- Getting started
- Balance
- Clusters
- Concept drift
- Coverage
- Datasets
- General fields (previously entities)
- Labels (predictions, confidence levels, hierarchy, etc.)
- Models
- Streams
- Model Rating
- Projects
- Precision
- Recall
- Reviewed and unreviewed messages
- Sources
- Taxonomies
- Training
- True and false positive and negative predictions
- Validation
- Messages
- Administration
- Manage sources and datasets
- Understanding the data structure and permissions
- Create a data source in the GUI
- Uploading a CSV file into a source
- Create a new dataset
- Multilingual sources and datasets
- Enabling sentiment on a dataset
- Amend a dataset's settings
- Delete messages via the UI
- Delete a dataset
- Export a dataset
- Using Exchange Integrations
- Preparing data for .CSV upload
- Model training and maintenance
- Understanding labels, general fields and metadata
- Label hierarchy and best practice
- Defining your taxonomy objectives
- Analytics vs. automation use cases
- Turning your objectives into labels
- Building your taxonomy structure
- Taxonomy design best practice
- Importing your taxonomy
- Overview of the model training process
- Generative Annotation (NEW)
- Dastaset status
- Model training and annotating best practice
- Training with label sentiment analysis enabled
- Train
- Introduction to Refine
- Precision and recall explained
- Precision and recall
- How does Validation work?
- Understanding and improving model performance
- Why might a label have low average precision?
- Training using Check label and Missed label
- Training using Teach label (Refine)
- Training using Search (Refine)
- Understanding and increasing coverage
- Improving Balance and using Rebalance
- When to stop training your model
- Using general fields
- Generative extraction
- Using analytics and monitoring
- Automations and Communications Mining
- Licensing information
- FAQs and more
Explore
User permissions required: ‘View Sources’ AND ‘View Labels’.
The Explore page allows you to search, review and filter a dataset to inspect and review individual messages and general fields. You can navigate the Explore page by clicking 'Explore' on the top navigation bar.
By default, Explore presents the 20 most recent messages in a dataset in the 'Recent' mode, you can click the dropdown mode selector in the top left-hand corner of the page to change this.
The different options you can select from the dropdown menu are:
- Recent – view 20 most recent messages
- Shuffle – view 20 random messages
- Teach – show 20 messages that the platform is unsure how to annotate
- Low confidence – show 20 messages which are not well covered by informative label predictions
- Rebalance - show 20 messages that are underrepresented by the training data in your dataset
- Label - view 20 messages with the selected label assigned / predicted (this is the default mode when a label is selected)
- Check label - view 20 messages that may have the selected label applied incorrectly
- Missed label - view 20 messages that may be missing the select label
At the bottom of the page you can click to move to the next page of 20 messages, or go back to a previous page.
The filter bar on the left-hand side of the page (as shown below) allows you to find specific groups of messages.
From this filter bar you can filter to:
- Specific date ranges (pick exact dates or select from options like the last week, month, 90 days or year)
- Reviewed or unreviewed messages
- messages with positive or negative sentiment predictions (if sentiment is enabled on the dataset)
- Add any filter based on the metadata properties associated with your messages (click 'Add a new filter')
- Filter to messages that have specific general fields predicted or assigned
- Filter to messages that have (or do not have) a specific label or combination of labels predicted (see the article on Advanced Prediction Filters for more detail)
When you click 'Add a new filter', the dropdown shows a full list of all the available property filters.
These are naturally grouped by categories, and some are unique to the communication type in the dataset, e.g. email.
The property categories that properties are grouped together in are:
- Source - this only appears if there is more than one source in the dataset
- Email - these are specific to individual emails, e.g. who sent it
- Thread - these are email specific and relate to the characteristics of email threads
- Attachment - specific for messages (primarily emails) with specific attachment properties.
- User - all other metadata properties uploaded (and not derived by the platform) with each message
To the left of each property, an icon indicates the property type, whether it's a number or string. For string user properties, the platform provides an example value on hover (see below).
When you add a filter to metadata fields with a string format, you will be able to choose which to include or exclude in your selection (as shown in the two examples below):
If you add a filter to metadata fields with a number format, you will be able to select minimum or maximum values (as shown below), to create a range of your choice:
To remove a filter that you've applied, simply click the bin icon that appears when you hover over it with your mouse (as shown below), or select 'Clear All' at the top of the filter bar, to remove all filters applied.
You can use the label filter bar to filter to messages that have (or do not have) specific labels predicted, either whilst Model Training or whilst exploring and interpreting your data. To see how they work in more detail, see the article on Advanced Prediction Filters here.
You can use the buttons at the top of the label bar to filter between showing all messages, to those that have had labels assigned to them, or those with predictions (that have not been reviewed). The icons are shown below, and they change colour when selected:
Select messages that have assigned labels | |
Select messages that have labels predicted |
To deselect the filter, simply click the button again.
If you select neither button, but filter to a label, the platform will filter to all messages that either have the label pinned or predicted, starting with the reviewed messages first.
The label filter bar and '+ Add label filter' allow you to add complex combination or inclusion and exclusion filters (i.e. show me messages with X and Y predicted, but not Z). To find out more about how to use these, see the 'Advanced Prediction Filters' article here.
Red dial training indicator:
- The red dial training indicator (see here for explanation) next to some labels highlights those which require more training examples for the platform to accurately evaluate the performance of the label
- The completeness of the circle indicates how many more examples are needed. The larger the red section, the more examples are required
- Once you have 25 annotated examples, the red circle will disappear (depending on the complexity of the label, however, you may need more examples to get accurate predictions)
- You should review messages to find more training examples.
For datasets containing emails, these are displayed showing the email that matches the selected sort order (e.g. Teach Label, Missed Label, etc.), but with easy access to the other emails that are in the same email thread.
In the example below, you can see the sorted email is in a thread of three emails, and this is the third email in the thread.
By clicking the bi-directional arrow icon below the subject, you can expand out the email thread to show partial views of the other emails in the thread, as seen below:
If you click again on any of the partially expanded emails, they will be expanded in full like the original sorted email, as seen below: