scispace - formally typeset
Search or ask a question
Proceedings ArticleDOI

Extracting Social Networks from Literary Fiction

11 Jul 2010-pp 138-147
TL;DR: The method involves character name chunking, quoted speech attribution and conversation detection given the set of quotes, which provides evidence that the majority of novels in this time period do not fit two characterizations provided by literacy scholars.
Abstract: We present a method for extracting social networks from literature, namely, nineteenth-century British novels and serials. We derive the networks from dialogue interactions, and thus our method depends on the ability to determine when two characters are in conversation. Our approach involves character name chunking, quoted speech attribution and conversation detection given the set of quotes. We extract features from the social networks and examine their correlation with one another, as well as with metadata such as the novel's setting. Our results provide evidence that the majority of novels in this time period do not fit two characterizations provided by literacy scholars. Instead, our results suggest an alternative explanation for differences in social networks.

Content maybe subject to copyright    Report

Citations
More filters
Proceedings Article
23 Jun 2011
TL;DR: It is argued that fictional dialogs offer a way to study how authors create the conversations but don't receive the social benefits (rather, the imagined characters do), and significant coordination across many families of function words in the large movie-script corpus is found.
Abstract: Conversational participants tend to immediately and unconsciously adapt to each other's language styles: a speaker will even adjust the number of articles and other function words in their next utterance in response to the number in their partner's immediately preceding utterance. This striking level of coordination is thought to have arisen as a way to achieve social goals, such as gaining approval or emphasizing difference in status. But has the adaptation mechanism become so deeply embedded in the language-generation process as to become a reflex? We argue that fictional dialogs offer a way to study this question, since authors create the conversations but don't receive the social benefits (rather, the imagined characters do). Indeed, we find significant coordination across many families of function words in our large movie-script corpus. We also report suggestive preliminary findings on the effects of gender and other features; e.g., surprisingly, for articles, on average, characters adapt more to females than to males.

373 citations


Cites background from "Extracting Social Networks from Lit..."

  • ...For example, one recent project identifies conversational networks in novels, with the goal of evaluating various literary theories (Elson et al., 2010; Elson and McKeown, 2010)....

    [...]

Proceedings ArticleDOI
01 Jan 2014
TL;DR: A model that employs multiple effects to account for the influence of extra-linguistic information (such as author) is introduced and it is found that this method leads to improved agreement with the preregistered judgments of a literary scholar, complementing the results of alternative models.
Abstract: We consider the problem of automatically inferring latent character types in a collection of 15,099 English novels published between 1700 and 1899. Unlike prior work in which character types are assumed responsible for probabilistically generating all text associated with a character, we introduce a model that employs multiple effects to account for the influence of extra-linguistic information (such as author). In an empirical evaluation, we find that this method leads to improved agreement with the preregistered judgments of a literary scholar, complementing the results of alternative models.

188 citations


Cites background from "Extracting Social Networks from Lit..."

  • ...To resolve the former to the latter, we largely follow Davis et al. (2003) and Elson et al. (2010): we define a set of initial characters corresponding to each unique character name that is not a subset of another (e.g., Mr. Tom Sawyer) and deterministically create a set of allowable variants for…...

    [...]

Proceedings ArticleDOI
01 Jun 2016
TL;DR: A novel unsupervised neural network is presented that incorporates dictionary learning to generate interpretable, accurate relationship trajectories and jointly learns a set of global relationship descriptors as well as a trajectory over these descriptors for each relationship in a dataset of raw text from novels.
Abstract: Understanding how a fictional relationship between two characters changes over time (e.g., from best friends to sworn enemies) is a key challenge in digital humanities scholarship. We present a novel unsupervised neural network for this task that incorporates dictionary learning to generate interpretable, accurate relationship trajectories. While previous work on characterizing literary relationships relies on plot summaries annotated with predefined labels, our model jointly learns a set of global relationship descriptors as well as a trajectory over these descriptors for each relationship in a dataset of raw text from novels. We find that our model learns descriptors of events (e.g., marriage or murder) as well as interpersonal states (love, sadness). Our model outperforms topic model baselines on two crowdsourced tasks, and we also find interesting correlations to annotations in an existing dataset.

159 citations

Proceedings ArticleDOI
01 Sep 2017
TL;DR: This paper presents a story comprehension model that explores three distinct semantic aspects: the sequence of events described in the story, its emotional trajectory, and its plot consistency, and uses a hidden variable to weigh the semantic aspects in the context of the story.
Abstract: Automatic story comprehension is a fundamental challenge in Natural Language Understanding, and can enable computers to learn about social norms, human behavior and commonsense. In this paper, we present a story comprehension model that explores three distinct semantic aspects: (i) the sequence of events described in the story, (ii) its emotional trajectory, and (iii) its plot consistency. We judge the model’s understanding of real-world stories by inquiring if, like humans, it can develop an expectation of what will happen next in a given story. Specifically, we use it to predict the correct ending of a given short story from possible alternatives. The model uses a hidden variable to weigh the semantic aspects in the context of the story. Our experiments demonstrate the potential of our approach to characterize these semantic aspects, and the strength of the hidden variable based approach. The model outperforms the state-of-the-art approaches and achieves best results on a publicly available dataset.

