Method of text classification without the use of training
Abstract
A new approach to text classification is proposed that does not employ machine learning methods or require a training set. The method is based on the Damerau-Levenshtein distance, which is the minimum number of editing operations required to transform one string into another and takes into account the semantic similarity of words, weighting of editing operations, and the order of importance of words. The main metrics for assessing the quality of a text classifier and the results of testing the proposed method against these metrics are presented.
Fields of Study & Subjects
Text and Document Classification Technologies
Natural Language Processing Techniques
Topic Modeling
Publication details
- Journal / source
- Известия высших учебных заведений. Приборостроение
- Volume
- 69
- Issue
- 1
- Pages
- 90–94
- Publication date
- 14 February 2026
- Language
- EN