APPLICATION OF THE COMPOSITIONAL MACHINE LEARNING DYNAMIC CLASSIFICATION ALGORITHM FOR NATURAL LANGUAGE SENTIMENT ANALYSIS.

Item request has been placed! ×
Item request cannot be made. ×
loading   Processing Request
  • Additional Information
    • Abstract:
      The use of artificial intelligence methods for extract meaning from natural text is a scientific and practical field that is increasingly important in the context of creating software tools to interact with humans. Social networks generate a huge amount of textual information, the classification and proper processing of which can serve to counter crimes such as hate speech or provide useful information about events and trends in society. This paper presents an application of the author's Compositional Machine Learning Dynamic Classification (CoMLDC) algorithm. The algorithm dynamically classifies the emotional attitudes from Google's dataset GoEmotions collected from communications of users in a social network. The results of the research show the advantages of the dynamic multi-class classification of the presented algorithm, over the classic algorithms for machine learning classification. The main advantage over the existing algorithms for multi-class, multi-label classification is finding a dynamic set of classes to which a given text message to be assigned without having to train a separate classifier for each class or set a constant number of classes. Instead, the classification result produced by the algorithm is achieved based on mathematical transformations and calculations. [ABSTRACT FROM AUTHOR]
    • Abstract:
      Copyright of International Journal on Information Technologies & Security is the property of SAER Forum Group and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)