Measuring the Structural and Conceptual Similarity of Folktales using Plot Graphs

Abstract

This paper presents an approach to organizing folktales based on a data structure called a plot graph, which captures the narrative flow of events in a folktale. The similarity between two folktales can be computed as the structural similarity between their corresponding plot graphs. This is performed using the well-known Needleman-Wunsch algorithm. To test the efficacy of this approach, experiments are carried out using a small collection of 24 folktales grouped into 5 categories based on the Aarne-Thompson index. The best result is obtained by combining the proposed structural-based similarity measure with a more conventional bag of words vector space model, where 19 out of the 24 folktales (79.16%) yield higher average similarity with folktales within their respective categories as opposed to across categories. c 2015 Association for Computational Linguistics and The Asian Federation of Natural Language Processing.