Gender identification in Russian written texts

Abstract

This article examines the identification of the gender of authors of Russian written texts using the quantitative parameters analysis approach. Identification of the gender of authors of texts is viewed as part of authorship profiling task. The material used for the study was a specially designed corpus of Russian texts "RusPersonality" which (along with other Slavic languages) has obtained little attention in authorship profiling studies. We made use of high-frequency text parameters occurring in texts of diffetent topics and genres. The correlation analysis data obtained using Russian texts were compared with those in other languages. The regression analysis was employed. The suggested approach allows one to identify gender as accurately as 64% using only 5 parameters.

The voice of Twitter: observable subjective well-being inferred from tweets in Russian

“…The best system ( Markov et al, 2017 ) reached only 68.25% accuracy in binary classification, and the organizers of the track hypothesised ( Litvinova et al, 2017b ) that the problem was that tweets are shorter and grammatically poorer in comparison with other sources ( e.g ., Facebook posts or essays). There were other studies on text-based gender detection that reported higher results, such as Sboev et al (2019) , which showed 0.62 accuracy on LiveJournal posts; Litvinova et al (2017a) achieved accuracy of 0.72 on tweets and 0.71 on Facebook posts; and Bogachev et al (2020) reported of 0.84 on RusPersonality ( Litvinova et al, 2016 ). Besides linguistic characteristics, some studies also considered information from user profiles as well as social graph.…”

Мислення Та Сприйняття: Логічне Та Кліпове Мислення Майбутніх Фахівців

“…Вчені з усього світу вивчають ці зміни та їх наслідки у різних сферах людського життя. Дослідження в цих областях можуть допомогти розуміти, як інформаційні технології впливають на людську поведінку та допомогти розробляти стратегії, які максимально використовують позитивні наслідки інформаційних технологій, зменшуючи їхні негативні наслідки [4].…”

Automated Deep Learning Framework for Accurate Human Identity and Gender Detection

“…The phrase "biometrics" may refer to a broad variety of various sorts of personal information, including but not limited to an individual's age, gender, and handedness, as well as other basic physical human traits that are unique to that person [1]. Research into the field of soft biometrics has exploded in recent years.…”