Redirecting to original paper in 30 seconds...

Click below to go immediately or wait for automatic redirect

arxiv_cl 75% Match Research Paper Linguists,Cultural Historians,NLP Researchers,Digital Humanities Scholars 3 weeks ago

Are Proverbs the New Pythian Oracles? Exploring Sentiment in Greek Sayings

large-language-models › evaluation
📄 Abstract

Abstract: Proverbs are among the most fascinating linguistic phenomena that transcend cultural and linguistic boundaries. Yet, much of the global landscape of proverbs remains underexplored, as many cultures preserve their traditional wisdom within their own communities due to the oral tradition of the phenomenon. Taking advantage of the current advances in Natural Language Processing (NLP), we focus on Greek proverbs, analyzing their sentiment. Departing from an annotated dataset of Greek proverbs, we expand it to include local dialects, effectively mapping the annotated sentiment. We present (1) a way to exploit LLMs in order to perform sentiment classification of proverbs, (2) a map of Greece that provides an overview of the distribution of sentiment, (3) a combinatory analysis in terms of the geographic position, dialect, and topic of proverbs. Our findings show that LLMs can provide us with an accurate enough picture of the sentiment of proverbs, especially when approached as a non-conventional sentiment polarity task. Moreover, in most areas of Greece negative sentiment is more prevalent.
Authors (2)
Katerina Korre
John Pavlopoulos
Submitted
October 15, 2025
arXiv Category
cs.CL
arXiv PDF

Key Contributions

This paper explores the sentiment of Greek proverbs using LLMs, creating an annotated dataset that includes local dialects and mapping the sentiment distribution across Greece. It demonstrates how LLMs can be exploited for accurate sentiment classification of proverbs and provides a combinatory analysis of sentiment based on geography, dialect, and topic, offering insights into cultural wisdom.

Business Value

This research contributes to the digital humanities and cultural preservation by leveraging AI to analyze and understand traditional wisdom. It can inform educational tools, cultural heritage projects, and linguistic research.