Help in doing Sentiment analysis in SAS

[PranavKarnavat]

I have been working in the area Text Mining for 6 months. However I have never tried doing Sentiment Analysis. I have read theory about sentiment analysis and I am really excited to know how SAS actually do it. It would be nice if someone tells me the tool of SAS used, procedure used in doing it.

[AnnKuo]

There are several SAS products that can analyze sentiment of of your documents.  

• SAS Sentiment Analysis. It uses a combination of statistical and linguistic rules to identify positive, negative, neutral, or unclassified opinions from unstructured text data. Multi-level taxonomies can now be defined, so that sentiment can be derived for the overall document, a concept in the document (such as a brand or product), an attribute or feature of the product, and characteristics of features – with different linguistic rules defined for each level. Please refer to SAS Sentiment Analysis for more details about this product.

• SAS Text Miner. You can use the topic node to get sentiment attached to documents.   Just use the sampsio.afinn_sentiment data set as your “user topics” in the text topic node, and it will add two user topics: one for positive and one for negative sentiment.  Furthermore, you can change the topic weights in the Interactive Topic Viewer to adjust to your data if you wish.  There is a SAS Tech Talk: Text Analytics YouTube video created by Dr. James Cox that shows you the "how to" starting at approximately 5 minutes after. 

• SAS Contextual Analysis. It derives sentiment scores in the document level.  However, it does not allow you to write your own linguistic rules.  Please refer to SAS Contextual Analysis for more details about this product.

 Hope this helps!

Ann