I train a classifier on a set of movie reviews to try to create a model for sentiment. Reviews are tokenized using TFIDF and then the respective TFIDF scores are used to train an SVM classifier. This classifer now knows a very basic understanding of what words correspond to positive and negative emotions/events. From here, incoming tweets are tokenized and the generated model is used to predict the sentiment of the tweet.
-
Notifications
You must be signed in to change notification settings - Fork 0
andrew749/Election-Sentiment-Analysis
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
Jupyter Notebook analyzing tweet sentiment during the election.
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published