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

2025-10-15

AI Summary

This study addresses the lack of dialectal coverage in existing Greek proverb sentiment resources. We construct the first annotated Greek dialectal proverb sentiment dataset and pioneer the application of large language models (LLMs) to fine-grained, proverb-level sentiment classification, integrated with geographic information systems (GIS) to generate spatial sentiment distribution maps. Multidimensional statistical analysis reveals that negative sentiment predominates across most regions and that dialectal variation significantly modulates affective expression. Our contributions are threefold: (1) establishing an LLM-driven paradigm for proverb sentiment computation; (2) enabling spatial modeling and quantitative interpretation of traditional oral culture through sentiment geospatialization; and (3) providing a reusable methodological framework bridging linguistic geography and digital humanities.

Technology Category

• Natural Language Processing: Sentiment Analysis, Stylistic Analysis, and Argument Mining
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Data Mining & Knowledge Management: Mining of Spatial, Temporal or Spatio-Temporal Data

Application Category

• Web Mining and Content Analysis: Sentiment analysis and opinion mining
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

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.

Problem

• Analyzing sentiment in Greek proverbs using NLP techniques
• Mapping sentiment distribution across Greek dialects and regions
• Evaluating LLMs for non-conventional sentiment classification tasks

Innovation

• Using LLMs for sentiment classification of proverbs
• Creating a map showing sentiment distribution across Greece
• Combining geographic, dialect, and topic analysis of proverbs