Boshko Koloski

Incremental Graph Construction Enables Robust Spectral Clustering of Texts

Abstract Neighborhood graphs over document embeddings are a common component of text-mining pipelines, supporting topic discovery, deduplication, semi-supervised label propagation, and retrieval-index construction, and they are a critical but fragile step in spectral clustering o...

Evaluating fine-tuned, embedding-based, and zero-shot models for aspect-based sentiment analysis in South Slavic news

In the contemporary digital media landscape, the ability to automatically distill public opinion from a vast and continuous stream of information is highly important. Aspect-Based Sentiment Analysis (ABSA) offers this granular capability. In this work, we address a specific, indu...