VLA-SSM: a visual learning analytics system for monitoring soft skills development through academic performance, STEM project participation, and stakeholder assessment

A comprehensive assessment of students’ soft skills alongside their academic achievement is an important task in higher education. The purpose of this study was to develop the Visual Learning Analytics System for Soft Skills Monitoring (VLA-SSM), which integrates academic performance, STEM project outcomes, and self-/peer-assessment data, and to examine the statistical relationships among these indicators in monitoring students’ soft skills. The study employed a quantitative research design and involved 122 first-year students enrolled in a Physics program. Descriptive statistics, Pearson correlation analysis, and simple linear regression analysis were used to analyze the data. The results showed that Project Grade was a statistically significant predictor of the Soft Skills Indicator ( β = 0.759, p < 0.001), with the regression model explaining 57.6% of the variance in the Soft Skills Indicator (R² = 0.576). VLA-SSM provides an integrated digital environment for collecting, processing, monitoring, and visualizing students’ academic performance, STEM project outcomes, and soft-skills-related assessment indicators. The system may support data-informed pedagogical decision-making and the planning of individual learning trajectories; however, the statistical findings should be interpreted as evidence of relationships among the integrated learning indicators rather than as direct evidence of the system's usability or technical effectiveness.