94 citations


Cites background from "Extracting Social Networks from Lit..."

  • ...…Proppian (Propp, 1968) roles (Valls-Vargas et al., 2014, 2015), inter-character relationships (Iyyer et al., 2016; Chaturvedi et al., 2016, 2017), and social networks of characters (Elson et al., 2010; Elson, 2012; Agarwal et al., 2013, 2014; Krishnan and Eisenstein, 2015; Srivastava et al., 2016)....

    [...]

Proceedings Article
01 Jun 2012
TL;DR: This paper annotates Lewis Carroll's Alice in Wonderland using a well-defined annotation scheme which has been used in previous computational models that extract social events from news articles and builds novel types of networks in which links between characters are different types of social events.
Abstract: We present a network analysis of a literary text, Alice in Wonderland. We build novel types of networks in which links between characters are different types of social events. We show that analyzing networks based on these social events gives us insight into the roles of characters in the story. Also, static network analysis has limitations which be- come apparent from our analysis. We propose the use of dynamic network analysis to over- come these limitations. tify these limitations, few have done so with a strict and specific rubric for categorizing interactions. In this paper, we annotate Lewis Carroll's Alice in Wonderland using a well-defined annotation scheme which we have previously developed on newswire text Agarwal et al. (2010). It is well suited to deal with the aforementioned limitations. We show that using different types of networks can be useful by al- lowing us to provide a model for determining point- of-view. We also show that social networks allow characters to be categorized into roles based on how they function in the text, but that this approach is limited when using static social networks. We then build and visualize dynamic networks and show that static networks can distort the importance of char- acters. By using dynamic networks, we can build a fuller picture of how each character works in a liter- ary text. Our paper uses an annotation scheme that is well- defined and has been used in previous computational models that extract social events from news articles (Agarwal and Rambow, 2010). This computational model may be adapted to extract these events from literary texts. However, the focus of this paper is not to adapt the previously proposed computational model to a new domain or genre, but to first demon- strate the usefulness of this annotation scheme for the analysis of literary texts, and the social networks derived from it. All results reported in this paper are based on hand annotation of the text. Further- more, we are investigating a single text, so that we do cannot draw conclusions about the usefulness of our methods for validating theories of literature. We summarize the contributions of this paper: • We manually extract a social network from Al-

87 citations


Cites background or methods or result from "Extracting Social Networks from Lit..."

  • ...Our work specifically addresses these missed cases, and in that sense our technique for creating social networks is complementary to that of Elson et al. (2010)....

    [...]

  • ...In Network Theory Plot Analysis, Moretti (2011) takes a similar path as Elson et al. (2010), where the act of speech signifies interaction....

    [...]

  • ...Recently, Elson et al. (2010) extracted networks from a corpus of 19th century texts in order to debunk long standing hypotheses from comparative literature (Elson et al., 2010)....

    [...]

  • ...Recently, Elson et al. (2010) extracted networks from a corpus of 19th century texts in order to debunk long standing hypotheses from comparative literature (Elson et al....

    [...]

  • ...In Network Theory Plot Analysis, Moretti (2011) takes a similar path as Elson et al. (2010), where the act of speech signifies interaction. Moretti (2011) points...

    [...]

References
More filters
Journal ArticleDOI
Jacob Cohen1
TL;DR: In this article, the authors present a procedure for having two or more judges independently categorize a sample of units and determine the degree, significance, and significance of the units. But they do not discuss the extent to which these judgments are reproducible, i.e., reliable.
Abstract: CONSIDER Table 1. It represents in its formal characteristics a situation which arises in the clinical-social-personality areas of psychology, where it frequently occurs that the only useful level of measurement obtainable is nominal scaling (Stevens, 1951, pp. 2526), i.e. placement in a set of k unordered categories. Because the categorizing of the units is a consequence of some complex judgment process performed by a &dquo;two-legged meter&dquo; (Stevens, 1958), it becomes important to determine the extent to which these judgments are reproducible, i.e., reliable. The procedure which suggests itself is that of having two (or more) judges independently categorize a sample of units and determine the degree, significance, and

34,965 citations

Proceedings ArticleDOI
25 Jun 2005
TL;DR: By using simulated annealing in place of Viterbi decoding in sequence models such as HMMs, CMMs, and CRFs, it is possible to incorporate non-local structure while preserving tractable inference.
Abstract: Most current statistical natural language processing models use only local features so as to permit dynamic programming in inference, but this makes them unable to fully account for the long distance structure that is prevalent in language use. We show how to solve this dilemma with Gibbs sampling, a simple Monte Carlo method used to perform approximate inference in factored probabilistic models. By using simulated annealing in place of Viterbi decoding in sequence models such as HMMs, CMMs, and CRFs, it is possible to incorporate non-local structure while preserving tractable inference. We use this technique to augment an existing CRF-based information extraction system with long-distance dependency models, enforcing label consistency and extraction template consistency constraints. This technique results in an error reduction of up to 9% over state-of-the-art systems on two established information extraction tasks.

