Create two different corpuses for each of the product, and also cleanse the data.

Page1: Cover Page
Page 2: Index
Page 3: Scrape product reviews data for two competing products from amazon.com using the Get Data slides in this presentation. Describe your data. Insert the CSV file on page 3 using insert object command (refer to the insert object slide in this presentation).
Page 4: Create two different corpuses for each of the product, and also cleanse the data. Provide top 20 most frequently occurring words; what interpretations do you draw from these top words about the product; explain DTM using a output of top 10 rows and 10 columns, for both the products.
Page 5: Provide a word cloud based on the reviews downloaded, interpret the word cloud for both the products.
Page 6: Provide Sentiment analysis; what interpretations do you draw from this sentiment analysis
Page 7: Provide association analysis. Use a word which reflects customer sentiments such as happy, sad, satisfied, nice (be creative here) to measure the association with different words occurring at 50%, 75% and 90% levels in your reviews. Repeat the analysis for 4 more words.
Page 8: Perform topic modeling with 2 topics, and interpret the two topics, for both the products.
Page 9: Perform topic modeling with any number of topics between 3 and 5, and interpret the different topics, for both the products.
Page 10: Perform one other analysis for both the products using the R techniques we have learned so far e..g, network analysis, visualization, descriptive analysis etc.
Page11: R code: provide your R code file, insert it as an object (refer to Insert Object slide). Your R code file needs to be well commented, and easy to read / understand.

order now