Natural Language Processing in R for Beginners

Learn how application programming interfaces enable computers to talk and retrieve data for natural language processing, with terms like client, resource, endpoint, and get or post requests.

Make your first get requests with the pooky api dutko api to fetch Pokemon data from the web, and learn how json data structures appear complex yet become clear.

Load the jsonlite package, transform JSON into R lists, and call an API in R Studio to retrieve Pokemon data, then loop through results and tidy into a data frame.

Discover how API keys and tokens control access to data, acting like passwords you must keep private, and learn to obtain, activate, and paste your key into your request URL.

Practice using the pokemon api to fetch name, height, weight, base experience, and primary type for several pokemon, then combine the results into a data frame.

Create film vectors, populate info inside a loop, and combine into a data frame; manage a private API key variable for the OMDb API from imdb.com.

Learn how to apply for a Twitter developer account and access the API v2 free sandbox, including selecting account type, answering policy questions, submitting the application, and email verification.

Learn how to obtain and store the five Twitter API credentials—Twitter app name, API key, API secret key, access token, and access token secret—through the developer portal.

Learn to use our tweet package to search tweets and retrieve timelines via Twitter's API, including token creation, API keys, and basic filtering for verified or non-verified users.

practice pulling tweets with rtweet, plot retweet-to-favorite ratios for dwayne the rock johnson via a scatterplot, and practice topic search with basic data cleaning on twitter data.

Learn to pull data from websites using rvest in R, inspect HTML structure, and transform scraped text—such as transcripts or news articles—into a tidy data frame for analysis.

Learn to fetch HTML from a web page, use XPath to target the Wikipedia table of the 2016 Summer Olympics, and convert it into a clean data frame in R.

Learn to scrape movie titles from unstructured html using read_html and css selectors, extracting text from lister-item-header elements and saving titles as a vector or data frame.

Scrape a twenty seventeen movie list by reading the HTML with rvest, extracting rank, title, runtime, genre, and primary genre, and assemble them into a data frame for analysis.

Discover how the getwiki package simplifies obtaining Wikipedia text in R with tidy output, and learn how to install it via the web tools package from GitHub.

Learn to fetch Wikipedia article text with get_wiki, save it as strings or a data frame, and prepare it for tidytext in this beginner natural language processing in R course.

Learn how to use a search function to return multiple articles based on a term, retrieve 20 results with titles and content, and fetch full articles with get wiki.

Practice using the getWiki workflow to search for the Soviet Union, retrieve 20 articles, and feed the results into getWiki to explore data size and insights.

Learn to use regex (regular expressions) in R for text data cleaning and pattern matching, leveraging tidytext workflows; understand patterns and shorthand for multiple words.

Explore stringr basics for beginners, including detect, extract, match, and replace patterns. Learn when to use replace all and how extract and match return lists versus vectors.

Explore how regex uses period, backslash, and character classes like \w, \d, and \s to match words such as walk and talk in R, and how escaping a period works.

Explore anchors in regex with start and end patterns in R, and use optional characters and grouping to flexibly match text, including mr x variants.

Explore using ranges and repeating patterns with brackets and braces to match specific character sets and extract data such as phone numbers.

Practice stringr techniques to detect phone numbers in text messages, filter fraud data, and handle optional formats like parentheses and dashes in R.

Learn how to prepare text data for computing by performing tokenization, removing stop words, and text normalization such as stemming or lemmatization, using unigrams and bigrams.

Download the Metamorphosis text from Gutenberg, import it in R, build a text data frame, and tokenize into unigrams and bigrams to analyze word patterns.

Remove stop words to reveal meaningful context in text data; the lecture demonstrates filtering stop words from a data frame and shows the before-and-after impact.

Apply stemming with the snowball stem package to reduce words to root forms, as shown with love. Note limitations such as overstepping and imperfect grouping that can misrepresent words.

Lemmatization applies language-aware text normalization to derive root words that belong to the language, using the limites words function from the text standard library.

Learn to clean text in R by tokenizing, filtering stop words, and limiting to single words in a data frame, then reconstruct and tokenize into n-grams.

Download heart of darkness from Gutenberg via doodlebug function, tokenize the text into trigrams, remove stop words, and convert to root forms; group by Gutenberg idea and reconstruct for visualization.

Create a bar chart and a word cloud to explore the most frequent words in a text dataset, using tokenization and stop-word removal to reveal key terms.

Load Hamlet text from Gutenberg, remove stop words, and build a bar chart of the ten most frequent words. Then create a word cloud from the tokens to visualize terms.

Create and inspect corpora in R using the tm package, importing Europe Wikipedia articles with getwiki, and convert data frames or vectors into a corpus with VCorpus.

Inspect or newsprint a corpus in R with the TM package to view metadata, access documents, and extract content with double brackets and substring.

Master data cleaning in R with tm_map, applying a function to a corpus with arguments like stop words removal and stemming, and using content transformer for lowercasing.

Explore the document term matrix, where rows are documents and columns are words with counts indicating term frequency, and examine sparsity, frequent terms, and word associations.

Learn to compute tf-idf by combining term frequency and inverse document frequency to compare word usage across chapters of metamorphosis, tokenize the text, and count word occurrences in R.

Explore term frequency in r by building a data frame of words per chapter, calculating chapter and book counts, and comparing across the book to uncover meaningful terms.

Explore idf, the inverse document frequency, and how it discounts very common words using the natural log of total documents over those containing the word, boosting rare terms.

Explore tf-idf in r by combining term frequency with inverse document frequency to identify chapter-specific, high-idf terms. Visualize top words by chapter to reveal important content beyond mere word frequency.

Pull Wikipedia articles for France, England, Russia, and Germany with the get wiki package, compute tf-idf top words per article, and visualize the results.