Create a dashboard to capture sentiments and trending topics behind customer feedback.
Prerequisites
Verify that Text Analytics is enabled. To check if Text Analytics is enabled, create a new dashboard and add a visualization tile. If Text Analytics is enabled an entry named Text Analytics Responses will be listed in the Choose an Explore dialog box.
Detailed Steps
- Create a new dashboard and select either Survey Responses or Text Analytics. The Text Analytics template automatically creates a number or predefined text analytics tiles, but is otherwise the same as the Survey Responses template.
- Open the dashboard in edit mode and select Add > Visualization.
- In the Choose an Explore dialog box, select Text Analytics Responses.
In the field picker two sections are available that are exclusive to text analytics dashboards:
Dimensions > Text Analytics and Measures > Text Analytics.
Field List
When you edit a tile in a text analytics dashboard, you will see a number of additional fields that do not appear in other dashboards.
| Type | Field | Description |
|---|---|---|
| Measure | Category - name | Taxonomy only - The actual category and subcategories predicted. (Category/Sub-category1/Sub-category2/...) |
| Measure | Category - score | Taxonomy only - The relevance score of the predicted category (not sure the range? 0-1?) |
| Measure | Full Text | Contains all open-ended responses. One record per question response |
| Measure | Full text - Language | The language of the text (en=English) |
| Measure | Full text - Sentiment Label | Positive, Negative, or Neutral - for a Full Text item |
| Measure | Full text - Sentiment Score |
A number between -1 and +1 -1 = completely negative 0 = neutral +1 = completely positive |
| Measure | Key phrase - count |
The count of the occurrences of the detected keyword. Does not count duplicates so if someone says “I will check if the check was cashed” it will count “check” only once |
| Measure | Key phrase - relevance | The relevance score of the detected keyword - a number between 0 and 1? |
| Measure | Key phrase - sentiment label | Positive, Negative, or Neutral - for a key phrase |
| Measure | Key phrase - sentiment score |
A number between -1 and +1 -1 = completely negative 0 = neutral +1 = completely positive |
| Measure | Key phrase - text | Contains all key phrases identified by the analytics engine |
| Measure | Text Fields - Field Name | The field name associated with the full text or key phrase |
| Dimension | Full text - Response Count | Counts each full text entry. This differs from the standard Count field which counts each survey response. So if you have a survey with 3 open-ends and 10 people complete it, this will be 30 and Count will be 10 |
| Dimension | Full text - Response Percent | The response count for a full text entry divided by the total response count - eg 10% of people answered “no comment” to an open-ended question |
| Dimension | Key phrase - count with duplicates | Unlike Key phrase - count this includes duplicates. So if someone says “I will check if the check was cashed” it will count “check” twice |
| Dimension | Key phrase - text concat | Concatenates all key phrases into one long sentence separated by commas |