Ekaterina Krivich

Dr. Ekaterina Krivich

orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
23 October 2025 in Preprints.org
Verified
Preprint
Open access
PDF file
EKEkaterina Krivich
Ekaterina Krivich
DHDanial Hooshyar
Danial Hooshyar
GŠGustav Šír
Gustav Šír
YYYeongwook Yang
Yeongwook Yang
MBMerja Lina Bauters
Merja Lina Bauters
Tommi KärkkäinenTommi Kärkkäinen
Tommi Kärkkäinen
Background and Objectives: Tracking and adapting to learners’ evolving knowledge is essential for effective teaching. In digital learning, Deep Knowledge Tracing (DKT) employs deep neural networks to analyze sequential learner interactions, model their evolving knowledge, and predict skill mastery over time. While DKT is widely studied, its real-world adoption remains limited. This review examines DKT research from 2015–2025 through the lens of responsible AI principles, investigating modeling trends, evaluation practices, input features used for representing learner performance and context, strategies for mitigating data quality issues, assessment of sequential stability (consistency of knowledge estimates over time), and interpretability for educators. Methods: Following PRISMA guidelines, five major scholarly databases (Web of Science, Scopus, ScienceDirect, ACM Digital Library, IEEE Xplore) and Google Scholar were searched, yielding 1,047 peer-reviewed articles. After two rounds of screening and a quality appraisal focused on methodological rigor, 84 studies were included in the final synthesis. Results: Graph-based architectures were most common (26.2%), followed by Hybrid/Meta (23.8%) and Attentive models (17.9%). ASSIST datasets were used in 82.1% of studies, and 90.5% predominantly used Area Under the Curve (AUC) for evaluation. A wide variety of input features were used, ranging from basic question–answer pairs and knowledge concepts to time-based metrics, difficulty levels, behavioral indicators, and learning resource interactions. Approaches to address data quality challenges appeared in 44.0% of studies. Only 3.6% quantitatively assessed sequential stability of predictions. Interpretability techniques—designed to make predictions understandable to educators—were present in 11.9% of studies. Conclusions: Current DKT models often overlook responsible AI principles, including robust handling of data quality issues, assessment of sequential stability of predictions, and interpretability of predictions. As AI regulatory frameworks increasingly mandate trustworthy and interpretable AI in education, future research should prioritize these principles for practical and responsible deployment.

3 October 2023
Verified
Conference Paper
Open access
EKEkaterina Krivich
Ekaterina Krivich
MMMati Mõttus
Mati Mõttus
MBMerja Lina Bauters
Merja Lina Bauters
The present study adds to the ongoing debate surrounding emotional responses to vicarious pain experienced towards humans and avatars. Empirical data on this topic has yielded controversial results: some studies report the same emotional responses towards humans and avatars experiencing pain, while others suggest different reactions. Our research strengthens the case for similarity. We investigated heart rate variability (HRV) and electrodermal activity (EDA)—physiological markers of emotion—in 23 adults from Estonia as they viewed videos depicting vicarious pain featuring either humans or avatars. We found no significant differences in HRV and EDA responses between the two conditions. These outcomes hint at the potential for avatars to mirror human-like responses, offering crucial insights for the broader use and design of avatars in various applications.

27 October 2026 in Electronics
Verified
Journal Article
Open access
PDF file
EKEkaterina Krivich
Ekaterina Krivich
GŠGustav Šír
Gustav Šír
Tommi KärkkäinenTommi Kärkkäinen
Tommi Kärkkäinen
DHDanial Hooshyar
Danial Hooshyar
Deep knowledge tracing (KT) models estimate students’ evolving skill mastery from sequences of question–response events and predict whether the next response will be correct. They are often compared using AUC, a score of how well predictions distinguish correct from incorrect answers. We evaluate two complementary aspects beyond AUC: temporal prediction behavior for 11 KT models on four educational datasets, and attribution diagnostics on ASSISTments 2017 data. The relationship between AUC and response-direction consistency varies by dataset: models with higher AUC sometimes show more, and sometimes fewer, prediction drops after correct answers or prediction rises after incorrect answers on repeated skills. Reference baselines further show that stability must be interpreted together with responsiveness, because a model that never updates its prediction also appears perfectly stable. In an exploratory ASSISTments 2017 analysis of 50 histories from 33 learners per model, gradient-based selected question–response events produce modest, model-dependent signed probability changes (original minus post-replacement probability) relative to recent-history, same-skill, and random controls. For practitioners comparing KT models, the paper contributes two practical checks to report alongside AUC: whether predictions respond coherently after student answers, and how explanation-selected history events compare with simple recent-history or same-skill alternatives under a shared intervention.