Ontology designed to formalize the dissemination of political discourse in digital media.

Code release for KCLarity at SemEval-2026 Task 6: Encoder and Zero-Shot Approaches to Political Evasion Detection

Toolkit for the paper "Explainable Subjective Stance Classification with SetFit in Political Discourse". The project leverages the SetFit few-shot learning framework, Sentence Transformers architecture, and traditional linguistic ML to enhance explainability in stance classification.

PFW at SemEval-2026 Task 6 (CLARITY): multi-seed DeBERTa ensembles for political response clarity & evasion classification. Macro F1 0.76 (18/41) on Subtask 1, 0.50 (12/33) on Subtask 2. Accepted at SemEval-2026.

Rhetorical analysis of Greek parliamentary speeches (2010–2020) using sentiment, complexity metrics, and semantic drift

NLP analysis of 107 political speech transcripts (TEI-XML corpus) — topic modeling, NER, cosine similarity, UMAP clustering & zero-shot classification · Python · spaCy

This Crawler was built as part of my PhD thesis to collect a huge corpus of political discourse by politicians in the USA.

An NLP project for SemEval-2026 Task 6: Detecting and classifying ambiguity in political interviews.