Abstract
We are interested in the textual features that correlate with the re- ported impact by readers of novels. We operationalize impact measurement through a rule-based reading impact model and apply it to 634,614 reader reviews mined from seven review platforms. We compute co-occurrences of impact-related terms and their keyness for genres represented in the corpus. The corpus consists of the full text of 18,885 books from which we derived topic models. The topics we find correlate strongly with genre, and we get strong indicators for which key impact terms are connected to which genre. These key impact terms give us a first evidence-based insight into genre-related readers’ motivations.
| Original language | English |
|---|---|
| Pages (from-to) | 1-32 |
| Number of pages | 32 |
| Journal | JCLS. Journal of Computational Literary Studies |
| Volume | 3 |
| Issue number | 1 |
| Early online date | 17 Oct 2024 |
| DOIs | |
| Publication status | Published - Oct 2024 |
| Externally published | Yes |
Keywords
- reader impact
- literary novels
- genre
- topic modeling
Fingerprint
Dive into the research topics of 'From Review to Genre to Novel and Back: An Attempt To Relate Reader Impact to Phenomena of Novel Text'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver