BERT

Sentiment Analysis of Ukrainian-language Citizen Appeals: Classical Methods and Transformer Architectures

This article presents an expanded experimental comparison of the effectiveness of machine learning methods for the task of three-class sentiment classification (negative, positive, neutral). The research focuses on the specific domain of Ukrainian-language citizen appeals to city administration bodies, which is a relevant and practically significant task for the development of modern e-Governance and decision support systems.

INFORMATION TECHNOLOGY FOR IDENTIFYING PROPAGANDA IN TIKTOK COMMENTS BASED ON NLP AND DEEP LEARNING

The article investigates the current scientific problem of automated detection of propaganda influence in short text comments of users of the TikTok social network, which operates in conditions of hybrid warfare and intensive disinformation campaigns. A hybrid model for detecting propaganda content has been developed, which integrates deep contextual representations of the text (transformer-based contextual representations) based on the BERT architecture with an additional vector of semiotic and structural features (number of emojis, repetition of symbols, use of caps lock).

PREDICTION OF AN INDIVIDUAL’S EMOTIONAL STATE BASED ON TEXTUAL DATA USING BERT AND PAD MODELS

This paper examines the problem of predicting a user’s multidimensional emotional state from textual records under conditions where most existing text-based approaches emphasize either categorical emotion recognition or coarse sentiment polarity, which limits the interpretability of broader affective assessment.

Standardizing Arabic Dialects for NLP: A BERT-Based Transcoding Approach with a Focus on Moroccan Darija

Processing Arabic dialects in Natural Language Processing (NLP) presents significant challenges due to linguistic diversity and the lack of standardized resources.  While Modern Standard Arabic (MSA) benefits from advanced NLP tools and extensive annotated datasets, dialects such as Moroccan Darija remain underrepresented.  This study introduces a BERT-based transcoding framework that bridges the gap between dialectal Arabic and MSA, enabling the use of pre-trained models optimized for MSA, such as AraBERT.  By integrating contextual multilingual embeddings, the propose

Assessing the Quality of Scientific Publications: A Thorough Analysis of Citation-Based and Content-Oriented Metrics for Evaluating Research Impact and Scholarly Contribution

The evaluation of scientific publications is a cornerstone of scholarly research, providing essential insights into the impact, significance, and intellectual contributions of research outputs.  Traditional bibliometric indicators, including Impact Factor (IF), h-index, and citation counts, have historically been the dominant measures to assess research quality.  However, with the rapid evolution of Artificial Intelligence (AI) and its increasing integration into various scientific disciplines, these conventional evaluation methodologies are being reevaluated due to the

Data Set Formation Method for Checking the Quality of Learning Language Models of the Transitive Relation in the Logical Conclusion Problem Context

A method for data set formation has been developed to verify the ability of pre-trained models to learn transitivity dependencies. The generated data set was used to test the quality of learning the transitivity dependencies in the task of natural language inference (NLI). Testing of a data set with a size of 10,000 samples (MultiNLI) used to test the RoBerta model.