An Analysis of the Effectiveness of Applying a Machine Learning Approach for Classification of Technical Documents in Knowledge Discovery Systems

An important component of knowledge management (KM) is the organization of documents for quick and easy access. One advantageous and effective way of organizing these documents is to group them by a fixed set of specific knowledge categories. For large-scale technical teams, the number of categories can reach thousands or even tens of thousands, which makes the aforementioned cataloging especially useful. Text classification (TC) is a sophisticated process that involves data pre-processing, transformation, dimensionality reduction, application of classification techniques, classifier evaluation, and classifier validation. TC remains a prominent research topic and still depends on human work rather than on machine learning (ML). It is a relatively new area of research and remains in a premature phase. The goal is to develop and evaluate a prototype model that uses ML algorithms to classify technical documentation in a KM system for technical teams of financial institutions involved in software development projects. This research contributes to the field of KM by determining whether an ML approach constitutes a feasible solution for TC in knowledge discovery.