How can we help you today?

Daylight getting started guide

Modified on: Thu, Oct 24, 2019 at 4:24 PM

Kickstart your Daylight experience with this guide.

Luminoso Daylight is a text analytics application powered by Quicklearn™, Luminoso’s proprietary natural language modeling system. You don’t need custom ontology libraries or data science experience to use Daylight. As soon as you create a project, Daylight immediately begins analyzing data. Use Daylight to enhance the value of your unstructured natural language text through intelligent, automated analysis and quantification.

Extract actionable insights from what your customers are saying with Daylight. Organizations use Daylight to analyze customer contact such as open-ended survey responses, product reviews, and support tickets. Using Daylight, they rapidly identify digital problems, understand concepts driving scores, and understand which aspects of their products and services hold the strongest sentiment.

Use this guide to familiarize yourself with the basic functionality you’ll need to begin discovery in your data. Once you’re done reading, check out some of the other resources on our help center. 

If you prefer to browse a hyperlinked version of this document, download the attached PDF. 

Log in to Daylight 

Luminoso staff create new workspaces and users in Daylight. You will receive an email after your Luminoso Daylight account and user profile are created with an invitation to your new workspace. The link in this email expires after seven days.  If your link expires or you can’t find the provisioning email after checking your spam folder, contact

Once you have the email from

  1. Click the link to access Daylight.
    The Daylight login page appears.

    Note: Use Google Chrome to access Daylight. Microsoft Edge is not a Daylight-compatible browser.  

  2. Enter your username, which is automatically set as your email address.

  3. Create a password and enter it a second time for validation. 

  4. Bookmark or save the login link for easy access.

Prepare the dataset for upload

Once you choose a natural language source, include all the information you’ll need in your analysis so you can get the best results from Daylight. Invest time now, since Daylight learns directly from the data you upload and data can’t be modified once it’s uploaded.  

Daylight’s Create a project feature only accepts comma-separated value (CSV) format with appropriately formatted columns. At a minimum, every uploaded data file must be a CSV file and have a column titled text.

Key vocabulary

  • verbatim is the conversational text component of the sample you have collected. 

  • document is a row of your source data, including the conversational text and any associated metadata.

  • Metadata is structured data that creates context for text responses. Metadata may include demographics, dates, scores, or product details. 

  • CSV file, or comma-separated value file, is a plain-text file format that is used to organize data. CSV files exclude styling information that is included in an Excel XLS or XLSX file format. You can create a CSV file from most spreadsheet editors. 

Supported languages and multilingual datasets 

Daylight includes 15 natural language processing pipelines that analyze unstructured text in one language at a time. For best results with a multilingual dataset, split your data into one language per CSV file. Then, select the appropriate language when uploading each file.


To add metadata, designate specific headers as you create your CSV file. These headers tell Daylight how to treat the contents of a column. Columns without a Daylight-compatible header will be ignored. 

Data type


Text (Required)

Column header: text

  • The natural language samples (verbatims) for Daylight to analyze

  • Only one text column is permitted per file

  • Each piece of text may not exceed 500,000 characters in length

  • I loved the free coffee and the room was very clean, but it smelled strongly of cigarette smoke.

  • I booked this room last-minute when my travel plans changed. The price was ok considering it was last-minute but it was way out of the way. 

  • We come to this hotel every year, and we appreciate the consistently top-notch experience!


Column header: title

  • Any identifier that is associated with text

  • Only one column permitted per data file

  • Isn’t analyzed as part of language sample, but can help organize text

  • Recent stay

  • Hotel visit

  • We’ll definitely be back!


Column header: string_[FieldName] 

Example: string_MemberLevel

  • Information that helps categorize text

  • Include as many string columns as needed

  • Can only filter fields in Daylight with up to 10,000 values

  • Helps filter your data by category





Column header: number_[FieldName] 

Example: number_MemberSince

  • Any numeric-only data associated with text

  • Include as many number columns as needed

  • Can optionally use in Driver feature





Column header: score_[FieldName] 

Example: score_OverallExperience

  • Any score or rating data associated with text

  • Include as many score columns as needed

  • Recommended for using the Drivers function




Column header: number_[FieldName] 

Example: date_CheckoutDate

ISO 8601 formatted dates:

  • 2018-04-10

  • 2018-04-10T13:45

  • 2018-04-10T13:45:00Z

US-style dates:

  • 04/10/2018

  • 04/10/2018 13:45:15

  • 4/10/18 1:45 PM

Multiple metadata values

string_prefix , string_prefix

If you want to add multiple values for one type of metadata, you can: 

  • Use the string_prefix column so each document can have up to two values in the "prefix" metadata field

  • Use a pipe character | to apply multiple metadata values to a single document row

  • Note: Both options produce metadata

  • Series 1|Series 2

Upload the dataset to create a new project

Before you can dive into your data, you’ll need to upload it to Daylight. Once you upload your dataset, Luminoso begins extracting top concepts. 

