Is Sentiment Banana-Shaped? Exploring the Geometry and Portability of Sentiment Concept Vectors

2026-01-12

AI Summary

This study addresses the need for context-sensitive, continuous sentiment scoring in the humanities and the lack of systematic evaluation of existing methods’ transferability and geometric assumptions across domains, languages, and historical periods. The authors propose a Concept Vector Projection (CVP)-based approach that models sentiment as directional vectors in embedding space, enabling continuous, multilingual sentiment ratings. By constructing a comprehensive evaluation framework spanning diverse genres, historical eras, and languages, they provide the first systematic assessment of CVP’s cross-domain transferability and demonstrate that its underlying linearity assumption holds only approximately. Results show that CVP maintains strong transferability with minimal performance degradation across varied contexts and offers novel insights into the geometric structure of sentiment representations.

Technology Category

• Natural Language Processing: Sentiment Analysis, Stylistic Analysis, and Argument Mining
• Application Domains: Humanities & Computational Social Science
• Cognitive Modeling & Cognitive Systems: Affective Computing

Application Category

• Web Mining and Content Analysis: Sentiment analysis and opinion mining
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics

Abstract

Use cases of sentiment analysis in the humanities often require contextualized, continuous scores. Concept Vector Projections (CVP) offer a recent solution: by modeling sentiment as a direction in embedding space, they produce continuous, multilingual scores that align closely with human judgments. Yet the method's portability across domains and underlying assumptions remain underexplored. We evaluate CVP across genres, historical periods, languages, and affective dimensions, finding that concept vectors trained on one corpus transfer well to others with minimal performance loss. To understand the patterns of generalization, we further examine the linearity assumption underlying CVP. Our findings suggest that while CVP is a portable approach that effectively captures generalizable patterns, its linearity assumption is approximate, pointing to potential for further development.

Problem

• sentiment analysis
• concept vector projections
• portability
• linearity assumption
• cross-domain generalization

Innovation

• Concept Vector Projections
• sentiment geometry
• cross-domain portability
• linearity assumption
• multilingual sentiment analysis