Deep Emotions Across Languages: A Novel Approach for Sentiment Propagation in Multilingual WordNets

TL;DR

This paper presents two innovative techniques, MSSE and CLDNS, for automatically propagating sentiment annotations across multilingual WordNets, significantly enhancing emotional metadata enrichment in multiple languages.

Contribution

Introduces MSSE and CLDNS, novel methods for automatic sentiment annotation propagation in multilingual WordNets, improving efficiency and coverage.

Findings

MSSE+CLDNS outperforms existing methods in sentiment propagation

Effective enrichment of WordNets with emotional metadata across languages

Provides a foundation for large-scale multilingual sentiment analysis

Abstract

Sentiment analysis involves using WordNets enriched with emotional metadata, which are valuable resources. However, manual annotation is time-consuming and expensive, resulting in only a few WordNet Lexical Units being annotated. This paper introduces two new techniques for automatically propagating sentiment annotations from a partially annotated WordNet to its entirety and to a WordNet in a different language: Multilingual Structured Synset Embeddings (MSSE) and Cross-Lingual Deep Neural Sentiment Propagation (CLDNS). We evaluated the proposed MSSE+CLDNS method extensively using Princeton WordNet and Polish WordNet, which have many inter-lingual relations. Our results show that the MSSE+CLDNS method outperforms existing propagation methods, indicating its effectiveness in enriching WordNets with emotional metadata across multiple languages. This work provides a solid foundation for large-scale, multilingual sentiment analysis and is valuable for academic research and practical applications.