R Package to Research the Riddle of Literary Quality

Description

The package contains the data of a reader survey about fiction in Dutch, a description of the novels the readers rated, and the results of stylistic measurements of the novels. The package also contains functions to combine, analyze, and visualize these data.

We will be grateful if you cite the package in your publications. To get the updated citation information please type: citation("litRiddle").

Details

The package litRiddle presents data generated in the project The Riddle of Literary Quality (2012–2019) in which a team of digital humanists aimed to find out if books that readers considered to be highly literary have a different set of values for stylistic features than books the same readers did not consider to be very literary.

The package contains five data sets:

1. The reviews gathered from a hired representative panel of citizens of the Netherlands and in a large online survey called The National Reader Survey (2013). Type help(reviews) for details.

2. The motivations that reviewers give for a subset or all of their ratings are provided as plain text and as POS tagged data. Type help(motivations) for details.

3. Data about the reviewers: age, gender, zipcode, average number of books read per year etc. Type help(respondents) for details.

4. A list of the 401 books that the survey respondents evaluated with metadata such as author, title, publisher, gender of the author, and for translations the original language, etc., as well as a number of stylometric measurements such as the average sentence lengh etc. Type help(books) for details.

5. For each of the 401 books, the relative frequencies of 5000 most frequent words are provided (due to copyright issues the books themselves cannot be made available). Type help(frequencies) for details.

To learn more about the functions provided to analyze the above datasets, type the function explain() in your terminal.

Author(s)

Maciej Eder, Joris van Zundert, Karina van Dalen-Oskam, Saskia Lensink

References

Information in Dutch about the package can be found at https://karinavdo.github.io/RaadselLiteratuur/02_07_data_en_R_package.html

Information in English at https://github.com/karinavdo/LitRiddleData/blob/master/README.md

Karina van Dalen-Oskam (2023). The Riddle of Literary Quality: A Computational Approach. Amsterdam University Press.

Karina van Dalen-Oskam (2021). Het raadsel literatuur. Is literaire kwaliteit meetbaar? Amsterdam University Press.

Maciej Eder, Saskia Lensink, Joris van Zundert, Karina van Dalen-Oskam (2022). Replicating The Riddle of Literary Quality: The litRiddle package for R, in: Digital Humanities 2022 Conference Abstracts. The University of Tokyo, Japan, 25–29 July 2022, p. 636-637 https://dh2022.dhii.asia/dh2022bookofabsts.pdf

Karina van Dalen-Oskam (2015). The Riddle of Literary Quality. Op zoek naar conventies van literariteit. "Vooys: tijdschrift voor letteren" 32(3): 25-33, https://literaryquality.huygens.knaw.nl/?p=537#more-537

Corina Koolen, Karina van Dalen-Oskam, Andreas van Cranenburgh, Erica Nagelhout (2020). Literary quality in the eye of the Dutch reader: The National Reader Survey. "Poetics" 79: 101439, doi: 10.1016/j.poetic.2020.101439

More publications from the project: see https://literaryquality.huygens.knaw.nl/?page_id=588

See Also

books, reviews, respondents, explain, make.table

Measurements of 401 novels

Description

Measurements (including word count, number of sentences, number of paragraphs, average sentence length, etc.) of 401 novels in Dutch.

Usage

data(books)

Details

This is a dataframe containing numerical, ordinal and lexical data (as well as metadata) for 401 novels. To see which variables are provided, type get.columns(). To learn more about what the column names really mean, type explain("books").

Author(s)

Karina van Dalen-Oskam, Joris van Zundert

Source

The dataset is a part of The Riddle of Literary Quality Project.

See Also

get.columns, explain, reviews, respondents, frequencies, motivations

Examples

data(books)

print(books)
summary(books)

Combine All Information of the Survey

Description

Function to combine all information of the survey, reviews, and books into one big dataframe. The user can specify whether or not they want to also load the freqTable with the frequency counts of the word n-grams of the books.

Usage

combine.all(load.freq.table = FALSE)

Arguments

Details

In order to identify (possible) correlations between particular reviews (e.g. the scores by the reviewers) with metadata about the reviewers themselves, it is usually required, or at least convenient, to combine two or more datasets into one large table.

Value

A data frame combining the two (optionally three) datasets: books, respondents, and reviews.

