Optimizing NLP-Text Classification in Knowledge Management Systems: A Literature Review
TL;DR
An outline of the evolution of NLP-based text classification methods from initial machine learning methods such as Naïve Bayes and Support Vector Machines to current sophisticated deep learning algorithms such as Convolutional Neural Networks, Recurrent Neural Networks, and Transformers is offered.
Abstract
Knowledge Management Systems (KMS) are required to organize and assign meaning to huge amounts of organizational knowledge that are largely in the form of unstructured text. Natural Language Processing (NLP), and more immediately methods of text categorization, has been one of the principal enabler technologies to enable KMS to be simpler by helping to automatically categorize documents, enhance searching for information, and assist in decision-making. This paper offers an outline of the evolution of NLP-based text classification methods from initial machine learning methods such as Naïve Bayes and Support Vector Machines to current sophisticated deep learning algorithms such as Convolutional Neural Networks, Recurrent Neural Networks, and Transformers. We offer real-world industry use cases, issues of scalability, explainability, and ethics and encapsulate research areas of existing gaps. The findings underscore the enormous potential of NLP text classification to assist the effectiveness and efficiency of knowledge management (KM) activities.