Daylight | Cloud | 2020-09-26



New feature


Enhancements


Fixes


Drivers: Trend analysis now available to all users

With this release, all Daylight users can access Drivers: Trend Analysis, previously a premium feature. Use this new version of the feature to harness Drivers’ powerful blend of qualitative and quantitative data through time-based comparisons.

This feature offers comparative scatter plots you can use to discover directional changes in drivers over time in periods you define using the options based on any metadata date fields included in your project.


To use trend analysis in Drivers

  1. Open Daylight and select the Drivers feature.

  2. In the Configure visualization tab, select a score field from the menu.

  3. Choose Autosuggest, Saved concepts, or Unique to this filter from the Which concepts to visualize section. Concepts that Daylight identified as strongly influencing your score are auto suggested. Alternately, save concepts that are relevant to your business to view them in Drivers. Finally, use the Unique to this filter option to identify auto suggested concepts that are uniquely relevant to any filters you’ve applied, as compared to the rest of your dataset.

  4. Click the pencil icon next to Select date field to compare periods and select your desired date field from the menu. The visualization splits into two scatterplots. The top scatterplot automatically displays the full date range for the filter you applied.

  5. Refine the date range in the top scatterplot to an interval you’re interested in. The bottom scatterplot automatically identifies and displays the same size time interval ending a day before the interval you selected for the top pane. For instance, if you selected a 10-day interval of time, the bottom scatterplot would display the previous 10-day interval.

  6. Change the date interval in the lower scatterplot, if desired. Each scatterplot displays the most relevant auto suggested or saved concepts for that period of time.



To configure Drivers concepts using the concept tab

As part of this change, we also introduce a Concepts tab at the top of the Drivers visualization. Use this tab to select the concepts you view in the single drivers visualization, or independently for the top and bottom comparative visualizations.


  1. Click the Concepts tab. It opens to a list of concepts that match whatever score field and type of concepts to visualize you selected, sorted by absolute difference.

  2. Configure the concepts to match what you want to see in the scatter plot visualization:

  • Quick select the top 10 or 20 concepts. Top concepts vary by the type of sorting you apply, but default to concepts with the greatest absolute difference.

  • Order concepts by Concepts, Total Matches, Average score, or Absolute difference. This order affects which concepts appear in your top 5, 10, or 15 concepts.

  • Click Deselect all to deselect all concepts.

  • Click the view icon in a concept row to select or deselect a specific concept. If you want to remove a concept from the visualization, deselect it. Only selected concepts appear in the scatter plot.

  • In Concepts (Below), toggle on Same concepts as top scatterplot to match the concepts that appear in the bottom scatterplot to the concepts that appear in the top scatterplot. If a concept was not discussed during the previous period or year over year period, it does not appear in the bottom scatterplot.

  • Hover or click on a concept to see a tip appear in one or both scatterplots.


3. Click Visualization to reopen the Drivers scatterplot and view your selected concepts.



To organize concepts in separate Drivers trend analysis panes

  1. Make sure the Drivers visualization is showing the dates you want to use, and that you’ve selected either Autosuggest or Saved Concepts in the Configure visualization tab.

  2. Click Concepts (Above) or Concepts (Below) to edit the concepts you view in each scatterplot. Depending on your needs, you may wish to view the same or different concepts in the top and bottom panes.


Single sidebar project completed

With this release, all changes that are part of our ongoing single sidebar project are complete. Now Daylight only has a left-hand sidebar with tabs where you can:

  • View all information for concepts

  • Manage saved and suggested concepts

  • Apply filters

  • Configure feature visualizations

  • View documents

  • Create exports


Updated order to sidebar tabs

Now, tabs in the sidebar are reordered to better reflect how users move through Daylight. The new order is:

  • Search details

  • Select concepts

  • Filter documents

  • Configure visualization

  • Documents

  • Export & share


Tooltips added to sidebar tabs

With this release, we also add tooltips to each sidebar tab. Hover over each tab to see its name appear in a tooltip.


New Search details tab

With this release, we move all previous Concept details information into a new Search details tab. View exact, conceptual, and excluded match information for concepts. You can select concepts by:

  • Clicking a concept name in the feature.

  • Entering concept(s) in the search bar. Note: You must use the search bar to view details for multiple concepts at the same time, unless you have saved a previous advanced concept search.


