titles

A dataset containing a simple random sample of article titles 
from WebOfScience records 
of articles of "biographical-items" or "items-about-individual" types
from all fields of study
published from 1945 to 2014.
The sample was drawn in December 2014.

datasets

Utilizes the 'genderize.io' Application Programming Interface
to predict gender from first names extracted from a text vector.
The accuracy of prediction could be controlled by two parameters:
counts of a first name in the database and probability of prediction.

Kamil Wais

genderizeR

Gender Prediction Based on First Names

Nathan VanHoudnos

John Ramey

titles function

A data frame with 2641 rows and 2 variables:<dl class="dl-horizontal">
 <dt>title</dt><dd>title of an article</dd>
 <dt>genderCoded</dt><dd>manually coded gender of an author. There are four codes: "female", "male", "noname, "unknown". "Noname" is the code for a case were human coders were not be able to find a proper first name of an author. "Unknown" if the code for a case were the coders found a full name of an author but were not be able to verify if she or he is a man or a female.</dd>
</dl>

Format

Titles sample — titles

A data frame with 2641 rows and 2 variables:<dl class='dl-horizontal'>
 <dt>title</dt><dd>title of an article</dd>
 <dt>genderCoded</dt><dd>manually coded gender of an author. There are four codes: "female", "male", "noname, "unknown". "Noname" is the code for a case were human coders were not be able to find a proper first name of an author. "Unknown" if the code for a case were the coders found a full name of an author but were not be able to verify if she or he is a man or a female.</dd>
</dl>

titles: Titles sample

Description

Usage

Arguments

Format