PCA - Enhanced regression approach for predicting internet use based on formal education

Abstract

The regular use of digital devices and Internet applications in modern society is significantly influenced by the user's educational attainment. In educational institutions, particularly at the primary and secondary levels, digital technologies (DT) are recognized as essential to the teaching process. Current educational programs involve active use of DT in class and thus improve digital skills necessary for active engagement in the digital world. A hybrid machine learning model was built to analyze the impact of varying educational degrees on Internet usage and innovation investments across the European Union (EU) population. Principal component analysis (PCA) was employed for detecting the primary indicators of education and innovation, resulting in the reduction of the initial variables to two factors, one including four indicators and the other containing two indicators. Linear regression (LR) was applied on the PCA factor loadings derived from the primary factor, which exhibited a statistically significant relationship with the percentage of Internet usage (r = 0.767). The results demonstrate that formal education, supported by investments in innovations within the education system, are essential preconditions for the continued development of the digital society.