This is the repository for the data for our paper "EmotionArcs: Emotion Arcs for 9,000 Literary Texts", Öhman et al. (2024), at the 8th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature (LaTeCH-CLfL 2024), St. Julians, Malta.
It is a dataset comprising emotional arcs and intensities from over 9,000 English novels (1880-2000), assembled to understand the dynamics of emotions represented in text and how these emotions may influence a novel’s reception and perceived quality.
- NRC emotions (anger, disgust, fear, anticipation, surprise, trust, sadness, joy)
- NRC emotion dictionary expanded for the literary domain using Word2Vec
- Data for 9,000 titles
- Author, title & year
- Emotion intensities
- Emotion arcs
Available formats: .xlsx, .json
| BOOK_ID | TITLE | AUTH_FIRST | AUTH_LAST | PUBL_DATE | ARC_ang | ARC_fea | ... | INTENS_ang | INTENS_joy | ... |
|---|---|---|---|---|---|---|---|---|---|---|
| 25732 | Infinite Jest | David Foster | Wallace | 1996 | 0.758,0.901... | 1.451,1.601... | ... | 70.44 | 102.37 | ... |
| 20636 | Dune | Frank | Herbert | 1965 | 2.918,5.031... | 4.164,4.231... | ... | 89.95 | 92.39 | ... |
| 22741 | Beloved | Toni | Morrison | 1987 | 7.603,5.461... | 7.806,6.235... | ... | 63.46 | 136.63 | ... |
| 21974 | The Gunslinger | Stephen | King | 1982 | 2.627,0.581... | 3.308,1.764... | ... | 84.02 | 102.07 | ... |
| 86 | The Portrait of a Lady | Henry | James | 1881 | 0.792,4.212... | 2.381,4.672... | ... | 40.59 | 169.74 | ... |
| Documentation | |
|---|---|
| 👩💻 Notebook | A notebook showing an example usage of the arcs. |
| 📄 Paper | The EmotionArcs paper. |
| 📚 Citation | Bibtex citation. |
| 🏆 The Chicago Corpus Data | The Chicago Corpus (a linked dataset with additional data about the books). |