In response to the growing challenge of propaganda through online media in online news, the increasing need for automated systems that can identify and classify narrative structures in multiple languages is evident. We present our approach to the SemEval-2025 Task 10 Subtask 2, focusing on the challenge of hierarchical multi-label, multi-class classification in multilingual news articles. Working with a two-level taxonomy of narratives and subnarratives in the Ukraine-Russia War and Climate Change domain, we present methods to handle long articles based on how they are naturally structured in the dataset, propose a hierarchical classification MLP with respect to the narrative taxonomy structure, and establish a continual learning training strategy that takes into advantage the multilingual nature of our data and tries to examine how different language orders affect performance. Our final system was evaluated in five languages, achieving competitive results while demonstrating low variance compared to similar systems in our leaderboard position.

We present an analysis of the sentiment in Greek political speech, by focusing on the most frequently occurring emotion in electoral data, the emotion of “disgust”. We show that emotion classification is generally tough, but high accuracy can be achieved for that particular emotion. Using our best-performing model to classify political records of the Greek Parliament Corpus from 1989 to 2020, we studied the points in time when this emotion was frequently occurring and we ranked the Greek political parties based on their estimated score. We then devised an algorithm to investigate the emotional context shift of words that describe specific conditions and that can be used to stigmatise. Given that early detection of such word usage is essential for policy-making, we report two words we found being increasingly used in a negative emotional context, and one that is likely to be carrying stigma, in the studied parliamentary records.

Proverbs carry wisdom transferred orally from generation to generation. Based on the place they were recorded, this study introduces a publicly-available and machine-actionable dataset of more than one hundred thousand Greek proverb variants. By quantifying the spatial distribution of proverbs, we show that the most widespread proverbs come from the mainland while the least widespread proverbs come primarily from the islands. By focusing on the least dispersed proverbs, we present the most frequent tokens per location and undertake a benchmark in geographical attribution, using text classification and regression (text geocoding). Our results show that this is a challenging task for which specific locations can be attributed more successfully compared to others. The potential of our resource and benchmark is showcased by two novel applications. First, we extracted terms moving the regression prediction toward the four cardinal directions. Second, we leveraged conformal prediction to attribute 3,676 unregistered proverbs with statistically rigorous predictions of locations each of these proverbs was possibly registered in.