Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2601.07995 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918434023931904 |
|---|---|
| author | Lyngbaek, Laurits Feldkamp, Pascale Bizzoni, Yuri Nielbo, Kristoffer L. Enevoldsen, Kenneth |
| author_facet | Lyngbaek, Laurits Feldkamp, Pascale Bizzoni, Yuri Nielbo, Kristoffer L. Enevoldsen, Kenneth |
| contents | 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. Code available at: github.com/lauritswl/representation-transfer |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_07995 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Is Sentiment Banana-Shaped? Exploring the Geometry and Portability of Sentiment Concept Vectors Lyngbaek, Laurits Feldkamp, Pascale Bizzoni, Yuri Nielbo, Kristoffer L. Enevoldsen, Kenneth Computation and Language 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. Code available at: github.com/lauritswl/representation-transfer |
| title | Is Sentiment Banana-Shaped? Exploring the Geometry and Portability of Sentiment Concept Vectors |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2601.07995 |