Communications Mining user guide

The filter bar works similarly to the one in the Explore page. The key difference is that in Reports, you can use thread filters for conversational datasets containing threads, including email threads, chats, and call transcripts. For more details on thread filters, check .

You can add multiple filters, including multiple metadata fields, in the Reports and Explore tabs, and that all of the filters will determine the messages in scope as shown by the summary statistics on the page.

When selecting which labels to appear in the label-specific charts, use the Charted labels dropdown menu on the Trends or Segments pages.

The label filter bar in Reports works similarly to the one in the Explore page. For more information and a detailed explanation of the advanced prediction filters, check Advanced prediction filters.

On the filter bar, you can toggle between Messages and Threads. This allows you to apply analytics at the level of conversations, instead of individual messages.

The threads filter is applicable for longer-form conversations like email threads, phone calls, and live chats. Once the Threads filter is selected, a fourth reports tab will become available, containing charts relating to thread properties and label volumes.

The attachment based properties are available for each message that supports attachments.

These properties include:

You can filter the time series within Reports using the time series filter in the filter bar, or by selecting an area on a time series chart.

This will filter the messages in scope to only the select period, as well as adjust any time series charts to the filtered period.

Using the time series filter in the filter bar works similarly as the one in the Explore page. Select the following filters: From or To, or both, or choose a preset custom range such as Last 7 days.

To select the area on a time series chart:

Once the chart refreshes, it shows the time period that you selected has automatically been applied to the timestamp in the filter bar. You can view the time period in the summary statistics.

In the Trends tab, you can select which time sequence you want the time series charts to be displayed in using the dropdown menu as shown in the following image. This allows you to plot the time series charts as:

Advanced prediction filters represent a significant step forward in how the label filters work in both the Explore and Reports pages in the platform.

The capability of the platform has expanded to support intelligent filter combinations on label predictions.

When filtering by label predictions you can:

Essentially, the new filters allow you to apply any combination of AND, OR, and NOT filters when applying more than one label filter. These filters can give you much greater flexibility when training and interpreting your data, and can provide much deeper insights on happens in your communication channels.

This section contains details on the way you select a label to sort by when training in Explore, and how you select labels to appear in the charts in Reports.

When you filter to a label in Explore, this no longer determines the training mode or the sort order of the current training mode. Instead, this is determined by a taxonomy dropdown menu that appears when you select a training mode that is specific to a certain label, such as Check label or Missed label.

This allows you to sort by a certain label for a training mode and have an additional label filter applied.

How this works in practice is covered in the following sections.

Similarly, when you filter to labels in Reports this no longer determines which labels appear in charts. Instead, this also acts exclusively as a filter and the dropdown Charted labels menu determine which labels are shown in the charts. How this works in practice is also discussed in more detail at the end of this article.

There are now two ways to apply label filters, and they can be used in combination with each other to create the right type of query.

The taxonomy of labels functions as a normal filter bar, and allows you to select multiple labels at once with a single select for each.

Selecting multiple labels from the taxonomy creates an OR type query.

If you selected Label A, Label B, and Label C in the taxonomy, this creates the following query: Show me messages with Label A, Label B, or Label C predicted.

The following example would return messages that contained at least one of the three selected labels:

The second filter option is the + Add Label Filter button.

This enables a dropdown taxonomy that allows you to select more complex filters, including or excluding certain labels from consideration.

From this dropdown menu, you can select multiple labels that you want to include or exclude, by selecting the plus or minus buttons.

The result would be something like the following example, which would return messages predicted to have the label Billing or Refund, but that also do not have the label Chaser or Urgent predicted:

You can select + Add Label Filter multiple times to add additional layers to your query. Two separate label filters create an AND type query, while multiple labels selected in the same label filter create an OR type query.

In the example below, multiple label filters have been applied individually. This creates a filter that will return messages predicted to have either of the two labels in the first filter, but that also have the Policy label predicted, and do not have the Quote label predicted.

You can combine filters from both the taxonomy bar, and individually added label filters. Filters applied in the taxonomy bar are treated as an AND query with any individually applied label filters.

What these new filters also mean, is that you can now apply label filters and sort by a specific label for a training mode.

To enable the advanced prediction filters, a number of other updates have been made that do change the way you select labels to train in Explore. Overall, these changes make the platform more consistent across the platform, as well as providing greater capabilities to run detailed queries on your data.

You can find the selected training mode and sort order in Explore as shown in the following image.

The following example shows a user having selected Check Label and then being prompted to select which label to sort by:

The page also shows that the pinned label counts, red dial indicators, and any performance warnings for a label are also displayed in the taxonomy dropdown, giving you all the information you need to select the right label to sort by.

Once a label is selected, it will show next to the training mode alongside the number of pinned examples and any performance warning indicators.

Now, if you select a label from the label filter bar, the platform will prompt you to select it from the sort order dropdown menu if you intend to train the selected label:

You can see a specific mode in Explore, Sentiment, to sort by positive or negative sentiment only as shown in the following image. If you want to sort by label and sentiment, you can still do that using the Label sort order and adding a sentiment filter:

The label filters act exclusively as filters to update the messages that are in consideration, similar to any other user property filter, by including or removing messages that have or do not have certain labels predicted.

To select which labels actually 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 and these will be plotted on the charts which distinguish between different labels, as in the example below.

Remember, this does not change the messages that are in consideration by the platform, 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.

All of the labels that you select will appear highlighted at the top of the page as a visual reminder, and can easily be removed by selecting the X button next to each label name.

You can find the Chart labels dropdown option in the Label Summary, Trends, Segments, Threads, and Comparison tabs. Use this dropdown to select which labels appear or do not appear in the charts in the Reports page.

If you select a number of labels, they will appear in a bar at the top of the page 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 selecting the X icon next to each label name.

In Segments, much like you can choose to chart labels as previously shown, you can also chart specific string property values.

You can select a number of property values you wish to display on the chart, and this will override the default values shown, which are typically the property values that have the highest corresponding message volumes.

In the following example, the email property of Sender Domain is shown. Using the dropdown from the chart, you can select a number values to display instead of the default ones shown.