Sentiment Locator
The
Sentiment Locator uses the built-in functionality of the
Natural Language Processing engine to extract
text sentiments from a document. This means that the
Sentiment Locator is able to determine the overall mood, or sentiment of a document based on the words
and phrases found on a document.
For example, if your company has several products, and each have online ratings, you can use the Sentiment Locator to determine whether your users are providing good and positive reviews, or bad and negative reviews.
This locator is mapped to a simple field and the extracted result of the locator is any value between -1.00 and 1.00 with the following ranges.
-
Positive - 0.12 to 1.00
-
Neutral - 0.025 to 0.11
-
Negative - 0.026 to -1.00
For example, a result of -0.75 indicates that the processed document contains a majority of bad or negative comments. A result of 0.8 indicates that the processed document contains a majority of good or positive comments, and a result of 0.1 indicates that there is about an equal ratio of both positive and negative comments.
Because this locator searches for sentiments automatically there are no configurable settings for this locator. You can however, narrow the area on a document or page where the locator is executed. You can do this by adding regions to a document or page so specific areas are included or excluded from the locator.
For example, if your document contains a header that includes an address and a salutation, these areas do not typically contain data related to the overall mood or sentiment of a document. As a result, you can use a region to exclude the top 1/3 of the first page of a document.
The Properties of Sentiment Locator window has the following tabs.
-
Regions tab
-
Test Results tab