Frowning Frodo, Wincing Leia, and a Seriously Great Friendship: Learning to Classify Emotional Relationships of Fictional Characters
E. Kim, and R. Klinger. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), page 647--653. Minneapolis, Minnesota, Association for Computational Linguistics, (June 2019)
DOI: 10.18653/v1/N19-1067
Abstract
The development of a fictional plot is centered around characters who closely interact with each other forming dynamic social networks. In literature analysis, such networks have mostly been analyzed without particular relation types or focusing on roles which the characters take with respect to each other. We argue that an important aspect for the analysis of stories and their development is the emotion between characters. In this paper, we combine these aspects into a unified framework to classify emotional relationships of fictional characters. We formalize it as a new task and describe the annotation of a corpus, based on fan-fiction short stories. The extraction pipeline which we propose consists of character identification (which we treat as given by an oracle here) and the relation classification. For the latter, we provide results using several approaches previously proposed for relation identification with neural methods. The best result of 0.45 F1 is achieved with a GRU with character position indicators on the task of predicting undirected emotion relations in the associated social network graph.
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
%0 Conference Paper
%1 kim-klinger-2019-frowning
%A Kim, Evgeny
%A Klinger, Roman
%B Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
%C Minneapolis, Minnesota
%D 2019
%I Association for Computational Linguistics
%K character-relations dfg-antrag-steckbriefe emotion imported neuralnet sentiment sentimentanalysis
%P 647--653
%R 10.18653/v1/N19-1067
%T Frowning Frodo, Wincing Leia, and a Seriously Great Friendship: Learning to Classify Emotional Relationships of Fictional Characters
%U https://www.aclweb.org/anthology/N19-1067
%X The development of a fictional plot is centered around characters who closely interact with each other forming dynamic social networks. In literature analysis, such networks have mostly been analyzed without particular relation types or focusing on roles which the characters take with respect to each other. We argue that an important aspect for the analysis of stories and their development is the emotion between characters. In this paper, we combine these aspects into a unified framework to classify emotional relationships of fictional characters. We formalize it as a new task and describe the annotation of a corpus, based on fan-fiction short stories. The extraction pipeline which we propose consists of character identification (which we treat as given by an oracle here) and the relation classification. For the latter, we provide results using several approaches previously proposed for relation identification with neural methods. The best result of 0.45 F1 is achieved with a GRU with character position indicators on the task of predicting undirected emotion relations in the associated social network graph.
@inproceedings{kim-klinger-2019-frowning,
abstract = {The development of a fictional plot is centered around characters who closely interact with each other forming dynamic social networks. In literature analysis, such networks have mostly been analyzed without particular relation types or focusing on roles which the characters take with respect to each other. We argue that an important aspect for the analysis of stories and their development is the emotion between characters. In this paper, we combine these aspects into a unified framework to classify emotional relationships of fictional characters. We formalize it as a new task and describe the annotation of a corpus, based on fan-fiction short stories. The extraction pipeline which we propose consists of character identification (which we treat as given by an oracle here) and the relation classification. For the latter, we provide results using several approaches previously proposed for relation identification with neural methods. The best result of 0.45 F1 is achieved with a GRU with character position indicators on the task of predicting undirected emotion relations in the associated social network graph.},
added-at = {2020-10-23T09:24:05.000+0200},
address = {Minneapolis, Minnesota},
author = {Kim, Evgeny and Klinger, Roman},
biburl = {https://www.bibsonomy.org/bibtex/2b6035b91b9f1f22cda95c2f1ea814f88/albinzehe},
booktitle = {Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)},
doi = {10.18653/v1/N19-1067},
interhash = {e65d72af4aa7a7b9bb374d8667d5b037},
intrahash = {b6035b91b9f1f22cda95c2f1ea814f88},
keywords = {character-relations dfg-antrag-steckbriefe emotion imported neuralnet sentiment sentimentanalysis},
month = jun,
pages = {647--653},
publisher = {Association for Computational Linguistics},
timestamp = {2020-10-23T09:32:58.000+0200},
title = {Frowning {F}rodo, Wincing {L}eia, and a Seriously Great Friendship: Learning to Classify Emotional Relationships of Fictional Characters},
url = {https://www.aclweb.org/anthology/N19-1067},
year = 2019
}