Daniele Di Mitri

Prof. Dr. Daniele Di Mitri

Research Centre Extended Reality, German University of Digital Science, Potsdam, Brandenburg, Germany
orcid

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
23 July 2018 in Journal of Computer Assisted Learning
Verified
Journal Article
Open access
PDF file
Daniele Di MitriDaniele Di Mitri
Daniele Di Mitri
JSJan Schneider
Jan Schneider
MSMarcus Specht
Marcus Specht
HDHendrik Drachsler
Hendrik Drachsler
Multimodality in learning analytics and learning science is under the spotlight. The landscape of sensors and wearable trackers that can be used for learning support is evolving rapidly, as well as data collection and analysis methods. Multimodal data can now be collected and processed in real time at an unprecedented scale. With sensors, it is possible to capture observable events of the learning process such as learner's behaviour and the learning context. The learning process, however, consists also of latent attributes, such as the learner's cognitions or emotions. These attributes are unobservable to sensors and need to be elicited by human‐driven interpretations. We conducted a literature survey of experiments using multimodal data to frame the young research field of multimodal learning analytics. The survey explored the multimodal data used in related studies (the input space) and the learning theories selected (the hypothesis space). The survey led to the formulation of the Multimodal Learning Analytics Model whose main objectives are of (O1) mapping the use of multimodal data to enhance the feedback in a learning context; (O2) showing how to combine machine learning with multimodal data; and (O3) aligning the terminology used in the field of machine learning and learning science.

25 January 2024 in International Journal of Artificial Intelligence in Education
Verified
Journal Article
Open access
PDF file
SGSebastian Gombert
Sebastian Gombert
AFAron Fink
Aron Fink
TGTornike Giorgashvili
Tornike Giorgashvili
IJIoana Jivet
Ioana Jivet
Daniele Di MitriDaniele Di Mitri
Daniele Di Mitri
HDHendrik Drachsler
Hendrik Drachsler
Various studies empirically proved the value of highly informative feedback for enhancing learner success. However, digital educational technology has yet to catch up as automated feedback is often provided shallowly. This paper presents a case study on implementing a pipeline that provides German-speaking university students enrolled in an introductory-level educational psychology lecture with content-specific feedback for a lecture assignment. In the assignment, students have to discuss the usefulness and educational grounding (i.e., connection to working memory, metacognition or motivation) of ten learning tips presented in a video within essays. Through our system, students received feedback on the correctness of their solutions and content areas they needed to improve. For this purpose, we implemented a natural language processing pipeline with two steps: (1) segmenting the essays and (2) predicting codes from the resulting segments used to generate feedback texts. As training data for the model in each processing step, we used 689 manually labelled essays submitted by the previous student cohort. We then evaluated approaches based on GBERT, T5, and bag-of-words baselines for scoring them. Both pipeline steps, especially the transformer-based models, demonstrated high performance. In the final step, we evaluated the feedback using a randomised controlled trial. The control group received feedback as usual (essential feedback), while the treatment group received highly informative feedback based on the natural language processing pipeline. We then used a six items long survey to test the perception of feedback. We conducted an ordinary least squares analysis to model these items as dependent variables, which showed that highly informative feedback had positive effects on helpfulness and reflection.

1 December 2022 in International Journal of Artificial Intelligence in Education
Verified
Journal Article
Open access
PDF file
Daniele Di MitriDaniele Di Mitri
Daniele Di Mitri
Jan SchneiderJan Schneider
Jan Schneider
HDHendrik Drachsler
Hendrik Drachsler
This paper describes the CPR Tutor, a real-time multimodal feedback system for cardiopulmonary resuscitation (CPR) training. The CPR Tutor detects training mistakes using recurrent neural networks. The CPR Tutor automatically recognises and assesses the quality of the chest compressions according to five CPR performance indicators. It detects training mistakes in real-time by analysing a multimodal data stream consisting of kinematic and electromyographic data. Based on this assessment, the CPR Tutor provides audio feedback to correct the most critical mistakes and improve the CPR performance. The mistake detection models of the CPR Tutor were trained using a dataset from 10 experts. Hence, we tested the validity of the CPR Tutor and the impact of its feedback functionality in a user study involving additional 10 participants. The CPR Tutor pushes forward the current state of the art of real-time multimodal tutors by providing: (1) an architecture design, (2) a methodological approach for delivering real-time feedback using multimodal data and (3) a field study on real-time feedback for CPR training. This paper details the results of a field study by quantitatively measuring the impact of the CPR Tutor feedback on the performance indicators and qualitatively analysing the participants’ questionnaire answers.

