Predictive Insights into Digital Competencies: A Data-Driven Approach to Inclusion

Abstract

Despite their significant demographic presence, accounting for nearly 16% of the global population, persons with disabilities (PWDs) remain underrepresented in research on their inclusion in digital society, revealing a significant gap in scientific understanding compared to the general population. To address this gap, this study proposes an innovative approach to empowering PWDs by developing predictive models that anticipate PWDs’ digital competence perceptions based on socio-demographic and contextual factors. The study was conducted on a sample of 250 PWDs in Serbia using a validated instrument based on the Digital Competence Framework (DigComp). Standard multiple regression was used to estimate the models for each DigComp competence area. The results show that three variables are statistically significant in all five DigComp areas: age, health conditions (walking impairments) and employment status (employed). The prediction of PWDs’ digital competence is also influenced by gender and education level, which were found to be statistically significant predictors in four DigComp competence areas. The development of predictive models that assess PWDs’ digital competence perceptions based on socio-demographic profiles enables personalized support and promotes digital inclusion through emerging technologies such as artificial intelligence (AI). The limitations of the study lie in the sample size, method of data collection and reliance on self-assessment.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 2 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.