
This article investigates the potential of AI-powered tools for automating the assessment of technical writing skills in IT education. The study reviews current developments in automated writing assessment, identifies key competencies required for technical communication in computing disciplines, and proposes an AI-based framework for evaluating student submissions. The framework integrates NLP techniques, machine learning algorithms, and rubric-based assessment methods to evaluate grammar, coherence, structure, technical accuracy, and readability. The article further discusses the reliability, validity, and educational implications of automated assessment systems. The findings suggest that AI-powered assessment can significantly reduce instructor workload, provide timely feedback, and support personalized learning experiences while maintaining acceptable levels of assessment accuracy. However, challenges related to transparency, fairness, and ethical implementation remain important considerations for educational institutions.
artificial intelligence, automated writing assessment, technical writing, IT education, natural language processing, educational technology, large language models.
artificial intelligence, automated writing assessment, technical writing, IT education, natural language processing, educational technology, large language models.
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 0 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
