Positive (P) and negative (N) sentiment are just transmitting two results based on many other variables. This in itself contains little knowledge. For creating strategy, it can only bench mark after the fact.
Inherently the use of data is to make better decisions for the future. Production is expensive and time consuming. So is deductive reasoning. The main goals should be to move away from adjusting to the end reaction and migrate to a predictive model. Look at the context in higher resolution i.e. control for variables which lead to PN sentiment.
Here are some suggestions
- Time of day
- Medium (Twitter,Facebook ,Blogs, Mainstream news)
- Comments PN sentiment
- New dissemination to comment count (time, PN)
If you are advanced, use NLP tools that allow for custom taxonomies – within the NLP, to create rules on varibels like types of framing. On a medium level this is very good at prediction, but more on that later.