feature_longwords: Long word features

In sebastian-fox/twitterfeatures: Simple Feature Engineering Functions for Twitter Data

Description

Engineers features related to long words in Tweets.

Usage

feature_longwords(data, doc_id_field, text_field, top_num = 10,
  remove_urls = TRUE)

Arguments

data	a dataframe or tibble containing the text data and document id
doc_id_field	unquoted field name identifying the field within the data that represents the unique document id
text_field	unquoted field name identifying the field name in data that contains the text of the Tweet
top_num	integer, the top n long words to create features from
remove_urls	logical; should urls be removed prior to identifying long words

Details

Tweets are first converted to lowercase before the features are calculated. Twitter URLs (if remove_urls = TRUE), hashtags and @usernames are also removed.

The long word features are calculated as a proportion of the total number of words in the Tweet:

• the count of words that have 3 or more identical consecutive characters

• the count of the top_num words that are over 10 letters long

Value

A data frame of document ids their associated long word features

Examples

tweets <- data.frame(status_id = c(1234, 5678),
                     text = c("I tweeet about one thing #onething #things",
                              "I tweeet about otherthings #otherthings
                               #things"),
                     stringsAsFactors = FALSE)
feature_longwords(tweets, status_id, text)

sebastian-fox/twitterfeatures documentation built on Nov. 5, 2019, 8:47 a.m.