Where Have I Heard This Story Before? Identifying Narrative Similarity in Movie Remakes

Abstract

People can identify correspondences between narratives in everyday life. For example, an analogy with the Cinderella story may be made in describing the unexpected success of an underdog in seemingly different stories. We present a new task and dataset for story understanding: identifying instances of similar narratives from a collection of narrative texts. We present an initial approach for this problem, which finds correspondences between narratives in terms of plot events, and resemblances between characters and their social relationships. Our approach yields an 8% absolute improvement in performance over an information-retrieval baseline on a novel dataset of plot summaries of 577 movie remakes from Wikipedia.

Extraction and Analysis of Fictional Character Networks

“…Evolution of the proportion of stable triads, used in[215]; b) Alignment between the characters of two different movies (Spoorloos and The Vanishing)[50].…”

Untitled

“…Most previous work within the NLP community applies distant reading (Jockers, 2013) to large collections of books, focusing on modeling different aspects of narratives such as plots and event sequences (Chambers and Jurafsky, 2009;McIntyre and Lapata, 2010;Goyal et al, 2010;Eisenberg and Finlayson, 2017), characters (Bamman et al, 2014;Iyyer et al, 2016;Chaturvedi et al, , 2017, and narrative similarity (Chaturvedi et al, 2018). In the same vein, researchers in computational literary analysis have combined statistical techniques and linguistics theories to perform quantitative analysis on large narrative texts (Michel et al, 2011;Franzosi, 2010;Underwood, 2016;Jockers and Kirilloff, 2016;Long and So, 2016), but these attempts largely rely on techniques such as word counting, topic modeling, and naive Bayes classifiers and are therefore not able to capture the meaning of sentences or paragraphs (Da, 2019).…”

“…Building computational models that can help form and test these interpretations is a fundamental goal of digital humanities research (Benzon and Hays, 1976). Within natural language processing, most previous work that engages with literature relies on "distant reading" (Jockers, 2013), which involves discovering high-level patterns from large collections of stories (Bamman et al, 2014;Chaturvedi et al, 2018). We depart from this trend by showing that computational techniques can also engage with literary criticism at a closer distance: concretely, we…”

Using Functional Schemas to Understand Social Media Narratives

“…Other work proposed to model inter-character relationships (Krishnan and Eisenstein, 2015;Chaturvedi et al, 2016Chaturvedi et al, , 2017a. Information about character types and their relationships has been demonstrated to be useful for story understanding tasks such as identifying incorrect narratives (e.g., reordered or reversed stories) (Elsner, 2012) and detecting narrative similarity (Chaturvedi et al, 2018). Finally, an interesting line of research has focused on constructing "plot units", which are story representations consisting of affect states of characters and tensions between them.…”

“…Recent advances in NLP have revived interest in this area, especially the task of story understanding (Mostafazadeh et al, 2016a). Most computational work has focused on extracting structured story representations (often called "schemas") from literary novels, folktales, movie plots or news articles (Chambers and Jurafsky, 2009;Finlayson, 2012;Chaturvedi et al, 2018). In our work, we shift the focus to understanding the structure of stories from a different data source: narratives found on social media.…”