New Documents tab

With this release, we move all document information that matches your filter and search selections from the right-hand Documents section into a new Documents tab in the left sidebar.


Use this tab to explore relevant documents in depth. If you’re viewing documents related to a specific concept, you can use the Exact and Conceptual icons to view only documents that contain exact or conceptual matches.

Click Download to view all matching documents in a spreadsheet. Click create project to create a project that includes only documents that match your concept and filter configurations.



New Exports tab

With this release, we move all Daylight exports into a new Export & share tab. This tab combines several ways to export information from Daylight:

  • Link to current view – Click Copy link to copy a link to your current view in Daylight. The link will bring you or anyone you share it with directly to all concepts, feature and filter configuration information you’re viewing.

  • Export current selections as spreadsheet – Click Export to download a spreadsheet based on the feature information you’re currently viewing. Selections reflected in this spreadsheet include filters, the type and number of concepts you’ve chosen to visualize, and Unique to this filter.

  • Export raw data as spreadsheet – Click Export to download a spreadsheet, after using a radio button to select one of the following options:

  • Current documents – Download all documents in your project that match your filter and concept selections. This download also includes all metadata for your project.

  • Concept-Filter association scores – Download a spreadsheet that contains the level of association between the metadata filters in your project and any concepts you selected. Daylight identifies these associations as part of the upload process, and associations may change depending on project size.

  • Concept-Concept association scores – Download a spreadsheet that contains the level of association between concepts you selected. Daylight identifies these associations as part of the upload process, and associations may change depending on project size.



Removed bottom left downloads icon

With this release, we remove the downloads icon from the bottom left corner of the app.

We also remove the Match counts download entirely, since the same information is available through opening Volume and clicking Export in the Export current selections as spreadsheet section.

Now, the Concept-Filter and Concept-Concept association scores downloads that you previously accessed through the bottom left download icon are available in the Export & share tab of the sidebar left sidebar.



Select or deselect all suggested concepts

With this release, we make it possible to select, or deselect, the entire contents of the Select concepts list by checking or unchecking the Select all box.



Concepts with positive and negative sentiment no longer appear twice in concept list

Previously, if Luminoso determined with high confidence that a concept had both strong positive sentiment and strong negative sentiment, it would appear twice in the list of sentiment suggestions in both the API and UI.

Now, concepts that fit this description are only included once, which is more intuitive for users.




Daylight | Cloud | 2020-09-12



Enhancements

  • Project management: Select and delete multiple saved concepts in the left sidebar

  • Drivers: Save concepts using + icon

  • Search: Search bar moved to the top of visualization space

  • API: Added result_count field to the get documents endpoint


Select and delete multiple saved concepts in the left sidebar

With this release, you can now use a checkbox in the left sidebar to select and delete multiple saved concepts. This change makes it easier and smoother to manage your saved concepts in Daylight


To delete multiple saved concepts

  1. Select the Concept details tab in the left sidebar.

  2. Select any saved concepts you want to delete, or use Select all to select all saved concepts.

  3. Click Delete selected. A dialog box appears.

  4. Click Ok to delete the concepts you selected.



Save concepts using + icon in Drivers

Now, when you click the + icon to the left of a concept’s name in the Drivers concept list, the concept is added to your saved concept list.


Search: Search bar moves to the top of visualization space

As part of our series of single sidebar changes, as of this release, the search bar is located above feature visualizations in Volume, Galaxy, Drivers, and Sentiment. This change helps make your Daylight experience more universal as you move from feature to feature.


Now, when you search for a concept or select it from a feature visualization, the concept appears in the search bar. If the concept you select is saved, the edit saved concept icon appears next to the search bar. If it is unsaved, a Save concept icon appears. At the end of the bar, view a summary of search results. As of this release, you still view search and concept details in the right sidebar.


For more information on changes coming to Daylight’s layout, read our article on Introducing a Single Sidebar to Daylight.


Added result_count field to the Get documents endpoint

With this release, we added a result_count field to the Get documents endpoint. This new field displays the number of documents that match any filter and search you applied when you called the Get documents endpoint.

Note: If a search is applied, only documents that contain exact or conceptual matches for that search are included in results.

For more on the Get documents endpoint, read its section in the API documentation.




Daylight | Cloud | 2020-08-29



Enhancements

  • Project Management: Introducing new tabbed left sidebar


Introducing new tabbed left sidebar

With this release, we move the filter documents, concept management, and configure visualization to a new tabbed left sidebar. This is the first step in a series of changes to the Daylight layout and workflow.


