Last updated on APRIL 24, 2017
Applies to:Oracle Social Engagement and Monitoring Cloud Service - Version N/A and later
Information in this document applies to any platform.
Sentiment analysis can get different results on tweet and retweet. In situations where we have a limited amount of text, it gets even harder to determine sentiment.
In situations when retweets or republishing of messages, the extra text (RT, url), are also included in the text body, and broken up for sentiment analysis. Sentiment analysis will break apart the message and analyze it piece-by-piece. In the retweet, it may see the new word "resists", or the increased number of times that "removes", "arrested", etc... as enough to push the message to negative.
Sign In with your My Oracle Support account
Don't have a My Oracle Support account? Click to get started
Million Knowledge Articles and hundreds of Community platforms