How to use the Sentiment Overview

1. What is Sentiment Analysis?

2. How to use Sentiment Analysis

1. What is Sentiment Analysis?

The sentiment analysis in 'Sentiment Overview' is based on a post-level deep learning-based model that detects the sentiment of an entire text and towards specific topics or categories. It goes beyond keyword sentiment and instead looks at sentences and paragraphs as a whole to truly understand what sentiment is associated with what topic.

The Sentiment analysis complements category and topic analysis to convey not only what a person is talking about, but also how they feel about it.

2. How to use Sentiment Analysis

In the chart, you will see the volume, Net Sentiment, and a bar chart with the absolute and relative numbers of sentiment.

Further possibilities when exploring this page are:

  1. Choose a filter option to break down the personality traits into your different filter options, e.g. company name/brand, ratings, source names, etc.
    This allows you to compare the sentiment by brand and other meta fields.
  2. Click here to export as CSV or PNG
  3. Apply Slicing filter: You can either slice it by category, topic, personality (emotional/rational), recommendation (promoter, detractor, indifferent), the meta fields you have added to your data file, or enter a date range. You can even type in a keyword to specify the search.

  4. Click on a value in the bar chart to open the sidebar: This will give you more detailed information about the selected value:

    - Details: Term Cloud with positive and negative terms and the psychographic segments
    - Posts: view the original posts here 

Net Sentiment = [(count of positive terms - count of negative terms)/ total count of terms] *100

If you want to read more about Net Sentiment please visit our FAQs page: What is Net Sentiment?