Ripple: Concept-Based Interpretation for Raw Time Series Models in Education

Source publication / research team or educational organization described in paper

Not specified in extracted text

Researchers, educators, instructors, or facilitators as described in the source publication

• Research / curriculum design context

Classroom, course, or resource-based AI education activity

10 weeks

our pipeline on a large educational data set including 23 MOOCs with over 100, 000 students and millions of in- teractions, addressing the following research questions: 1. Can we use raw time series as input and

ML concepts / supervised learning, Explainable AI / robustness, Assessment / tutoring analytics

• High-stakes or student-data-centered AI use requires stronger governance, transparency, and bias monitoring.

Unspecified / broad education

Mixed or not explicitly specified; infer from target learner group and intervention design.

Varies by intervention; not specified unless the paper explicitly describes prerequisites.

• Document the AI education intervention, course, tool, or resource described in the source publication.
• Extract the learner context, AI role, pedagogy, outcomes, and constraints for AAB registry comparison.
• Time series is the most prevalent form of input data for edu- cational prediction tasks.

• Support AAB comparison across AI literacy, AI education, teacher training, higher education, and workforce contexts.
• Capture evidence maturity, transferability, and limitations rather than treating the publication as product endorsement.

• Not an AAB endorsement of the tool, curriculum, provider, or result.
• Not a direct replication record unless the source paper reports implementation details sufficient for replication.

ML concepts / supervised learning, Explainable AI / robustness, Assessment / tutoring analytics

Not specified in extracted text

• Evaluator

• Primary interaction pattern inferred from publication: Assessment support.
• AI capability focus: ML concepts / supervised learning, Explainable AI / robustness, Assessment / tutoring analytics.

• Minimize personal data collection and avoid storing identifiable learner media unless approved by local policy/IRB.

• Review the publication’s reported context, learner group, AI tool or curriculum, implementation process, and outcome evidence.
• Map the case to AAB registry fields for comparison across educational levels and AI capability types.
• Use the source publication and PDF for any manual verification before public registry release.

• Human educators/researchers remain responsible for instructional design, supervision, interpretation, and ethical safeguards.
• AI systems or AI concepts provide the learning object, support tool, evaluator, simulator, or automation context depending on the paper.

• Instructional / curriculum-based learning
• Registry extraction emphasizes explicit learning goals, observed outcomes, constraints, and safety limitations.

• High-stakes or student-data-centered AI use requires stronger governance, transparency, and bias monitoring.

• Case classified under: Published curriculum / implementation paper.
• Pedagogical pattern: Instructional / curriculum-based learning.
• Any additional adaptations should be verified against the full paper before public-facing publication.

• Engagement evidence should be interpreted according to the source paper’s reported method and sample.
• The vast majority of research using time series data focuses on hand-crafted features, designed by experts for predictive performance and interpretability.

• The vast majority of research using time series data focuses on hand-crafted features, designed by experts for predictive performance and interpretability.

Time series is the most prevalent form of input data for edu- cational prediction tasks. The vast majority of research using time series data focuses on hand-crafted features, designed by experts for predictive performance and interpretability.

• Minimize personal data collection and avoid storing identifiable learner media unless approved by local policy/IRB.

• Learning analytics

• Can be used as an AAB evidence record for cross-case comparison, standards drafting, and evidence-maturity mapping.
• Supports identification of recurring patterns in AI literacy, AI education implementation, teacher preparation, assessment, and responsible AI learning.

• Conceptual understanding
• Assessment / feedback quality
• Assessment support
• ML concepts / supervised learning
• Explainable AI / robustness
• Assessment / tutoring analytics

• Completed

Unspecified / broad education

Research / curriculum design context

ML concepts / supervised learning, Explainable AI / robustness, Assessment / tutoring analytics

Instructional / curriculum-based learning

High

High

Ripple: Concept-Based Interpretation for Raw Time Series Models in Education

• Mohammad Asadi
• Vinitra Swamy
• Jibril Frej
• Julien Vignoud
• Mirko Marras
• Tanja Käser

Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 37 No. 13, EAAI-23

2023

10.1609/aaai.v37i13.26888

https://ojs.aaai.org/index.php/AAAI/article/view/26888

https://ojs.aaai.org/index.php/AAAI/article/view/26888/26660

079_Ripple_ Concept-Based Interpretation for Raw Time Series Models in Education.pdf

9

Time series is the most prevalent form of input data for edu- cational prediction tasks. The vast majority of research using time series data focuses on hand-crafted features, designed by experts for predictive performance and interpretability. However, extracting these features is labor-intensive for hu- mans and computers. In this paper, we propose an approach that utilizes irregular multivariate time series modeling with graph neural networks to achieve comparable or better accu- racy with raw time series clickstreams in comparison to hand- crafted features. Furthermore, we extend concept activation vectors for interpretability in raw time series models. We an- alyze these advances in the education domain, addressing the task of early student performance prediction for downstream targeted interventions and instructional support. Our exper- imental analysis on 23 MOOCs with millions of combined interactions over six behavioral dimensions show that models designed with our approach can (i) beat state-of-the-art edu- cational time series baselines with no feature extraction and (ii) provide interpretable insights for personalized interven- tions. Source code: https://github.com/epfl-ml4ed/ripple/.

• Research / curriculum design context

• High-stakes or student-data-centered AI use requires stronger governance, transparency, and bias monitoring.

Not specified in extracted text unless noted in duration field.

Requires educators/researchers/facilitators with sufficient AI literacy and pedagogy knowledge for the target learners.

Infrastructure depends on AI tool type, learner devices, data access, and institutional policy context.

High

This entry was automatically extracted from the PDF text and manifest metadata. Fields should be manually verified before public registry publication, especially group size, location, duration, and outcome claims.