  1. On the Projects page, click New Project.
    The Create project page appears.

  2. Click Choose dataset.
    A file explorer appears.

  3. Select the dataset you want to upload and click Open or drag and drop the dataset you want to upload onto the Create a project page.
    A preview of your dataset appears in the Create project page. If you attempt to upload a file that isn’t saved as a .csv or doesn’t include a text header, you see an error message.

  4. Complete the remaining fields on the Create project page:

    • Select project language: Select your dataset’s language from the menu.

    • Name your project: Type a name for your project.  

    • Describe your project: Add a description for your project. This is optional. 

  5. Click Create project. If you want to be notified by email when your project is created, select Send me an email when this project is finished building.
    The upload page appears as Daylight begins analyzing your data.
    Warning: Stay on the upload page until a banner appears confirming that your dataset uploaded successfully. If you exit this page before your dataset is done uploading, the upload process fails.

  6. Wait on the Create project page until your project is done calculating and select Click here to enter your new project, or return to the Projects page to work in a different project.

Start with the Highlights feature 

The Highlights feature is a starting point to understand the contents of your project. In this feature, orient yourself and start navigating the primary questions you can answer using Daylight:

  • Theme detection – What are people talking about?

  • Emotional analysis – What are the overall and specific sentiments?

  • Differential analysis – What differences can Daylight identify in your metadata?

  • Score drivers – What is driving your customer experience up or down?

You’ll first view Daylight’s answers to these questions in Highlights, and then engage deeply with each data perspective as you move through the Volume, Sentiment, Drivers, and Galaxy features. 

  1. Display Highlights: In your Projects list, click on the name of the project you want to view.
    The Highlights feature appears.

  2. Use the top section of the page to manage your project:

    • Edit name & description — Click and type here to update your project’s title and description. 

    • Project details  View who created your project and when they created it. You can share or delete your project in this section. 

    • How many documents are in this project?  View how many documents are in your project. You can upload more documents or make a copy of your project here. 

    • What metadata do my documents have?  View the amount and type of metadata your project includes. 

  3. Make immediate observations about your data in the Insights from your project section: 

    • Which concepts are most prevalent?  View which concept groups appear most frequently in your dataset. For a deeper look at prevalence, click Volume feature to access the volume view or select the volume iconin the sidebar.

    • What do people feel strongly about?  View a preview of some of the concepts in your dataset that provoked a strong reaction. For a deeper look at sentiment, click Sentiment feature or select the sentiment icon in the sidebar.

    • What issues are affecting my scores?  View how certain concepts affect scores for your project. If you did not include a column titled score in your metadata, this section is blank. If you have multiple saved scores, you can toggle between by selecting a field with score data in the upper right of the card. For a deeper look at your score drivers, click Drivers feature or select the drivers iconin the sidebar.

    • What are the largest clusters of conversation?  View the largest concept groups that Daylight identified in your project. Concept groups are colored to help you identify them at a glance. For a deeper look at your concepts, click Galaxy feature or select the galaxy iconin the sidebar. 

Learn the universal tools

Each feature, except for Highlights, shares common tools that help you manage your project, filter your documents and view the specific document information associated with concepts. These tools are visible each feature.

An image of the Volume feature with the Filter documents, Download & share this data, and Concept details sections highlighted.

Filter documents

When you view the Volume, Sentiment, Drivers, or Galaxy features, you see the Filter documents pane on the left of your screen. Select or deselect the filters to change what data you see in the feature view. If you select a filter, it remains consistent across features. This is also true if you share a direct link to the page you’re viewing with another Daylight user.

Download & share this data

You also see the Download & share this data section, where you can manage your project. Select Download XSLX to download an Excel spreadsheet that contains your data with formatting applied or click Share to copy a direct link to the project feature (Volume, Sentiment, Drivers, or Galaxy) that you are viewing to your clipboard. 

