- Getting Started
- 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, entities 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)
- Understanding the status of your dataset
- Model training and labelling 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 Analytics & Monitoring
- Automations and Communications Mining
- FAQs and More
Reports
The platform's built in reporting functionality has up to six tabs — Dashboard, Label Summary, Trends, Segments, Threads, and Comparison.
- Dashboard allows you to create custom dashboard views using the data from the other tabs. Please see here for more information.
- Label Summary presents high level summary statistics for labels. Please see here for more information.
- Trends presents charts for message volume and label volume and sentiment over a given time period. Please see here for more information.
- Segments presents charts of label volumes versus message metadata fields, e.g. sender domain. Please see here for more information.
- Threads presents charts of thread volumes and label volumes within a thread (only accessible when the 'Thread' filter is applied). Please see here for more information.
- Comparison allows you to compare different cohorts of data against each other. Please see here for more information.
At the top of each tab in the Reports page, you will see the number of messages contained in the dataset, net sentiment (if sentiment analysis is enabled) and the date period for the selected data.
You can think of the Dashboard page as a place to create fully customizable reports or even a homepage for your datasets. Here you can add high-level information on the datasets, such as accuracy of the model, various charts, recent messages and the health of your taxonomy, etc.
To access the dashboard, go to the Reports page on the top navigation bar, then click Dashboard. You can see the default dashboard automatically created (see below).
Dashboards are specific to the dataset itself. You can create new dashboards, delete and edit existing ones. The titles of the dashboards can be renamed to suit your use case.
These dashboards can be viewed by anyone with view access to the dataset, but to create, edit and delete any dashboard, you need the Modify dashboards permission.
As a default, the dashboard does contain a few example visuals (as shown below). Users can fully customize their dashboards (both what’s included, removed, and how it's arranged) by adding charts to them from the Reports page. You can also resize cards by dragging the bottom corner.
Example of a customized Dashboard page:
Each dashboard card has its own filter, determining which information is presented on it. To create a card, you simply create the filtered card on the Reports page and tap the add button in the top hand corner. You can change the filters of a specific card, directly from the dashboard.
You also have access to a global filters feature, which allows you to augment any existing filters across the existing cards on the dashboard (by narrowing down to a specific time-range, for example). To learn more about updating dashboards, go to the Using Dashboards page.
By selecting from the time sequence dropdown menu just below the summary statistics in the Trends tab, you can view the data in the time series charts:
- Daily
- Weekly
- Monthly
- Yearly
Beneath each chart you’ll see a number of buttons when you hover over it with your mouse.
The buttons available change depending on the exact chart type, and some are revealed when you click on the existing view to change to a new one:
| Add this chart to your dashboard | |
| Option to download an image of the chart, download the raw data for the chart as CSV, or add chart to your dashboard | |
| Show percentages | |
| Show totals | |
| Display as column/bar chart | |
| Display as line chart | |
| Display as scatter graph | |
| Display as doughnut chart | |
| Sort by prominence | |
| Sort alphabetically | |
| Sort reverse alphabetically | |
| View labels with the biggest changes in rank | |
| Change the number of labels displayed |
To understand more about how Reports actually works and how to use it, see here.
Next to the time sequence dropdown menu at the top of the page is the 'Charted labels' dropdown menu.
To select which labels actually appear or do not appear in the charts in the Reports page, there is now a 'Charted labels' dropdown menu in the top bar.
Simply select whichever combination of labels you want to appear (the plus symbol) and these will be plotted on the charts that distinguish between different labels, as in the example below. Alternatively, you can select labels you don't want to appear by using the exclude button (the minus symbol).
If you select a number of labels, they will appear in a bar at the top of the page (see below) as a visual indicator of which labels have been selected to appear on the charts.
All of the labels that you select or exclude will appear highlighted at the top of the page as a visual reminder, and can easily be removed by clicking the 'x' icon next to each label name.
Reports page showing 'Charted labels' selected
Please Note: This action does not change the messages that are in consideration, merely which labels are plotted on the label specific charts. An easy way to remind yourself of this is to note that the total number of messages shown at the top of the page does not change when you select any labels from the 'Charted labels' dropdown.
In Segments, much like you can choose to chart labels (see above), you can also chart specific string property values.
You can click a number of property values you wish to plot on the chart, and this will override the default values plotted, which are typically the property values that have the highest corresponding message volumes.
In the example below, the email property of 'Sender Domain' is shown. Using the dropdown at the top-right of the chart, you can select a number values to plot instead of the default ones shown.
The Segments tab loads a number of property based charts by default, but some of those with a very high number of potential values can default to hidden. Users can also choose to hide property charts that they do not find useful.
In the example below, the property charts for 'Inbound', 'Cc', and 'To' (all email related) are hidden.
To unhide a chart, simply click the eye icon next to its name and the platform will load the chart for the property.
To hide a chart, simply do the click the corresponding icon (the eye with a strike through it) at the top right of the chart. The chart will then appear in the 'Hidden property charts' list.
For more information about filtering, check the Applying Filters on Reports page.
The Compare page allows you to compare the distribution of labels across two different user defined cohorts of messages or threads.
Users can apply filters to Group A and Group B to compare the count, proportion, and sentiment of the labels across the groups and see the differences in these numbers. Depending on the analytics a user would like to extract, one can toggle between 'messages' and 'threads' depending on if they want to compare individual messages or compare at a thread level (e.g. for email threads, phone calls and live chats).
