We submitted an application to determine the authorship of anonymous Ukrainian texts on the Internet
March 29, 2024
0
The Ukrainian Scientific Center for Linguistic Research presented a project to determine the authorship of anonymous Ukrainian texts on the Internet. The presentation of the project took place
The Ukrainian Scientific Center for Linguistic Research presented a project to determine the authorship of anonymous Ukrainian texts on the Internet.
The presentation of the project took place at Ukrinform.
“As a result of our work, we received the application TextAttributor 1.0, which can perform a number of tasks: automatic linguistic analysis of the text, attribution of the text in the Ukrainian language, stylometry of the author’s texts, determination of the toxicity of the Ukrainian language text, detection of hate speech in social networks, candidate of philological sciences Oksana Zuban said at the presentation. automatic generation of expert opinion on text citation,” he said.
He stated that the aim of the project is to create a system for parameterization of Ukrainian-language media text that will serve as a tool for linguistic analysis in telemetry missions, determining authorship and determining the toxicity of the text.
As Zuban adds, the application analyzes any text according to 18 parameters; Among these, the basic parameters include the number of words, the number of sentences and the volume of the dictionary. The other 15 parameters are calculated according to specific formulas. One of these parameters is the text toxicity index, which takes into account verbal characteristics calculated according to the formula and systematized in separate databases.
The application’s database includes a lexicographic dictionary of 5 thousand words containing words with a negative tone, a dictionary of hate speech of 3 thousand words containing negative human names, obscene and abusive words, a dictionary of toxic compounds consisting of 1.5 thousand sequences that convey a negative meaning only in a certain combination of words.
During the presentation of the project, scientists demonstrated the operation of the TextAttributor 1.0 web application to determine the possible authorship of anonymous texts and detect the level of toxicity of the content.
The project was implemented by the Ukrainian Language Center together with the Institute of Taras Shevchenko National Philological University with the support of the Embassy of Great Britain and Northern Ireland.
As an experienced journalist and author, Mary has been reporting on the latest news and trends for over 5 years. With a passion for uncovering the stories behind the headlines, Mary has earned a reputation as a trusted voice in the world of journalism. Her writing style is insightful, engaging and thought-provoking, as she takes a deep dive into the most pressing issues of our time.