Loved by learners at thousands of companies
Expand Your Text Mining Skill SetAdd sentiment analysis to your text mining toolkit! Sentiment analysis is used by text miners in marketing, politics, customer service, and elsewhere. In this course you will learn to identify positive and negative language, specific emotional intent, and make compelling visualizations. You’ll start with an introduction to polarity scoring using qdap’s sentiment function, and will build your understanding of Zipf’s law and subjectivity lexicons along the way.
Use Tidytext to Perform Sentiment AnalysisSentiment, and the language used to express it, is complicated and nuanced. It’s based on linguistics, sociology, and psychology, as well as culture and slang. The second chapter in this course helps you navigate those difficulties using Plutchik’s wheel of emotion, and organizes your work using Tidytext from the Tidyverse.
Bolster Your Insights with Sentiment Analysis VisualizationsTurning your sentiment analysis into clear data visualizations will help you create a clearer narrative and share your insights with the rest of the business. The third chapter of this course shows you how to visualize your sentiment analysis, and takes you beyond word clouds to create simple and impactful graphics that tell the full story of your data.
You’ll finish off the course by putting all of your knowledge to the test with a case study. Using Airbnb reviews, you’ll explore what people really look for in a good rental.
Fast & Dirty: Polarity scoringFree
In the first chapter, you will learn how to apply qdap's sentiment function called polarity() .Let's talk about our feelings50 xpJump right in! Visualize polarity100 xpTM refresher (I)100 xpTM refresher (II)100 xpHow many words do YOU know? Zipf's law & subjectivity lexicon50 xpWhat is a subjectivity lexicon?50 xpWhere can you observe Zipf's law?100 xpPolarity on actual text100 xpExplore qdap's polarity & built-in lexicon50 xpHappy songs!100 xpLOL, this song is wicked good100 xpStressed Out!100 xp
Sentiment Analysis the tidytext Way
In the second chapter you will explore 3 subjectivity lexicons from tidytext. Then you will do an inner join to score some text.Plutchik's wheel of emotion, polarity vs. sentiment50 xpOne theory of emotion50 xpDTM vs. tidytext matrix100 xpGetting Sentiment Lexicons100 xpBing lexicon with an inner join explanation50 xpBing tidy polarity: Simple example100 xpBing tidy polarity: Count & pivot the white whale100 xpBing tidy polarity: Call me Ishmael (with ggplot2)!100 xpAFINN & NRC methodologies in more detail50 xpAFINN: I'm your Huckleberry100 xpThe wonderful wizard of NRC100 xp
Make compelling visuals with your sentiment output.Parlor trick or worthwhile?50 xpReal insight?50 xpUnhappy ending? Chronological polarity100 xpWord impact, frequency analysis100 xpIntrospection using sentiment analysis50 xpDivide & conquer: Using polarity for a comparison cloud100 xpEmotional introspection100 xpCompare & contrast stacked bar chart100 xpInterpreting visualizations50 xpKernel density plot100 xpBox plot100 xpRadar chart100 xpTreemaps for groups of documents100 xp
Case study: Airbnb reviews
Is your property a good rental? What do people look for in a good rental?Refresher on the text mining workflow50 xpStep 1: What do you want to know?50 xpStep 2: Identify Text Sources100 xpQuickly examine the basic polarity100 xpStep 3: Organize (& clean) the text50 xpCreate Polarity Based Corpora100 xpCreate a Tidy Text Tibble!100 xpCompare Tidy Sentiment to Qdap Polarity100 xpStep 4: Feature Extraction & Step 5: Time for analysis... almost there!50 xpAssessing author effort100 xpComparison Cloud100 xpScaled Comparison Cloud100 xpStep 6: Reach a conclusion50 xpConfirm an expected conclusion50 xpChoose a less expected insight50 xpYour turn!50 xp
In the following tracksText Mining
DatasetsLine by line polarity for 4 books4 books as a tidy data frame4 books as DocumentTermMatricesPolarity scores of Boston Airbnb reviewsHousing rental reviews from Airbnb in Boston
PrerequisitesText Mining with Bag-of-Words in R
Adjunct Professor, Harvard University
Ted Kwartler is the VP, Trusted AI at DataRobot. At DataRobot, Ted sets product strategy for explainable and ethical uses of data technology in the company's application. Ted brings unique insights and experience utilizing data, business acumen and ethics to his current and previous positions at Liberty Mutual Insurance and Amazon. In addition to having 4 DataCamp courses he teaches graduate courses at the Harvard Extension School and is the author of Text Mining in Practice with R.