SENTIMENT ANALYSIS ON SOCIAL MEDIA
The analyses were conducted using a Lexicon-based approach on Python
Sentiment analysis can be used to classify large amounts of information on the web, into groups based on the sentiment (i.e. the feelings) of the people who stated their opinions. Many many people write reviews daily, rate products/services/books/movies and state opinions online. This technique can be used to gauge people's sentiment toward something.
A Sentiment Analysis can be used to gauge people's impressions of new music releases, movies, opinions about the local police and people's feelings towards government and political parties.
The analyses were conducted following the guide by Peter D. Turney.
This paper introduces a simple unsupervised learning algorithm for rating a review as thumbs up or down. The algorithm has three steps: (1) extract phrases containing adjectives or adverbs, (2) estimate the semantic orientation of each phrase, and (3) classify the review based on the average semantic orientation of the phrases.
Peter D. Turney "Thumbs Up or Thumbs Down? Semantic Orientation Applied to
Unsupervised Classification of Reviews"
Analysis specific to text on Twitter was conducted with the help of "Twitter Sentiment Classification using Distant Supervision", a technique by Go, Bhayani & Huang from Stanford University.