15 December 2022 in Journal of Computer Assisted Learning
Verified
Journal Article
Open access
SGSebastian Gombert
Sebastian Gombert
Daniele Di MitriDaniele Di Mitri
Daniele Di Mitri
OKOnur Karademir
Onur Karademir
MKMarcus Kubsch
Marcus Kubsch
HKHannah Kolbe
Hannah Kolbe
HDHendrik Drachsler
Hendrik Drachsler
Background: Formative assessments are needed to enable monitoring how student knowledge develops throughout a unit. Constructed response items which require learners to formulate their own free‐text responses are well suited for testing their active knowledge. However, assessing such constructed responses in an automated fashion is a complex task and requires the application of natural language processing methodology. In this article, we implement and evaluate multiple machine learning models for coding energy knowledge in free‐text responses of German K‐12 students to items in formative science assessments which were conducted during synchronous online learning sessions.Dataset: The dataset we collected for this purpose consists of German constructed responses from 38 different items dealing with aspects of energy such as manifestation and transformation. The units and items were implemented with the help of project‐based pedagogy and evidence‐centered design, and the responses were coded for seven core ideas concerning the manifestation and transformation of energy. The data was collected from students in seventh, eighth and ninth grade.Methodology: We train various transformer‐ and feature‐based models and compare their ability to recognize the respective ideas in students' writing. Moreover, as domain knowledge and its development can be formally modeled through knowledge networks, we evaluate how well the detection of the ideas within responses translated into accurate co‐occurrence‐based knowledge networks. Finally, in terms of the descriptive accuracy of our models, we inspect what features played a role for which prediction outcome and if the models pick up on undesired shortcuts. In addition to this, we analyze how much the models match human coders in what evidence within responses they consider important for their coding decisions.Results: A model based on a modified GBERT‐large can achieve the overall most promising results, although descriptive accuracy varies much more than predictive accuracy for the different ideas assessed. For reasons of comparability, we also evaluate the same machine learning architecture using the SciEntsBank 3‐Way benchmark with an English RoBERTa‐large model, where it achieves state‐of‐the‐art results in two out of three evaluation categories.

1 January 2024 in IEEE Transactions on Learning Technologies
Verified
Journal Article
Open access
AZAndrea Zanellati
Andrea Zanellati
Daniele Di MitriDaniele Di Mitri
Daniele Di Mitri
MGMaurizio Gabbrielli
Maurizio Gabbrielli
OLOlivia Levrini
Olivia Levrini
Knowledge tracing is a well-known problem in AI for education, consisting of monitoring how the knowledge state of students changes during the learning process and accurately predicting their performance in future exercises. In recent years, many advances have been made thanks to various machine learning and deep learning techniques. Despite their satisfactory performances, they have some pitfalls, e.g., modeling one skill at a time, ignoring the relationships between different skills, or inconsistency for the predictions, i.e., sudden spikes and falls across time steps. For this reason, hybrid machine-learning techniques have also been explored. With this systematic literature review, we aim to illustrate the state of the art in this field. Specifically, we want to identify the potential and the frontiers in integrating prior knowledge sources in the traditional machine learning pipeline as a supplement to the normally considered data. We applied a qualitative analysis to distill a taxonomy with the following three dimensions: knowledge source, knowledge representation, and knowledge integration. Exploiting this taxonomy, we also conducted a quantitative analysis to detect the most common approaches.

19 November 2024 in Journal of Computer Assisted Learning
Verified
Journal Article
Open access
RKRashmi Khazanchi
Rashmi Khazanchi
Daniele Di MitriDaniele Di Mitri
Daniele Di Mitri
HDHendrik Drachsler
Hendrik Drachsler
Background: Despite educational advances, poor mathematics achievement persists among K‐12 students, particularly in rural areas with limited resources and skilled teachers. Artificial Intelligence (AI) based systems have increasingly been adopted to support the diverse learning needs of students and have been shown to enhance mathematics achievement through personalized learning experiences by adapting to student's needs. Existing studies have documented the positive impact of AI‐based systems on mathematics achievement. However, there is a lack of research that has studied AI‐based systems on students' mathematics achievement and engagement in rural settings. The present study addresses the existing literature gap by focusing on the AI‐based Edmentum Exact Path, analyzing its effectiveness in enhancing mathematics achievement and engagement among 8th‐grade students in rural schools in the Southern United States. By examining both cognitive and affective engagement, along with students' mathematics achievement, this research explores the role of AI‐based systems in student learning.Objective: This study aims to explore the effectiveness of Edmentum Exact Path, an AI‐based system, in improving 8th‐grade students' mathematics achievement and affective and cognitive engagement in the Southern United States.Methods: This study utilized a quasi‐experimental design involving 78 students from socioeconomically disadvantaged backgrounds, comparing those receiving supplemental Edmentum Exact Path‐led instruction and traditional teacher‐led methods to a control group receiving only the teacher‐led instructions. Mathematics achievement was measured through pre‐tests and post‐tests, while student engagement was assessed using the 5‐point Student Engagement Instrument (SEI). Statistical analysis was performed using t‐tests and ANOVA.Results and Conclusions: The findings revealed statistically significant improvements in mathematics achievement for both the experimental and control groups. However, the group using teacher‐led instruction showed a statistically significant improvement in affective engagement, while no statistically significant differences were observed in cognitive engagement between groups.Implications: The findings suggest that integrating AI‐based systems like Edmentum Exact Path may enhance affective engagement in mathematics among students from rural areas. However, the impact on cognitive engagement remains unclear, indicating a need for further research. These results support the potential for integrating AI‐based systems to enhance mathematics achievement in rural settings.