G. Sidorov

Exploring Crime Reports from Social Media Through Transformer-Based Text Classification and Geovisualization

The analysis of criminal acts is of great importance within society, as it enables the identification of high-risk areas with elevated crime rates. This type of knowledge not only provides insightful information about the safety of the environment to the population but can also serve as a strategic instrument for direc...

VCR at Hope-EXP2026: Parameter-Efficient Large Language Models and Multilingual Transformers for Hope Speech Analysis ⋆

Multilingual Social Support Detection Using Transformer-Based Sentence Embeddings and Hierarchical Classification at IberLEF 2026

A BERT BiLSTM and BiTCN model for suicidal ideation identification in Spanish texts

This study proposes a computational model for detecting suicidal ideation in Spanish-language social media posts that combines Transformer-based representations with BiLSTM and BiTCN neural network layers to capture contextual and sequential linguistic patterns.

Multiclass Sentiment Analysis for Identifying Political Viewpoints

This work designs and evaluates two machine-learning approaches based on XGBoost and BERT to automatically discriminate multiple sentiment classes over political issues and figures, and demonstrates the challenge of classifying complex and contextualized political discourse sentiment.

H-FuseNet: A Hybrid Multi-Representation Fusion Framework for Robust Misinformation Detection

H-FuseNet is proposed, a hybrid multi-representation fusion framework that combines pretrained transformer representations with deception-oriented handcrafted linguistic, stylistic, and semantic features that can improve the reliability of automated fake news detection systems.