Methods of Automatic Selection of Named Entities (NER) in Uzbek Language for Text Tone Analysis

This paper investigates integrated approaches for automatic detection of named entities (Named Entity Recognition, NER) and sentiment analysis in Uzbek texts. The development proposes an architecture that combines NER and sentiment analysis, taking into account the morphological features of the Uzbek language and the lack of a sufficiently annotated database. The study performed named entity detection using the BiLSTM+CRF model (F1=0.82) and sentiment analysis using the Uzbek-tuned XLM-RoBERTa model (accuracy=89%). The results showed that the NER system allows for more accurate context analysis in sentiment assessment. In particular, geographical entities such as “Tashkent city” were evaluated as positive with 95% accuracy, and sentences such as “The new performance at the Navoi Theater was great” were evaluated as positive with 91% reliability. At the same time, dialectical expressions and ambiguous words created difficulties in the analysis. The results of the study can serve as a basis for improving NER and tonality analysis in Uzbek. It is recommended that future work be carried out to adapt transformer models to the Uzbek language and expand annotated corpora.