3,209 citations


"Extracting Social Networks from Lit..." refers methods in this paper

  • ...with the Stanford NER tagger (Finkel et al., 2005) and extracted noun phrases that were categorized as persons or organizations....

    [...]

  • ...We processed each novel with the Stanford NER tagger (Finkel et al., 2005) and extracted noun phrases that were categorized as persons or organizations....

    [...]

Book
01 Jan 1973
TL;DR: As a brilliant survey of English literature in terms of changing attitudes towards country and city, Williams' highly-acclaimed study reveals the shifting images and associations between these two traditional poles of life throughout the major developmental periods of English culture.
Abstract: As a brilliant survey of English literature in terms of changing attitudes towards country and city, Williams' highly-acclaimed study reveals the shifting images and associations between these two traditional poles of life throughout the major developmental periods of English culture.

3,113 citations


"Extracting Social Networks from Lit..." refers methods in this paper

  • ...Raymond Williams used the term “knowable communities” to describe this world, in which face-to-face relations of a restricted set of characters are the primary mode of social interaction (Williams, 1975, 166)....

    [...]

Proceedings Article
01 May 2004
TL;DR: The objective of the ACE program is to develop technology to automatically infer from human language data the entities being mentioned, the relations among these entities that are directly expressed, and the events in which these entities participate.
Abstract: The objective of the ACE program is to develop technology to automatically infer from human language data the entities being mentioned, the relations among these entities that are directly expressed, and the events in which these entities participate. Data sources include audio and image data in addition to pure text, and Arabic and Chinese in addition to English. The effort involves defining the research tasks in detail, collecting and annotating data needed for training, development, and evaluation, and supporting the research with evaluation tools and research workshops. This program began with a pilot study in 1999. The next evaluation is scheduled for September 2004. Introduction and Background Today’s global web of electronic information, including most notably the www, provides a resource of unbounded information-bearing potential. But to fully exploit this potential requires the ability to extract content from human language automatically. That is the objective of the ACE program – to develop the capability to extract meaning from multimedia sources. These sources include text, audio and image data. The ACE program is a “technocentric” research effort, meaning that the emphasis is on developing core enabling technologies rather than solving the application needs that motivate the research. The program began in 1999 with a study intended to identify those key content extraction tasks to serve as the research targets for the remainder of the program. These tasks were identified in general as the extraction of the entities, relations and events being discussed in the language. In general objective, the ACE program is motivated by and addresses the same issues as the MUC program that preceded it (NIST 1999). The ACE program, however, attempts to take the task “off the page” in the sense that the research objectives are defined in terms of the target objects (i.e., the entities, the relations, and the events) rather than in terms of the words in the text. For example, the so-called “named entity” task, as defined in MUC, is to identify those words (on the page) that are names of entities. In ACE, on the other hand, the corresponding task is to identify the entity so named. This is a different task, one that is more abstract and that involves inference more explicitly in producing an answer. In a real sense, the task is to detect things that “aren’t there”. Reference resolution thus becomes an integral and critical part of solving the problem. During the period 2000-2001, the ACE effort was devoted solely to entity detection and tracking. During the period 2002-2003, relations were explored and added. 1 While the ACE program is directed toward extraction of information from audio and image sources in addition to pure text, the research effort is restricted to information extraction from text. The actual transduction of audio and image data into text is not part of the ACE research effort, although the processing of ASR and OCR output from such transducers is. Now, starting in 2004, events are being explored and added as the third of the three original tasks.

1,073 citations


"Extracting Social Networks from Lit..." refers background in this paper

  • ...While researchers have not attempted the automatic construction of social networks representing connections between characters in a corpus of novels, the ACE program has involved entity and relation extraction in unstructured text (Doddington et al., 2004)....

    [...]

Book
21 Jul 2005
TL;DR: MoreMoretti as discussed by the authors argues that literature scholars should stop reading books and start counting, graphing, and mapping them instead, and offers charts, maps and time lines, developing the idea of "distant reading" into a full-blown experiment in literary history.
Abstract: "In this groundbreaking book, Franco Moretti argues that literature scholars should stop reading books and start counting, graphing, and mapping them instead. In place of the traditionally selective literary canon of a few hundred texts, Moretti offers charts, maps and time lines, developing the idea of “distant reading” into a full-blown experiment in literary historiography, in which the canon disappears into the larger literary system." -- Publisher's website.

717 citations