Analyzing Features for the Detection of Happy Endings in German Novels
Information Retrieval
2016-11-29 v1 Artificial Intelligence
Computation and Language
Abstract
With regard to a computational representation of literary plot, this paper looks at the use of sentiment analysis for happy ending detection in German novels. Its focus lies on the investigation of previously proposed sentiment features in order to gain insight about the relevance of specific features on the one hand and the implications of their performance on the other hand. Therefore, we study various partitionings of novels, considering the highly variable concept of "ending". We also show that our approach, even though still rather simple, can potentially lead to substantial findings relevant to literary studies.
Cite
@article{arxiv.1611.09028,
title = {Analyzing Features for the Detection of Happy Endings in German Novels},
author = {Fotis Jannidis and Isabella Reger and Albin Zehe and Martin Becker and Lena Hettinger and Andreas Hotho},
journal= {arXiv preprint arXiv:1611.09028},
year = {2016}
}