Author(s)

Saskia Lensink, Maciej Eder

References

https://literaryquality.huygens.knaw.nl/

See Also

reviews, respondents, motivations, books

Examples

# combine and load all data from the books, respondents and reviews into 
# a new dataframe (tibble format)
combine.all(load.freq.table = FALSE)

# combine and load all data from the books, respondents and reviews into 
# a new dataframe (tibble format), and additionally also load the frequency
# table of all word 1grams of the corpus used. 
combine.all(load.freq.table = TRUE)

Explain Variables

Description

Function that lists a short explanation of what the different column names refer to and what their levels consist of.

Usage

explain(dataset = "")

Arguments

Details

In the current version, the option dataset = TRUE is not fully implemented.

Value

A character vector being a description of the dataset.

Author(s)

Saskia Lensink, Maciej Eder

References

https://literaryquality.huygens.knaw.nl/

See Also

reviews, respondents, motivations, books

Examples

explain("books")
explain("reviews")
explain("respondents")

Find Dataset, Given a Column Name

Description

Return the name of the dataset where a column can be found.

Usage

find.dataset(name = NULL)

Arguments

Details

The function returns the name of the data table containing a given column name.

Value

A character vector containing names of relevant datasets.

Author(s)

Saskia Lensink, Maciej Eder

References

https://literaryquality.huygens.knaw.nl/

See Also

reviews, respondents, motivations, books

Examples

find.dataset("book.id")
find.dataset("age.resp")

Word frequencies (5000 most frequent words) of 401 novels.

Description

Word frequencies (5000 most frequent words) of 401 novels in Dutch.

Usage

data(frequencies)

Details

This is a dataframe containing numerical values for word frequencies of the 5000 most frequent words (in a descending order of frequency) of 401 literary novels in Dutch. The table contains relative frequencies, meaning that the original word occurencies from a book were divided by the total number of words of the book in question. The measurments were obtained using the R package stylo, and were later rounded to the 5th digit. To learn more about the novels themselves, type help(books).

Author(s)

Karina van Dalen-Oskam, Maciej Eder

Source

The dataset is a part of The Riddle of Literary Quality Project.

See Also

get.columns, explain, books, reviews, respondents, motivations

Examples

data(frequencies)

print(frequencies)
summary(frequencies)

Print Column Names

Description

The function creates a list of all the column names from all three datasets, i.d. reviews, respondents, books.

Usage

get.columns()

Details

This simple function works best when combined with explain, which provides a detailed description of particular variables. Type help(explain) for more details.

Value

A list with three elements: books, respondents, and reviews, each containing the names of supported variables.

Author(s)

Saskia Lensink, Maciej Eder

References

https://literaryquality.huygens.knaw.nl/

See Also

reviews, respondents, books, motivations, explain

Make Table and Plot

Description

A function to make a table of frequency counts for one variable, and to plot a histogram of the results.

Usage

make.table(table.of = NULL, 
    plot = TRUE, 
    xlab = table.of, 
    ylab = "count", 
    title = table.of,
    barcolor = "grey", 
    barfill = "darkgrey")

Arguments

Details

A basic way to show the distribution of an indicated variable from the litRiddle package. It provides the values, but also a simple histrogram.

Value

A character vector containing one chosen variable, optionally followed by a plot.

Author(s)

Saskia Lensink, Maciej Eder

References

https://literaryquality.huygens.knaw.nl/

See Also

make.table2, get.columns

Examples

make.table(table.of = "age.resp")

make.table(table.of = "age.resp", xlab = "age respondent", 
  ylab = "number of people", title = "Distribution of respondent age",
  barcolor = "red", barfill = "white")

Make Table of Two Variables and Plot

Description

A function to make a table of frequency counts for two variables, and to plot a histogram of the results.

Usage

make.table2(table.of = NULL, 
    split = NULL, 
    plot = TRUE, 
    xlab = table.of, 
    ylab = "counts", 
    title = table.of,
    barcolor = "grey", 
    barfill = "darkgrey")

Arguments

Details

Unlike make.table, this function provides a comparison of two variables at a time, or to be more precise: a distribution of an indicated variable when subdivided into two or more groups. The function provides the values themselves, but also a final histrogram.

Value

A character vector containing one chosen variable, optionally followed by a plot.

