University Student Survey on Online Learning Continuance Intention, 421 Responses

Survey data from 421 university students on their intention to continue using online learning platforms. The data was analyzed using five comparative machine learning models, including BiLSTM-Attention and Random Forest. The dataset was authored by Yizhen Wang and last updated on June 2, 2026.

Use Cases

• Modeling continuance intention based on psychological constructs like usefulness and trust.
• Comparing predictive performance of different ML architectures (e.g., BiLSTM, Transformer) on survey data.
• Investigating the relationship between affective appraisal and behavioral intention in educational contexts.
• Informing online learning platform design based on patterns of student trust and evaluative experience.

Strengths

• Data from 421 survey respondents provides a substantive sample size.
• Analysis reports high internal consistency and strong convergent validity for the retained constructs.
• Predictive models achieved a mean AUC between 0.936 and 0.954, indicating strong performance.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• Discriminant validity required cautious interpretation, particularly for the relationship between Affective Appraisal and Continuance Intention.

Provenance

Source

Yizhen Wang via figshare.

Collection Method

Survey data collected from university students.

Freshness

Last updated 2026-06-02 16:00:28; freshness should be verified.