Barcelona, chaired by Carlos Castillo. Her excellent research has been awarded three times in a row with the fem:talent Scholarship from the University of Applied Science Emden/Leer, besides she received the prestigious German Reading Award in 2017. Her current research interest is about how to solve social issues with computer science techniques.
AG 1, AG 2, AG 3, INET, AG 4, AG 5, SWS, RG1, MMCI
How can we make better applications for social impact issues? For example, the combination of Human-Centered Design (HCD) and Data Science (DS) can be the answer to avoid biases in the collection of data with online-experiments and the analysis of small data.
This presentation shows how we combine HCD and DS to design applications and analyze the collected data for Good. We will focus mainly on the project: "Early screening of dyslexia using a language-independent content game and machine learning". With our two designed games (MusVis and DGames), we collected data sets (313 and 137 participants) in different languages (mainly Spanish and German) and evaluated them with machine learning classifiers. For MusVis, we mainly use content that refers to one single acoustic or visual indicator, while DGames content refers to generic content related to various indicators. Our results open the possibility of low-cost and early screening of dyslexia through the Web. In this talk, we will further address the techniques used from HCD and DS to reach these results.