Over the next few releases, other elements of the current right sidebar will move out of the right sidebar:

  • Concept selection tool, and concept editor flyout

  • Search details and Matching documents

  • The concept search bar

This change helps increase parity across features, enhances concept management, and provides more space for visualizations.




Daylight | Cloud | 2020-08-15


Science

  • Science version 2.2.1: Improved handling of an English idiom with negation

Enhancements

  • Sentiment: View an error message when no sentiment suggestions are available

  • Sentiment: Sentiment concepts default to volume sorting

  • Sentiment: Sentiment build progress bars update dynamically


Fixes

  • Settings: When logged in with SSO, a password is not required to create an API token


Science version 2.2.1: Improved handling of an English idiom with negation

With this release, we update Daylight’s science to better handle an idiomatic English-language construction. Previously, when Daylight encountered a sentence with the word “could” followed by a comparative adjective, like “I couldn’t be happier!” it the resulting concept would be parsed as “not|en happy|en.”

English speakers understand that this phrase means it’s not possible to be more satisfied and is a positive construction, but Daylight interpreted it as a negative construction.


Now, when Daylight encounters a construction like “I couldn’t be happier!” it categorizes “could not” as a stopword, which is not included in analysis, and correctly parses the words as “happy|en.”

This change only affects English-language projects.


View an error message when no sentiment suggestions are available

Occasionally, Daylight projects may contain no sentiment suggestions. There are a few reasons this might happen, but this is most likely to occur in very small projects or projects that contain a high amount of boilerplate text.

When a Daylight project has no sentiment suggestions, an error message displays on the What do people feel strongly about? card in Highlights and in the Sentiment feature’s sentiment suggestions view.

We do not recommend creating Daylight projects with datasets that contain fewer than 300 verbatims. Read our article on Formatting your data for more information on best practices for Daylight uploads.


Sentiment concepts default to volume sorting

With this release, the suggested sentiment concepts in the Sentiment feature now default to sorting by volume, or number of exact matches, rather than by negativity. This produces a more mixed at-a-glance view of a project’s sentiment data.

Use the arrows next to Negative matches and Positive matches to sort sentiment concepts by strength of sentiment type.


Sentiment build progress bars update dynamically

Now, when you open the Sentiment feature as Daylight is analyzing a project’s sentiment, the progress bar you see on that page updates dynamically, without requiring you to reload the page.


When logged in with SSO, a password is not required to create an API token

Before, Daylight prompted users who were logged in to Daylight with their organizations’ SSO for a password when the user used the Settings page to create a long-lived API token.

Now, users who are connected to SSO don’t need to enter a password to create a long-lived API token.




Daylight | Cloud | 2020-08-01


Enhancements

  • Sentiment: Updates to document export


Fixes

  • Concept details: Matching documents section now displays up to 50 matches


Sentiment: Updates to document export

With this release, when you click a concept in the Sentiment feature and click Download more matches, the XLSX no longer shows summary rows for positive, negative and neutral matches. These summary rows showed Document-Level Sentiment information, so they were not accurate to new Concept-Level Sentiment data.


Concept details: Matching documents section now displays up to 50 matches

Now, when you select exact or conceptual matches in the Matching documents section of the Concept details pane, Daylight displays up to 50 matching documents of that type, if available. Previously, Daylight would only display matching documents from a total combined set of 50 matches, meaning that fewer matches were available if you selected only exact or conceptual.




Daylight | Cloud | 2020-07-25


We’re excited to introduce Concept-Level Sentiment analysis to Luminoso Daylight. Concept-Level Sentiment uses deep learning to intelligently detect sentiment for all concepts in every Daylight document.

Previously, Daylight detected sentiment in every document as a whole, but did not provide insight for each concept’s sentiment. With this major step forward, Daylight includes sentiment technology that is on par with the industry gold standard, all as part of the app – still with no coding or ontologies required. Head to Science Explained: Sentiment for more information on Concept-Level Sentiment in Daylight

Use Concept-Level Sentiment to:

  • Catch buried positive and negative sentiment items that other tools miss

  • View positive, negative, and neutral sentiment examples for each concept

  • Export from the Sentiment feature and see more sentiment examples for each concept


Concept-Level Sentiment in Projects

Daylight Cloud users have access to Concept-Level Sentiment on July 25, 2020. To access

Concept-Level Sentiment:

  • Click the Upgrade science button on the Project details card on the Highlights page.

