Matthew L. Jockers

Digital archives: Don't let copyright block data mining

Matthew L. Jockers, Matthew Sag and Jason Schultz explain why humanities scholars have pitched in to the Authors Guild v. Google lawsuit.

A multiscale theory for the dynamical evolution of sentiment in novels

Recent work in literary sentiment analysis has suggested that shifts in emotional valence may serve as a reliable proxy for plot movement in novels. The raw sentiment time series of a novel can now be extracted using a variety of different methods, and after extraction, filtering is commonly used to smooth the irregular sentiment time series. Using an adaptive filter, which is among the most effective in determining trends of a signal, reducing noise, and performing fractal and multifractal analysis, we show that the energy of the smoothed sentiment signals decays with the smoothing parameter as a power-law, characterized by a Hurst parameter H of 1/2 <; H <; 1, which signifies long-range correlations. We further show that a smoothed sentiment arc corresponds to the sentiment of fast playing mode or sentiment retained in ones memory, and that for a novel to be both captivating and rich, H has to be larger than 1/2 but cannot be too close to 1.

From a distance ‘You might mistake her for a man’: A closer reading of gender and character action in Jane Eyre, The Law and the Lady, and A Brilliant Woman1

This research examines and contributes to recent work by Matthew Jockers and Gabi Kirilloff on the relationship between gender and action in the nineteenth-century novel. Jockers and Kirilloff use dependency parsing to extract verb and gendered pronoun pairs (“he said,” “she walked,” etc.). They then build a classification model to predict the gender of a pronoun based on the verb being performed. This present study examines the novels that were categorized as outliers by the classification model to gain a better understanding of the way the observed trends function at the level of individual narratives. We argue that while the classifier successfully categorized and identified novels in which characters behave digitalcommons.unl.edu Published in Digital Scholarship in the Humanities, Vol. 33, No. 4 (2018), pp 821–844. doi:10.1093/llc/fqy011 Copyright

Token Distribution Analysis

This chapter explains how to use the positions of words in a vector to create distribution plots showing where words occur across a narrative. Several important R functions are introduced including seq_along, rep, grep, rbind, apply, and do.call. if conditionals and for loops are also presented.

Do It KWIC (Better)

This chapter expands upon the previous chapter in order to build an interactive and reusable Key Word in Context (KWIC) application that allows for quick and intuitive KWIC list building. Readers are introduced to interactive R functions including readline and functions for data type conversion.

Accessing and Comparing Word Frequency Data

In this chapter, we derive and compare word frequency data. We learn about vector recycling, and the exercises invite you to compare the frequencies of several words in Melville’s Moby Dick to the same words in Jane Austen’s Sense and Sensibility.

Measures of Lexical Variety

In this chapter we’ll begin to transition from microanalysis to macroanalysis. We’ll leave behind the study of single terms and begin to explore two global measures of lexical variety: mean word frequency and type-token ratios.

First Foray into Text Analysis with R

In this chapter readers learn how to load, tokenize, and search a text. Several methods for exploring word frequencies and lexical makeup are introduced. The exercise at the end introduces the plot function.

Do It KWIC

In the last chapter a simple function was created within a call to the sapply function. In this chapter we explore user-defined functions more broadly and write a function for producing a keyword in context (KWIC) list.