A Unified Feature Representation for Lexical Connotations

TL;DR

This paper introduces a new lexical resource and embedding-based method for capturing word connotations, improving stance detection especially with limited data.

Contribution

It presents a novel approach to representing lexical connotations using distant labeling and embedding space modeling, enhancing stance detection performance.

Findings

Lexical resource aligns well with human judgments

Embedding-based representations improve stance detection accuracy

Method is effective with limited training data

Abstract

Ideological attitudes and stance are often expressed through subtle meanings of words and phrases. Understanding these connotations is critical to recognizing the cultural and emotional perspectives of the speaker. In this paper, we use distant labeling to create a new lexical resource representing connotation aspects for nouns and adjectives. Our analysis shows that it aligns well with human judgments. Additionally, we present a method for creating lexical representations that captures connotations within the embedding space and show that using the embeddings provides a statistically significant improvement on the task of stance detection when data is limited.