  • Create a Daylight new project or add new documents to an existing project

  • Leave a project unopened for six months after July 25, 2020, generating an automatic science rebuild.

Concept-Level Sentiment is calculated after the core Daylight build. Since the time it takes Sentiment to build depends on dataset size, it may take several hours to complete large datasets. While Sentiment is building, you can’t access the Sentiment feature, though you can explore all other Daylight features.


To view Concept-Level Sentiment in an existing Daylight project

  1. Open the project you wish to rebuild with Concept-Level Sentiment. The project opens to the Highlights feature.

  2. Check to see if the project uses Document-Level Sentiment. If it does, you see a banner at the top of the page asking you to upgrade.

  3. Click Upgrade science on the Project details card on the Highlights page. A confirmation window appears, notifying you that your project will be rebuilt with upgraded science.

  4. Click Upgrade. Your project begins to upgrade. Note: Because Sentiment in Daylight is calculated after the core build is done, you may have to wait to access the Sentiment feature after the rest of the build.


To use the Concept-Level Sentiment Feature

  1. Open a fully built project that uses Concept-Level Sentiment. The Highlights feature opens.

  2. Take a look at the What concepts do people feel strongly about? card to view initial concept sentiment suggestions. Note: Because sentiment suggestions prioritize sentiment is strong and has high confidence scores, this card will display very negative suggestions.

  3. Open Sentiment by clicking Sentiment feature on the What concepts do people feel strongly about? card in Highlights or the Sentiment icon. The Sentiment feature opens. By default, the visualization displays sentiment suggestions, which are concepts that Daylight has identified as having especially strong sentiment. Note: Because sentiment suggestion concepts are prioritized by strong sentiment, they may appear polarized and usually include very little neutral sentiment.

  4. Use the arrows at the top of the concept list to sort concepts alphabetically, by number of exact matches, percent negative, or percent positive.

  5. Change the concepts displayed in the concept list using the options in Configure sentiment visualization.

  6. Click on an interesting concept to view examples of how the concept is used in contexts with negative, positive, and neutral sentiment. Note: If Daylight can't confidently determine that a concept was used in a positive, negative, or neutral context, it does not display a corresponding example.


To conduct deeper analysis in spreadsheet exports
  1. Apply filters as desired.

  2. Select a concept and click Download more matches to explore more matching documents. A spreadsheet downloads with documents based on:

  • The specific concept(s) you have selected

  • The filters you have selected.

  • The type of concept you have selected – Top concepts, Sentiment suggestions, or Saved concepts


  1. Open the spreadsheet. It opens automatically to the Sentiment distribution tab.

  2. Use the Sentiment distribution tab to:

  • Browse sentiment information for the total product

  • Skim sentiment information using color-coded concepts

  • View sentiment information for all concepts included in your filter


3. Use the Sentiment documents tab to view all documents that were included in your filter, and their associated sentiment information.


Other major Daylight updates

Some Concept-Level Sentiment changes occur outside the Sentiment feature:

  • Project management – Now, the Sentiment feature builds after the rest of the Daylight project. Optionally, receive emails that notify you when Sentiment is done calculating.

  • Highlights card – The What concepts do people feel strongly about? card now displays information about concepts, not documents, that communicate strong sentiment.

  • Update to build emails – Now, build emails reflect the build status for your overall project and for the sentiment feature.

  • Sentiment export – Now, if a search is applied at the time of download, the Sentiment export contains two tabs. The second tab contains Sentiment Documents. Sentiment export – Advanced concepts are now included in the sentiment export. The export represents the same document in multiple rows so that each concept-document pair displays correct sentiment.

  • Download Documents – The Download Documents export no longer displays sentiment information, since sentiment is now calculated on a concept-document pair basis, and not document-level basis.

  • Concept details pane – Now, there is no option to select Sentiment documents in the Documents section of the Concept details pane, since Daylight no longer calculates sentiment on the document level.