Concept details

Concept details is the final consistent section that appears in the Volume, Sentiment, Drivers, and Galaxy features. In this section, you can select a concept by typing in the search bar. Any time you click on a concept, the concept also appears in the Concept details pane. When you select a concept, it remains selected across features. 

The number of exact, conceptual, and total matches are automatically quantified for your selected concept in the Match counts section. View concepts that correlate to your selected concepts and filter concepts by exact or conceptual match in the Top matches section. Select Sentiment matches to view the concept’s use in positive and negative sentiment documents. 

Click Download to download the data you’re currently viewing, including any filters you’ve applied. Click create project to create a Daylight project that includes only the data subset you’re viewing. Quicklearn™ then recalculates conceptual associations in the smaller dataset, allowing you to view how concepts interact in large and small data samples.

See how each concept is used in context in the Matching documents section. Scroll to skim the relevant document sections, or click Read more to expand a specific document. 

Volume feature: Quantify concepts

Gain quick insight into concept representation across the dataset. Volume automatically quantifies how frequently concepts are referenced in the project using the exact and conceptual matching identified by Quicklearn™.   

Daylight's Volume feature, displaying data from a sample project.

  1. Display Volume: Click the volume icon in the sidebaror select Volume feature on the Highlights page.
    The Volume feature appears.
    Browse the concepts. If you’re viewing a newly created project, no filters are applied from your project’s metadata in the
    Filter documents pane and the sorting filters are defaulted to their presets.

  2. Use the sorting filters at the top of the page to change how your concepts are displayed:

    • Select concepts to compare — Select Top concepts or Saved concepts, if you have them, from the menu. You can also select the number of Top concepts you want to view. 

    • Select match type  Select Total matches or Exact matches only from the menu. 

    • Choose sort order — Select the sort order you want:

      • Default (Most prevalent) — Sorts by the most uniquely represented concepts in the dataset compared to everyday conversation, raising highly represented concepts and pushing down common terms.

      • Concept name  Sorts based on the first letter in concept.

      • Match count  Sorts by raw frequency of either Total matches or Exact matches that you selected in Select match type.

    • Break down by field  Select from the menu. This section draws on metadata, so the options depend on your dataset. You may be able to select additional options once you have selected a field. For instance, if you selected a Date option, you may be able to select Month or Quarter as additional options. 

  3. Click the save concept iconto save a concept. If you haven’t saved any concepts yet, every concept displays the save concept icon next to it. 

Sentiment feature: Identify positive, negative, and mixed sentiment concepts  

Use Sentiment to learn about concepts’ association with types of emotion. Sentiment determines how often a concept is included in positive or negative documents and correlates the concept to positive or negative emotion across the project. Sentiment calculates using the full text of a document, so concepts may be incorrectly labelled in some instances. Use the percentage counts in this feature as a general indication. 

  1. Display Sentiment: Click the sentiment icon in the sidebaror select Sentiment feature on the Highlights page.
    The Sentiment feature appears.

  2. Browse the data and use the sorting filters at the top of the page to change how your concepts are displayed:

    1. Select concepts  Select Top concepts, Sentiment suggestions, or Saved Concepts, if you have them, from the menu. You can also select the number of topics you want to view. 

    2. Choose sort order  Select your preferred option from the menu. 

  3. If you see filter options in the Filter documents section on the left of your screen, you can also filter with those options. 

  4. View an overview of all the documents you chose to filter in the bar at the top of the page. This overview bar updates depending on your filter selection criteria.

Drivers feature: Analyze mixed datasets

In the Drivers feature, view how your structured numeric data relates to unstructured natural language concepts and reveals why scores increase or decrease. See how concepts in subsets of your data raise or lower overall satisfaction scores for your product. The graph allows you to identify trends in a glance, and the filtering criteria allow you to laser-focus for deeper insights. 

  1. Display the Drivers feature: Click the Drivers icon in the sidebaror select Drivers feature on the Highlights page. 

  2. Browse the concepts and use the sorting filters to change how your concepts are displayed:

    1. Select concepts  Select Suggested drivers or Saved concepts, if you have them, from the menu. 

    2. Select score field  Select from the available scores. The contents of this menu will depend on the score and number data that you created when you formatted your CSV file before uploading it. 

