FeelingBlue: A Corpus for Understanding the Emotional Connotation of Color in Context
AbstractWhile the link between color and emotion has been widely studied, how context-based changes in color impact the intensity of perceived emotions is not well understood. In this work, we present a new multimodal dataset for exploring the emotional connotation of color as mediat...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
The MIT Press
2023-01-01
|
| Series: | Transactions of the Association for Computational Linguistics |
| Online Access: | https://direct.mit.edu/tacl/article/doi/10.1162/tacl_a_00540/115241/FeelingBlue-A-Corpus-for-Understanding-the |
| _version_ | 1827917944921784320 |
|---|---|
| author | Amith Ananthram Olivia Winn Smaranda Muresan |
| author_facet | Amith Ananthram Olivia Winn Smaranda Muresan |
| author_sort | Amith Ananthram |
| collection | DOAJ |
| description |
AbstractWhile the link between color and emotion has been widely studied, how context-based changes in color impact the intensity of perceived emotions is not well understood. In this work, we present a new multimodal dataset for exploring the emotional connotation of color as mediated by line, stroke, texture, shape, and language. Our dataset, FeelingBlue, is a collection of 19,788 4-tuples of abstract art ranked by annotators according to their evoked emotions and paired with rationales for those annotations. Using this corpus, we present a baseline for a new task: Justified Affect Transformation. Given an image I, the task is to 1) recolor I to enhance a specified emotion e and 2) provide a textual justification for the change in e. Our model is an ensemble of deep neural networks which takes I, generates an emotionally transformed color palette p conditioned on I, applies p to I, and then justifies the color transformation in text via a visual-linguistic model. Experimental results shed light on the emotional connotation of color in context, demonstrating both the promise of our approach on this challenging task and the considerable potential for future investigations enabled by our corpus.1 |
| first_indexed | 2024-03-13T03:36:39Z |
| format | Article |
| id | doaj.art-a909652578074afcaa89f346922c330d |
| institution | Directory Open Access Journal |
| issn | 2307-387X |
| language | English |
| last_indexed | 2024-03-13T03:36:39Z |
| publishDate | 2023-01-01 |
| publisher | The MIT Press |
| record_format | Article |
| series | Transactions of the Association for Computational Linguistics |
| spelling | doaj.art-a909652578074afcaa89f346922c330d2023-06-23T18:59:22ZengThe MIT PressTransactions of the Association for Computational Linguistics2307-387X2023-01-011117619010.1162/tacl_a_00540FeelingBlue: A Corpus for Understanding the Emotional Connotation of Color in ContextAmith Ananthram0Olivia Winn1Smaranda Muresan2Department of Computer Science, Columbia University, USA. amith@cs.columbia.eduDepartment of Computer Science, Columbia University, USA. olivia@cs.columbia.eduDepartment of Computer Science, Columbia University, USA AbstractWhile the link between color and emotion has been widely studied, how context-based changes in color impact the intensity of perceived emotions is not well understood. In this work, we present a new multimodal dataset for exploring the emotional connotation of color as mediated by line, stroke, texture, shape, and language. Our dataset, FeelingBlue, is a collection of 19,788 4-tuples of abstract art ranked by annotators according to their evoked emotions and paired with rationales for those annotations. Using this corpus, we present a baseline for a new task: Justified Affect Transformation. Given an image I, the task is to 1) recolor I to enhance a specified emotion e and 2) provide a textual justification for the change in e. Our model is an ensemble of deep neural networks which takes I, generates an emotionally transformed color palette p conditioned on I, applies p to I, and then justifies the color transformation in text via a visual-linguistic model. Experimental results shed light on the emotional connotation of color in context, demonstrating both the promise of our approach on this challenging task and the considerable potential for future investigations enabled by our corpus.1https://direct.mit.edu/tacl/article/doi/10.1162/tacl_a_00540/115241/FeelingBlue-A-Corpus-for-Understanding-the |
| spellingShingle | Amith Ananthram Olivia Winn Smaranda Muresan FeelingBlue: A Corpus for Understanding the Emotional Connotation of Color in Context Transactions of the Association for Computational Linguistics |
| title | FeelingBlue: A Corpus for Understanding the Emotional Connotation of Color in Context |
| title_full | FeelingBlue: A Corpus for Understanding the Emotional Connotation of Color in Context |
| title_fullStr | FeelingBlue: A Corpus for Understanding the Emotional Connotation of Color in Context |
| title_full_unstemmed | FeelingBlue: A Corpus for Understanding the Emotional Connotation of Color in Context |
| title_short | FeelingBlue: A Corpus for Understanding the Emotional Connotation of Color in Context |
| title_sort | feelingblue a corpus for understanding the emotional connotation of color in context |
| url | https://direct.mit.edu/tacl/article/doi/10.1162/tacl_a_00540/115241/FeelingBlue-A-Corpus-for-Understanding-the |
| work_keys_str_mv | AT amithananthram feelingblueacorpusforunderstandingtheemotionalconnotationofcolorincontext AT oliviawinn feelingblueacorpusforunderstandingtheemotionalconnotationofcolorincontext AT smarandamuresan feelingblueacorpusforunderstandingtheemotionalconnotationofcolorincontext |