Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Subversive Characters and Stereotyping Readers: Characterizing Queer Relationalities with Dialogue-Based Relation Extraction

Kent K. Chang, Anna Ho, David Bamman

Abstract

Television is often seen as a site for subcultural identification and subversive fantasy, including in queer cultures. How might we measure subversion, or the degree to which the depiction of social relationship between a dyad (e.g. two characters who are colleagues) deviates from its typical representation on TV? To explore this question, we introduce the task of stereotypic relationship extraction. Built on cognitive stylistics, linguistic anthropology, and dialogue relation extraction, in this paper, we attempt to model the cognitive process of stereotyping TV characters in dialogic interactions. Given a dyad, we want to predict: what social relationship do the speakers exhibit through their words? Subversion is then characterized by the discrepancy between the distribution of the model's predictions and the ground truth labels. To demonstrate the usefulness of this task and gesture at a methodological intervention, we enclose four case studies to characterize the representation of queer relationalities in the Big Bang Theory, Frasier, and Gilmore Girls, as we explore the suspicious and reparative modes of reading with our computational methods.

Subversive Characters and Stereotyping Readers: Characterizing Queer Relationalities with Dialogue-Based Relation Extraction

Abstract

Television is often seen as a site for subcultural identification and subversive fantasy, including in queer cultures. How might we measure subversion, or the degree to which the depiction of social relationship between a dyad (e.g. two characters who are colleagues) deviates from its typical representation on TV? To explore this question, we introduce the task of stereotypic relationship extraction. Built on cognitive stylistics, linguistic anthropology, and dialogue relation extraction, in this paper, we attempt to model the cognitive process of stereotyping TV characters in dialogic interactions. Given a dyad, we want to predict: what social relationship do the speakers exhibit through their words? Subversion is then characterized by the discrepancy between the distribution of the model's predictions and the ground truth labels. To demonstrate the usefulness of this task and gesture at a methodological intervention, we enclose four case studies to characterize the representation of queer relationalities in the Big Bang Theory, Frasier, and Gilmore Girls, as we explore the suspicious and reparative modes of reading with our computational methods.

Paper Structure

This paper contains 27 sections, 3 equations, 8 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Task and data
  3. Task: dialogue-based stereotypic relationship extraction
  4. Dataset: dialogues and dyads
  5. Dialogues from parsed teleplays.
  6. Relationship type labels.
  7. Dyads.
  8. Anonymization.
  9. Models and experiments
  10. Models
  11. Supervised.
  12. Prompting.
  13. Experimental results
  14. Analysis
  15. Queer characters and suspicious reading
  16. ...and 12 more sections

Figures (8)

  • Figure 1: Example of an anonymized and post-processed scene (only first two lines represented here).
  • Figure 2: A heatmap representing the progression of relationship types, "colleague_of" and "spouse_of", between Raj and Howard in The Big Bang Theory across the first eight seasons.
  • Figure 3: Another heatmap representing the progression of relationship types between Niles and Frasier in Frasier over eleven seasons. Only the top five relationship types are presented here.
  • Figure 4: Heatmap representing the mother--daughter relationship arc between Rory and Lorelai Gilmore (above) and between Lorelai and Emily Gilmore (below) in Gilmore Girls in the first six seasons.
  • Figure 5: Another heatmap representing the progression of relationship types between Sheldon Cooper and Penny over eight seasons in the Big Bang Theory. Only the top five relationship types are presented here.
  • ...and 3 more figures