Sentiment analysis

Tools for sentiment analysis:

 Textblob:

 textblob is the python library for processing text data. PatternAnalyzer and NaiveBayesAnalyzer.

Pattern analyzer is the default.

Naive bayes gives name with tuple (p_pos, p_neg) where p_pos is the probability of pos emotion and p_neg is the probability of negative emotions

Vader:

it is rule based sentiment analysis and suitable for predicting sentiments on social media.

it uses dictionary that maps lexical features (word frequency, word neighborhood count, word association) to intensity of emotions known as sentiment scores.

we can use it using NLTK library.

it returns positive, neg, neutral, and compounds which represent emotional intensity.