Identifying Reproductive Behavior Arguments in Social Media Content Users’ Opinions through Natural Language Processing Techniques

Kalabikhina, I.; Zubova, E.; Loukachevitch, N.; Kolotusha, A.; Kazbekova, Z.; Banin, E.; Klimenko, G.

Статья опубликована в журнале из списка RSCI Web of Science

Информация о цитировании статьи получена из Scopus
Статья опубликована в журнале из списка Web of Science и/или Scopus
Дата последнего поиска статьи во внешних источниках: 20 февраля 2024 г.

Авторы: Kalabikhina I., Zubova E., Loukachevitch N., Kolotusha A., Kazbekova Z., Banin E., Klimenko G.
Журнал: Population and Economics
Том: 7
Номер: 2
Год издания: 2023
Издательство: Московский государственный университет им. М.В. Ломоносова
Местоположение издательства: Москва
Первая страница: 40
Последняя страница: 59
DOI: 10.3897/popecon.7.e97064
Аннотация: Big data provides researchers with valuable sources of information for studying demographic behavior in the population. One such source is the texts posted by social network users on various demographic issues. This study utilizes methods for automatically extracting user opinions from the “VKontakte” social network. The extracted texts are then classified using the Conversational RuBERT neural network model to investigate opinions related to reproductive behavior in the population. The classification process addresses two consecutive problems. Firstly, it aims to identify whether a user’s comment contains argumentation. Secondly, if an argument is present, it seeks to determine its type within the context of the “personal-public” dichotomy. To search for arguments and classify their types, six experiments were conducted, varying the dataset and the number of classes. The method employed for automatic extraction and classification of user opinions on the “VKontakte” social network has demonstrated the ability to accurately classify users’ comments, identifying the presence of argumentation and categorizing the arguments within the “personal-public” dichotomy. This enables the identification of personal and social attitudes, values, stories, and opinions, thus facilitating the study of reproductive behavior.
Добавил в систему: Казбекова Зарина Германовна

	ИСТИНА	Войти в систему Регистрация
	ИСТИНА ЦЭМИ РАН
	Главная Поиск Статистика О проекте Помощь

ИСТИНА

ИСТИНА ЦЭМИ РАН

Identifying Reproductive Behavior Arguments in Social Media Content Users’ Opinions through Natural Language Processing Techniquesстатья

Прикрепленные файлы