Reader’s Comment in on-Line Magazine as a Genre of Internet Discourse (By the Material of the German and Russian Languages)

Biryukova, Evgeniya Viktorovna; Sobyanina, Valentina A.; Volkova, Yuliya Vyacheslavovna

doi:10.30853/filnauki.2018-12-1.16

Cited by 3 publications

(3 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While a significant amount of studies examined toxic and aggressive behaviour in Russian-language social media source [7], [33], [41], there are a limited amount of research papers directly exploring the automatic classification of toxicity of the texts. Gordeev utilized Convolutional Neural Networks (CNNs) and Random Forest Classifier (RFC) for detecting the state of aggression in English-language and Russianlanguage texts [17].…”

Section: Related Workmentioning

confidence: 99%

“…We used pre-trained Multilingual BERT BASE Cased and ru-BERT, which support 104 languages, including Russian, with 12 stacked Transformer blocks, a hidden size of 768, 12 self-attention heads, and 110M parameters in general. The fine-tuning stage was performed with the recommended parameters from the paper [43] and the official repository 7 : a number of train epochs of 3, a number of warmup steps of 10%, a max sequence length of 128, a batch size of 32, and a learning rate of 5e-5.…”

Section: Bidirectional Encoder Representations From Transformersmentioning

confidence: 99%

“…For both models, we used recommended parameters from and the TensorFlow Hub page 8 : a number of train epochs of 100, a batch size of 32, and a learning rate of 3e-4. 6 https://github.com/google-research/bert/blob/master/multilingual.md 7 https://github.com/google-research/bert 8 https://www.tensorflow.org/hub/tutorials/text_classification_with_tf_hub…”

Section: Multilingual Universal Sentence Encodermentioning

confidence: 99%

See 2 more Smart Citations

Toxic Comments Detection in Russian

Smetanin¹

2020

Computational Linguistics and Intellectual Technologies

View full text Add to dashboard Cite

Currently, social network sites tend to be one of the major communication platforms in both offline and online space. Freedom of expression of various points of view, including toxic, aggressive, and abusive comments, might have a long-term negative impact on people’s opinions and social cohesion. As a consequence, the ability to automatically identify and moderate toxic content on the Internet to eliminate the negative consequences is one of the necessary tasks for modern society. This paper aims at the automatic detection of toxic comments in the Russian language. As a source of data, we utilized anonymously published Kaggle dataset and additionally validated its annotation quality. To build a classification model, we performed fine-tuning of two versions of Multilingual Universal Sentence Encoder, Bidirectional Encoder Representations from Transformers, and ruBERT. Finetuned RuBERT achieved F1 = 92.20%, demonstrating the best classification score. We made trained models and code samples publicly available to the research community.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Bidirectional Encoder Representations From Transformersmentioning

confidence: 99%

Section: Multilingual Universal Sentence Encodermentioning

confidence: 99%

See 1 more Smart Citation

Toxic Comments Detection in Russian

Smetanin¹

2020

Computational Linguistics and Intellectual Technologies

View full text Add to dashboard Cite

show abstract

Verbalisation of impoliteness in comments of German politicians in Instagram news posts

Arkhipova¹,

Sobyanina²

2022

Litera

View full text Add to dashboard Cite

This article focuses on the description of impoliteness in computer-mediated communication. The purpose of the study is to identify markers of verbal aggression a way of expressing impoliteness and to analyse the ways in which they are implemented. The material for this study was German-language comments under the Instagram posts of the largest German parties and German politicians who participated in the German Federal Chancellor elections (2021). As the main methods of research were used linguopragmatic and linguocultural types of analysis. In addition, this paper includes a continuous sampling of comments that contain signs of implicit and/or explicit verbal aggression. Then was done a contextual analysis of the selected comments. The analysis revealed that implicit and explicit types of verbal aggression are equally common in the comments under political figures' Instagram posts, and that both types of verbal aggression can be used simultaneously by the authors in the same comment. The most frequent lexical and grammatical means of implementation of verbal aggression were also distinguished. The conclusions drawn during the research can be used in further studies that focus on the peculiarities of realisation of verbal aggression in computer communication as well as in those that focus on speech culture in a computer-mediated communication.

show abstract

Методологический Алгоритм Анализа Отрицания Интерактивного Контраргумента

Фан¹

2022

Гуманитарные Науки

View full text Add to dashboard Cite

Статья посвящена методологическим аспектам исследования отрицания интерактивного контраргумента в текстах жанра интернет-комментария. Разработан пятиэтапный алгоритм изучения отрицания: 1) сбор корпуса сообщений-стимулов, 2) выявление интерактивных контраргументов, 3) и 4) обработка комментариев с отрицательной аргументацией и языковых средств их выражения, 5) прагма-диалектический анализ интерактивного контраргумента. Выявлены основные речевые модели отрицательного реагирования, из которых самой распространенной является конфронтационная речевая модель.

show abstract

Reader’s Comment in on-Line Magazine as a Genre of Internet Discourse (By the Material of the German and Russian Languages)

Cited by 3 publications

References 1 publication

Toxic Comments Detection in Russian

Toxic Comments Detection in Russian

Verbalisation of impoliteness in comments of German politicians in Instagram news posts

Методологический Алгоритм Анализа Отрицания Интерактивного Контраргумента

Contact Info

Product

Resources

About