API: Concept-Level Sentiment

API users will also experience changes as part of Concept-Level Sentiment:

  • Sentiment information in the API is not available until sentiment finishes calculating

  • Now, the get_concept_sentiment endpoint returns sentiment_counts and sentiment_shares, rather than only has always returned sentiment_share which is the % of positive negative neutral docs -- a concept “purchase” would turn up the % of positive documents, etc

  • To update, use the rebuild endpoint in the API to rebuild an existing project without adding documents

  • Scripts which rely on knowing when the Sentiment build is done are going to have to be updated, as we will now be calculating sentiment after the regular build is complete

Additionally the newest version of the API client, version 2.0.1, now includes a wait_for_sentiment_build() method you can use if Concept-Level Sentiment is enabled in your Daylight Cloud Environment. Since the new Concept-Level Sentiment science is calculated after the core project build, you can use this new command in the same way the existing wait_for_build() method waits for the core project build to finish, wait_for_sentiment_build() waits for the Concept-Level Sentiment build to finish. Since Concept-Level Sentiment always finishes after the core project build, this is useful for scripts that use the API to build a project and then get sentiment data from it.



Daylight | Cloud | 2020-07-18


Enhancements

  • Daylight: Reordered feature list

  • API client: New features available


Daylight: Reordered feature list

Now, the feature icons in the sidebar in Daylight are also reorganized:

  • Highlights

  • Volume

  • Galaxy

  • Drivers

  • Sentiment


This change helps to guide users more intuitively through the application. Each Daylight feature pairs well with another feature for various stages of analysis. When initially discovering concepts, some users may prefer the visual Galaxy view, while others may prefer to look at the metric-oriented Volume feature. Some users might prefer to explore the spirit of a dataset through Sentiment, and others might consult quantitative Drivers metrics.

Along with this update, we also reorganize the cards on the Highlights feature. Now, the cards are ordered as follows:

  • Which concepts are most prevalent? — This card displays a snapshot of the Volume feature.

  • What are the largest clusters of conversation? —This card displays a snapshot of the clusters you view in the Galaxy.

  • What issues are affecting [score field]? —This card displays suggested drivers based on score fields included in your metadata.

  • What do people feel strongly about? — This card displays concepts Daylight detected as displaying strong sentiment


API Client: New features available

With this release, there are two new features available in the API client:

  • Now, when you create an instance of the API client, you can specify a timeout option. Before, if you made a call to the server with the API client that never returned, the script would wait forever. Now, if you set a timeout, it raises an exception if it has not received a response within the amount of seconds for which you specified the timeout.

  • If Concept-Level Sentiment is enabled in your Daylight Cloud environment, you can use a new wait_for_sentiment_build() method. Since new Concept-Level Sentiment science is calculated after the core project build, you can use this new command in the same way the existing wait_for_build() method waits for the core project build to finish, wait_for_sentiment_build() waits for the Concept-Level Sentiment build to finish. Since Concept-Level Sentiment always finishes after the core project build, this is useful for scripts that use the API to build a project and then get sentiment data from it. Note: If you use wait_for_sentiment_build() method in the updated API client before Concept-Level Sentiment is enabled for you, you will receive an error message.




Daylight | Cloud | 2020-07-04


Enhancement

  • Project management: Update to build emails


Fixes

  • Sentiment Concept List: Now displays more than 50 top concepts

  • Highlights: Copying a project now displays correct messages


Project management: Update to build emails

Now, when you build a project in Daylight and indicate that you would like to receive a confirmation email, the subject is updated from:


Luminoso Daylight Job Succeeded ([Project Name])


to


Explore your Luminoso Daylight project: [Project Name]


Additionally, the email’s body now reads:


The Luminoso Daylight project [Project Name], begun at [time/date], is ready to explore.

To view the project, go to: [url]

If you have any questions, send an email to support@luminoso.com.


Sentiment Concept List: Now displays more than 50 top concepts

Previously, when you selected Top concepts in Configure sentiment visualization and selected a number other than 50, the Sentiment Concept List would not be affected. Now, the Concept List accurately updates to reflect the concepts you selected.


Highlights: Copying a project now displays correct messages

Before, when you applied a filter in any analytic feature to narrow the set of documents, and then copied the project through the Highlights feature, a modal would appear and notify that you were only copying that narrow set of documents, not copying all documents as you would expect. This error was cosmetic, as the project copied with all documents as expected.

Now, the modal that appears when you apply a filter and then copy a project through Highlights notifies that you’re copying all your documents and gives you confirmation when the copy is complete.

How helpful was this article?

Thank you for your feedback!