English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Open

Personalized learner modeling using cognitive diagnosis (CD), which aims tomodel learners' cognitive states by diagnosing learner traits from behavioraldata, is a fundamental yet significant task in many web learning services.Existing cognitive diagnosis models (CDMs) follow the proficiency-responseparadigm that views learner traits and question parameters as trainableembeddings and learns them through learner performance prediction. However, wenotice that this paradigm leads to the inevitable non-identifiability andexplainability overfitting problem, which is harmful to the quantification oflearners' cognitive states and the quality of web learning services. To addressthese problems, we propose an identifiable cognitive diagnosis framework(ID-CDF) based on a novel response-proficiency-response paradigm inspired byencoder-decoder models. Specifically, we first devise the diagnostic module ofID-CDF, which leverages inductive learning to eliminate randomness inoptimization to guarantee identifiability and captures the monotonicity betweenoverall response data distribution and cognitive states to preventexplainability overfitting. Next, we propose a flexible predictive module forID-CDF to ensure diagnosis preciseness. We further present an implementation ofID-CDF, i.e., ID-CDM, to illustrate its usability. Extensive experiments onfour real-world datasets with different characteristics demonstrate that ID-CDFcan effectively address the problems without loss of diagnosis preciseness.

Towards the Identifiability and Explainability for Personalized Learner Modeling: An Inductive Paradigm