Using Twitter generated API Keys, the data has been imported basis keyword, language, location & date filters.
The extracted data has additional features as well and requires immediate data cleaning before performing further analysis.
After performing Data Mining, the codes show 2 visualization plots : WordCloud and Sentiment Analysis Barplot.
Word Cloud : A WordCloud is a visual representation of text data depicting key words, trends and patterns for the specified duration. The greater the word size in the plot, the more frequently is the word used.
Sentiment Analysis Barplot : After performing Data Mining and Sentiment Analytics, the tweets are given a sentiment score (ranging from -1 to 1) and are accordingly classified and visualised in the form of a Barlot with 3 categories namely : Negative, Neutral and Positive.
There are generally 3 methods used while classifying Sentiments :
-
AFINN : Assigns words with a score between -5 and 5, with negative score indicating negative sentiment and positive score indicating positive sentiment.
-
BING : Assigns words with a score between -1 and 1, which can be classified into 3 categories namely : Positive, Neutral and Negative.
-
NRC : Assigns words into one or more of the following 10 categories : positive, negative, anger, anticipation, disgust, fear, joy, sadness, surprise and trust.