Information System for Detecting Abusive Speech in Audio Content by Means of Natural Language
Вантажиться...
Дата
2024
Автори
Назва журналу
Номер ISSN
Назва тому
Видавець
Анотація
An information technology for the detection of abusive speech is proposed, which is designed to receive input information in the form of a training set of data for a neural network model for
determining emotional tonality and test audio content of the output data in the form of a numerical assessment of the abusiveness of the content and a conclusion regarding the acceptability of content according to the level of abuse. Appropriate software was developed to study the effectiveness of information technology for detecting abusive speech in Ukrainian-language audio content. The Python programming language was used to implement the intelligent system. The developed software includes a software module for training recurrent neural network models and further saving trained instances, and a software module for detecting abusive manifestations in Ukrainian-language audio content using trained neural network models. The developed test software modules make it possible to conduct an applied study of the information technology for detecting abusive speech
Опис
Ключові слова
Бібліографічний опис
Nazarov V., Molchanova M. Information System for Detecting Abusive Speech in Audio Content by Means of Natural Language. Proceedings of V International Scientific and Practical Conference «Modern strategies of global scientific solutions». December 27-29, 2023. Stockholm, Sweden, International Scientific Unity. Pp. 132-135.