Author(s)

Saskia Lensink, Maciej Eder

References

https://literaryquality.huygens.knaw.nl/

See Also

make.table, get.columns

Examples

make.table2(table.of = "age.resp", split = "gender.resp")
make.table2(table.of = "literariness.read", split = "gender.author")



# Note that you can only provide an argument to the 'split' variable 
# that has less than 31 unique values, to avoid uninterpretable outputs:
make.table2(table.of = "age.resp", split = "zipcode") 

# You can also adjust the x label, y label, title, and colors.
make.table2(table.of = "age.resp", split = "gender.resp", 
  xlab = "age respondent", ylab = "number of people", 
  barcolor = "purple", barfill = "yellow")
make.table2(table.of = "literariness.read", split = "gender.author", 
  xlab = "Overall literariness scores", ylab = "number of people", 
  barcolor = "black", barfill = "darkred")

Reviewers' motivations for their scores (if given)

Description

Reviewers' motivations for their scores (if provided by the respondents) from the survey called The National Reader Survey (2013).

Usage

data(motivations)

Details

This is a dataframe containing that lists all tokens from all motivations together with lemma and POS tag information. To see which variables are provided, type get.columns(). To learn more about what the column names really mean, type explain("motivations").

Author(s)

Karina van Dalen-Oskam, Joris van Zundert

Source

The dataset is a part of The Riddle of Literary Quality Project.

See Also

get.columns, explain, books, frequencies, respondents, reviews

Examples

data(motivations)

head(motivations, n = 30)
summary(motivations)

Motivations Sentences

Description

Convenience function that produces a 'view' of the token table motivations with one (plain text) sentence of each motivation per row, listening motivation.id, book.id, respondent.id, sentence.id, and sentence.

Usage

motivations.sentences()

Arguments

None

Value

A data table containing all sentences of all given motivations and IDs related to respondents and books.

Author(s)

Joris van Zundert, Saskia Lensink, Maciej Eder

References

https://literaryquality.huygens.knaw.nl/

See Also

motivations.text, reviews, respondents, books

Examples

# to create a data frame with one sentence per motivation per row for all motivations:
mots <-  motivations.sentences()
head( mots, n=10 )

Motivations Text

Description

Convenience function that produces a 'view' of the token table motivations with the full text of a motivation for each motivation, listening motivation.id, book.id, respondent.id, and text.

Usage

motivations.text()

Arguments

None

Value

A data table containing motivations and IDs related to respondents and books.

Author(s)

Joris van Zundert, Saskia Lensink, Maciej Eder

References

https://literaryquality.huygens.knaw.nl/

See Also

motivations.sentences, reviews, respondents, books

Examples

# to create a data frame with the full (plain) text of all motivations:
mots <-  motivations.text()
head( mots, n=10 )

Order Responses

Description

Function that transforms the survey responses into ordered factors. Levels quality.read and quality.notread: "very bad", "bad", "a bit bad", "neutral", "a bit good", "good", "very good", "NA". Levels literariness.read and literariness.notread: "absolutely not literary", "non-literary", "not very literary", "between literary and non-literary","a bit literary", "literary", "very literary", "NA". Levels statements 4/12: "completely disagree", "disagree", "neutral", "agree", "completely agree", "NA".

Usage

order.responses(bookratings.or.readingbehavior = NULL)

Arguments

Value

A data table containing relevant variables.

Author(s)

Saskia Lensink, Maciej Eder

References

https://literaryquality.huygens.knaw.nl/

See Also

reviews, respondents, motivations, books

Examples

# to create a data frame with ordered factor levels of the questions 
# on reading behavior:
dat.reviews = order.responses("readingbehavior")
str(dat.reviews)

# to create a data frame with ordered factor levels of the book ratings:
dat.ratings = order.responses("bookratings")
str(dat.ratings)

Respondents' Answers

Description

The information about the reviewers that participated in the survey called The National Reader Survey (2013).

Usage

data(respondents)

Details

This is a dataframe containing numerical, ordinal and textual data about the 13541 reviewers that scored 401 novels. To see which variables are provided, type get.columns(). To learn more about what the column names really mean, type explain("respondents").

Author(s)

Karina van Dalen-Oskam, Joris van Zundert

Source

The dataset is a part of The Riddle of Literary Quality Project.

See Also

get.columns, explain, books, reviews, frequencies, motivations

Examples

data(respondents)

print(respondents)
summary(respondents)

Reviewers' scores

Description

Reviewers' scores from the survey called The National Reader Survey (2013).

Usage

data(reviews)

Details

This is a dataframe containing numerical, ordinal and textual data for thousands of individual reviews (and the reviewers' scores) for 401 novels. To see which variables are provided, type get.columns(). To learn more about what the column names really mean, type explain("reviews").

Author(s)

Karina van Dalen-Oskam, Joris van Zundert

Source

The dataset is a part of The Riddle of Literary Quality Project.

See Also

get.columns, explain, books, frequencies, respondents, motivations

Examples

data(reviews)

print(reviews)
summary(reviews)