Predicting emotional links between genre, plot, and reader response
| Autor: | Sharma, Srishti, Pianzola, Federico |
|---|---|
| Rok vydání: | 2022 |
| Předmět: |
online book reviews
Communication computational literary studies digital literary studies digital social reading Linguistics Experimental Analysis of Behavior Social and Behavioral Sciences FOS: Sociology Computational Linguistics FOS: Psychology Sociology sentiment analysis reader response reading impact FOS: Languages and literature Communication Technology and New Media Psychology digital humanities natural language processing Critical and Cultural Studies Social Media Library and Information Science |
| DOI: | 10.17605/osf.io/xg6d4 |
| Popis: | The purpose of this article is to explore the effect of the emotions expressed in fictional stories on the emotions experienced by their readers. We use around 450 books from 9 different genres and their corresponding reviews from Goodreads. We use sentiment analysis, calculating three different types of sentiment values: the average book sentiment, the average review sentiment and the emotion story arc of each book. We use three different methods, namely, a dictionary-based approach, a transformer-based approach, and a vector-space model approach. We then define the plot type of every book by clustering the emotion story arc using k-means with Dynamic time warping Barycenter Averaging (DBA) as the distance metric. We test our hypotheses using linear regression models (ANCOVA) to analyze the covariance between the sentiment values of books and reviews. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|