Spot the Bot: Semantic Paths of Natural Language Texts

Student: Aleksandra Kogan

Educational Programme: Data Science (Master)

Year of Graduation: 2024

Models for text generation - bots - have recently become widespread. Consequently, classifying texts into those generated by a bot and those written by a person is a major problem. Despite the significant amount of work in this area, most of them are focused on detecting a specific bot. Moreover, there are no sufficiently complete studies of semantic spaces of natural language texts. This study proposes a new approach to the problem of bot detection, based on the analysis of the structures of semantic spaces obtained using clustering and graph approach. As a result of the current work, clustering of semantic trajectories was analyzed for various languages and classifiers that demonstrated good quality (F-measure > 0.9) in detecting bots whose texts the models were not trained on were built.

Student Theses at HSE must be completed in accordance with the University Rules and regulations specified by each educational programme.

Summaries of all theses must be published and made freely available on the HSE website.

The full text of a thesis can be published in open access on the HSE website only if the authoring student (copyright holder) agrees, or, if the thesis was written by a team of students, if all the co-authors (copyright holders) agree. After a thesis is published on the HSE website, it obtains the status of an online publication.

Student theses are objects of copyright and their use is subject to limitations in accordance with the Russian Federation’s law on intellectual property.

In the event that a thesis is quoted or otherwise used, reference to the author’s name and the source of quotation is required.

Search all student theses