License: Creative Commons Attribution 3.0 Unported license (CC BY 3.0)
When quoting this document, please refer to the following
DOI: 10.4230/OASIcs.CMN.2013.166
URN: urn:nbn:de:0030-drops-41508
URL: http://dagstuhl.sunsite.rwth-aachen.de/volltexte/2013/4150/
Go to the corresponding OASIcs Volume Portal

Ofek, Nir ; Darányi, Sándor ; Rokach, Lior

Linking Motif Sequences with Tale Types by Machine Learning

pdf-format:
p166-ofek.pdf (0.6 MB)

Abstract

Abstract units of narrative content called motifs constitute sequences, also known as tale types. However whereas the dependency of tale types on the constituent motifs is clear, the strength of their bond has not been measured this far. Based on the observation that differences between such motif sequences are reminiscent of nucleotide and chromosome mutations in genetics, i.e., constitute "narrative DNA", we used sequence mining methods from bioinformatics to learn more about the nature of tale types as a corpus. 94% of the Aarne-Thompson-Uther catalogue (2249 tale types in 7050 variants) was listed as individual motif strings based on the Thompson Motif Index, and scanned for similar subsequences. Next, using machine learning algorithms, we built and evaluated a classifier which predicts the tale type of a new motif sequence. Our findings indicate that, due to the size of the available samples, the classification model was best able to predict magic tales, novelles and jokes.

BibTeX - Entry

@InProceedings{ofek_et_al:OASIcs:2013:4150,
  author =	{Nir Ofek and S{\'a}ndor Dar{\'a}nyi and Lior Rokach},
  title =	{{Linking Motif Sequences with Tale Types by Machine Learning}},
  booktitle =	{2013 Workshop on Computational Models of Narrative},
  pages =	{166--182},
  series =	{OpenAccess Series in Informatics (OASIcs)},
  ISBN =	{978-3-939897-57-6},
  ISSN =	{2190-6807},
  year =	{2013},
  volume =	{32},
  editor =	{Mark A. Finlayson and Bernhard Fisseni and Benedikt L{\"o}we and Jan Christoph Meister},
  publisher =	{Schloss Dagstuhl--Leibniz-Zentrum fuer Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{http://drops.dagstuhl.de/opus/volltexte/2013/4150},
  URN =		{urn:nbn:de:0030-drops-41508},
  doi =		{10.4230/OASIcs.CMN.2013.166},
  annote =	{Keywords: Narrative DNA, tale types, motifs, type-motif correlation, machine learning}
}

Keywords: Narrative DNA, tale types, motifs, type-motif correlation, machine learning
Collection: 2013 Workshop on Computational Models of Narrative
Issue Date: 2013
Date of publication: 02.08.2013

DROPS-Home | Fulltext Search | Imprint | Privacy Published by LZI