May 2021 - EduTec Science

May292021 by Daniele Di MitriNo Comments

Meine KI-Forschung hilft dabei, produktive Lernverläufe zu identifizieren und Kompetenzen zu verbessern

Artificial Intelligence, Higher Education, Multimodal Learning Analytics, Press

[This article appeared on bildungsserver.de and it was written by Christine Schumann for Deutscher Bildungsserver] Wie bei digitalen Lerneinheiten entstehende Daten für personalisiertes Feedback genutzt werden können. FRAGEN AN Daniele Di Mitri, der im April 2021 in der Kategorie Geistes- und Sozialwissenschaften zum AI-Newcomer des Jahres gewählt wurde. Am DIPF | Leibniz-Institut baut er gerade eine Forschungsgruppe zum Thema Künstliche Intelligenz auf, um verantwortungsvolle KI-Systeme für die Bildung zu entwickeln. Zurzeit konzentrieren sich seine Arbeiten auf praktische Lernaufgaben – und nicht auf allgemeine Lernsituationen im Klassenzimmer. Herr Di Mitri, sind Sie stolz auf Ihre Auszeichnung als „AI Newcomer“ des Jahres 2021? Ja, ich bin begeistert, dass ich im Rahmen des KI-Camps zum „AI Newcomer of 2021“ gewählt wurde. Das KI-Camp ist das nationale Event in Deutschland zur Künstlichen Intelligenz, das das Bundesministerium für…

May202021 by Daniele Di MitriNo Comments

Interview for Hessischer Rundfunk

Artificial Intelligence, Higher Education, Multimodal Learning Analytics, Press

Dr. Draniele Di Mitri was interviewed (in German) by Hessischer Rundfunk by Alexander Schmitt. The theme of the episode was: Artificial intelligence is penetrating deeper and deeper into our lives: we talk to computers, rely on their search results and will soon be driven by robot cars. The revolution is just beginning. What are young research talents in Hesse working on? [audio mp3="https://edutec.science/wp-content/uploads/2021/05/hr-info_wirtschaft_20210512_87919984-AudioTrimmer.com_.mp3"][/audio] Listen to the entire episode Below the answer to the questions translated into English: *** You are interested in education and in technology - is it related to your parents? Yes, I believe I inherited my two main passions from my parents. My father was a first-generation software engineer and my mother was a teacher. In my teenage years, my father showed me how to create a…

May32021 by Prof. Dr. Hendrik DrachslerNo Comments

New Pub: Towards Automatic Collaboration Analytics for Group Speech Data Using Multimodal Learning Analytics

General education, Journal, Multimodal Learning Analytics, Open access, Publication

Collaboration is an important 21st Century skill. Co-located (or face-to-face) collaboration (CC) analytics gained momentum with the advent of sensor technology. Most of these works have used the audio modality to detect the quality of CC. The CC quality can be detected from simple indicators of collaboration such as total speaking time or complex indicators like synchrony in the rise and fall of the average pitch. Most studies in the past focused on “how group members talk” (i.e., spectral, temporal features of audio like pitch) and not “what they talk”. The “what” of the conversations is more overt contrary to the “how” of the conversations. Very few studies studied “what” group members talk about, and these studies were lab based showing a representative overview of specific words as topic clusters…