preprocess_text: Preprocess article text

In LBDiscover: Literature-Based Discovery Tools for Biomedical Research

Preprocess article text

Description

This function preprocesses article text for further analysis.

Usage

preprocess_text(
  text_data,
  text_column = "abstract",
  remove_stopwords = TRUE,
  custom_stopwords = NULL,
  stem_words = FALSE,
  min_word_length = 3,
  max_word_length = 50
)

Arguments

text_data	A data frame containing article text data (title, abstract, etc.).
text_column	Name of the column containing text to process.
remove_stopwords	Logical. If TRUE, removes stopwords.
custom_stopwords	Character vector of additional stopwords to remove.
stem_words	Logical. If TRUE, applies stemming to words.
min_word_length	Minimum word length to keep.
max_word_length	Maximum word length to keep.

Value

A data frame with processed text and extracted terms.

LBDiscover documentation built on June 16, 2025, 5:09 p.m.