Andrew Piper, Derek Ruths, Syed Ahmed, Faiyaz Al Zamal The Sociability of Detection.

Andrew Piper, Derek Ruths, Syed Ahmed, Faiyaz Al Zamal

The Sociability of Detection

The History of Character Theory

The History of Character Theory Vladimir Propp, The Morphology of the

Folktale

The History of Character Theory Vladimir Propp, The Morphology of the

Folktale James Phelan, Reading People, Reading

Plots: Character, Progression, and the Interpretation of Narrative (Chicago, 1989)

The History of Character Theory Vladimir Propp, The Morphology of the

Folktale James Phelan, Reading People, Reading

Plots: Character, Progression, and the Interpretation of Narrative (Chicago, 1989)

David A. Brewer, The Afterlife of Character, 1726-1825 (Penn, 2005)

The History of Character Theory Vladimir Propp, The Morphology of the

Folktale James Phelan, Reading People, Reading

Plots: Character, Progression, and the Interpretation of Narrative (Chicago, 1989)

David A. Brewer, The Afterlife of Character, 1726-1825 (Penn, 2005)

Deidre Shauna Lynch, The Economy of character: Novels, Market culture, and the Business of Inner Meaning (Chicago, 1998)

The History of Character Theory Vladimir Propp, The Morphology of the Folktale James Phelan, Reading People, Reading Plots:

Character, Progression, and the Interpretation of Narrative (Chicago, 1989)

David A. Brewer, The Afterlife of Character, 1726-1825 (Penn, 2005)

Deidre Shauna Lynch, The Economy of character: Novels, Market culture, and the Business of Inner Meaning (Chicago, 1998)

Lisa Zunshine, Why We Read Fiction: Theory of Mind and the Novel (Columbus: Ohio State UP, 2006)

The History of Character Theory Vladimir Propp, The Morphology of the Folktale James Phelan, Reading People, Reading Plots:

Character, Progression, and the Interpretation of Narrative (Chicago, 1989)

David A. Brewer, The Afterlife of Character, 1726-1825 (Penn, 2005)

Deidre Shauna Lynch, The Economy of character: Novels, Market culture, and the Business of Inner Meaning (Chicago, 1998)

Lisa Zunshine, Why We Read Fiction: Theory of Mind and the Novel (Columbus: Ohio State UP, 2006)

Blakey Vermeule, Why do we care about literary characters? (JHU, 2010)

SNA and Literary Theory

SNA and Literary Theory

Franco Moretti, “Network Theory, Plot Analysis,” New Left Review 68 (2011)

Franco Moretti, “Operationalizing,” New Left Review 84 (2013)

SNA and Literary Theory

Franco Moretti, “Network Theory, Plot Analysis,” New Left Review 68 (2011)

Franco Moretti, “Operationalizing,” New Left Review 84 (2013)

Padraig MacCarron & Ralph Kenna, “Universal properties of mythological networks,” EPL, 99 (2012) 28002

SNA and Literary Theory

Franco Moretti, “Network Theory, Plot Analysis,” New Left Review 68 (2011)

Franco Moretti, “Operationalizing,” New Left Review 84 (2013)

Padraig MacCarron & Ralph Kenna, “Universal properties of mythological networks,” EPL, 99 (2012) 28002

Apoorv Agarwal, Anup Kotalwar and Owen Rambow, “Automatic Extraction of Social Networks from Literary Text: A Case Study on Alice in Wonderland,” Proceedings of the 6th International Joint Conference on Natural Language Processing (IJCNLP 2013)

SNA and Literary Theory

Franco Moretti, “Network Theory, Plot Analysis,” New Left Review 68 (2011)

Franco Moretti, “Operationalizing,” New Left Review 84 (2013) Padraig MacCarron & Ralph Kenna, “Universal properties of

mythological networks,” EPL, 99 (2012) 28002 Apoorv Agarwal, Anup Kotalwar and Owen Rambow, “Automatic

Extraction of Social Networks from Literary Text: A Case Study on Alice in Wonderland,” Proceedings of the 6th International Joint Conference on Natural Language Processing (IJCNLP 2013)

D. K. Elson, N. Dames, and K. R. McKeown. Extracting social networks from literary fiction. In Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, pages 138–147. Association for Computational Linguistics, 2010.

AMT Interface

The performance of the AMT-based interaction mapping system when assessed on the annotated dataset.

The effect of changing the number of workers who code the same text block on the sensitivity and specificity with which interactions are identified in the text.

Terms

Nodes = Characters Edges = Relationships Edge Weights = Interactions

Detective Fiction has larger, sparser networks

Detective Fiction has larger, sparser networks

# Nodes DF 13.52 ± 7.76 SF 5.45 ± 2.91 P-value < 0.0001

Detective Fiction has larger, sparser networks

# Nodes DF 13.52 ± 7.76 SF 5.45 ± 2.91 P-value < 0.0001

# Edges DF 9.76 ± 4.03 SF 5.55 ± 2.50 P-value < 0.0001

Detective Fiction has larger, sparser networks

# Nodes DF 13.52 ± 7.76 SF 5.45 ± 2.91 p-value < 0.0001

# Edges DF 9.76 ± 4.03 SF 5.55 ± 2.50 p-value < 0.0001

Density DF 0.35 ± 0.14 SF 0.53 ± 0.25 p-value = 0.007

Short Fiction

Detective Fiction

Short Fiction

Detective Fiction has fewer indirectly connected neighborhoods

Detective Fiction has fewer indirectly connected neighborhoods

Clustering Coefficient DF 0.36 ± 0.23 SF 0.36 ± 0.36 P-value 0.965

Detective Fiction has fewer indirectly connected neighborhoods

Clustering Coefficient DF 0.36 ± 0.23 SF 0.36 ± 0.36 P-value 0.965

2-Clustering (Dispersion) DF 0.92 ± 0.06 SF 0.97 ± 0.04 P-value 0.003

Detective Fiction has fewer indirectly connected neighborhoods

Clustering Coefficient DF 0.36 ± 0.23 SF 0.36 ± 0.36 P-value 0.965

2-Clustering (Dispersion) DF 0.92 ± 0.06 SF 0.97 ± 0.04 P-value 0.003

2-Clustering along heaviest edge DF 0.83 ± 0.21 SF 0.96 ± 0.11 P value 0.017

Detectives don’t invest in strong relationships

Detectives don’t invest in strong relationships

Heaviest edge fraction DF 0.26 ± 0.13 0.40 ± 0.12 P-value 0.001

Detectives don’t invest in strong relationships

Heaviest edge fraction DF 0.26 ± 0.13 SF 0.40 ± 0.12 P-value 0.001

Degree-weighted heaviest edge DF 0.88 ± 0.11 0.98 ± 0.05 P-value 0.001

Detectives are not the center of the social universe

Detectives are not the center of the social universe

Normalized Closeness Vitality DF 3.14 ± 1.36 SF 4.28 ± 1.92 P-value 0.039

Detective Fiction takes longer to reveal the entire network

Detective Fiction takes longer to reveal the entire network

Time to completion – Nodes DF 72.74 ± 15.18 61.99 ± 22.99 P-value 0.091

Time to completion – Interactions DF 88.27 ± 11.43 SF 80.46 ± 18.33 P-value 0.117

Detective Fiction takes longer to reveal the entire network

Time to completion – Edges DF 87.15 ± 11.05 SF 73.77 ± 17.09 P-value 0.006

To Do

Naming

To Do

Naming Language and other genres

To Do

Naming Language

To Do

Naming Language Other Genres

To Do

Naming Language Other Genres Random Models

To Do

Naming Language Other Genres Random Models Citizen Science