  3. If you see filter options in the Filter documents section on the left of your screen, you can filter using those options. The contents of this section should match the options in the Select score field menu. The average score line, which runs horizontally across the graph, updates as you change your filter criteria.
    Note: You can’t use the value you selected as a score as a filter.

  4. Use the cursor to zoom in and out on the concepts you see in the graph. 

  5. Click on a concept’s colored dot to see more details about it.
    The concept opens in the
    Concept details pane. 

Drivers: Trend Analysis

Beginning in September 2019, Daylight users may access a Drivers: Trend Analysis, a premium feature that uses comparative scatterplots to examine how drivers change over time. Use this feature to: 

  • Discover directional changes in drivers over time

  • Compare period over period, or year over year

  • Decide exactly which concepts to visualize for easy comparison

  • Consult a concept list with key metrics

Want to request access to the premium feature? Please contact your Customer Success Manager. 

To compare drivers over time

  1. Open Daylight and select the Drivers feature.

  2. Select a field from the Select a score field menu. 

  3. Choose Autosuggest or Saved concepts from the Which concepts to visualize section. Autosuggest provides concepts that strongly influence your score.

  4. Click Select date field to compare periods and select the 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. 
    Note: In Drivers: Trend Analysis, you can view up to 15 concepts, reducing scatterplot density. 

  5. Refine the date range in the top scatterplot to a narrow interval. The bottom scatterplot responds and displays the previous period or year over year. Each scatterplot displays the most relevant autosuggested or saved concepts for that period of time.

If you share a direct URL to a project’s Drivers scatterplot, the URL reflects:

  • Any filters you selected

  • The score field you selected

  • Whether concepts are saved or autoselected 

  • The top 15 concepts by average score ascending

Galaxy feature: Visualize associations

Use the Galaxy feature to see how strong concept relationships are in the context of your entire project. The size of a concept in the visualization indicates how relevant it is in the project and related concepts themes cluster together. Since the view is dynamic, you can drag concepts in the space to realign the axis.  Highly related concepts group more closely while less related concepts rotate away. 

  1. Display the Galaxy: Click the Galaxy icon in the sidebaror select Galaxy feature on the Highlights page.
    The Galaxy opens.

  2. Use the Galaxy as a visual overview of your data.  Click, hold, and drag a concept to rotate the Galaxy and view the 150 dimensions the Galaxy contains. As soon as you stop holding the concept, the Galaxy collapses and displays as two-dimensional again, although it is now reoriented.

  3. Click the reset buttonto restore the Galaxy to its default orientation.

  4. Click the X and Y axis icons to orient the Galaxy to around specific saved concepts. If you haven’t saved any concepts yet, you can’t use this option.

    • Once either the X or Y axis are set the grey axis toggle buttonturns blue. Click the button to turn on the axis label.  When selected, the button is green. 

  5. View the concepts in the Select concepts pane. If you haven’t saved any concepts yet, you see suggested relevant concepts that Daylight identified when you created your project. Daylight automatically suggests groupings of related concepts and assigns colors to demonstrate association.

  6. If you’re viewing a new project, select Keep selected to save all suggested concepts or Dismiss to clear them.  To save a mix, clear the check boxes to dismiss the concepts you don’t want to keep.  Click Keep selected when you’re done.
    Note: If you select Dismiss, you can view all suggested concepts again by clicking the three dotsat the top of the Select concepts pane.

  7. Select a concept in the Galaxy or the Select concepts pane to view its concept details.
    The concept appears in the
    Concept details pane and displays as orange in the Galaxy while related concepts turn blue and unrelated concepts turn gray.

  8. Click thenext to the concept's name to deselect it.
    The concept disappears from the
    Concept details pane and Galaxy’s colors return. 

Edit a concept in the Galaxy feature

  1. Hover over a concept in the Select concepts pane and click the pencil iconto edit that concept.
    Note: Editing a concept doesn’t change its size or location in the Galaxy. 

  2. Click the pencil icon in the Name field to update the concept’s name. 

  3. Type in the Concepts field to start creating a compound concept. When your desired concept appears,  click theicon to add that concept.

  4. Select a color to assign a new color to the concept.
    Your changes save immediately.

  5. Click Done to exit the concept editor. 

Create a new project from selected data

After you spend some time with your data, consider leveraging Daylight’s learning ability to gain new insights from a smaller data set. When you create a new project from filtered data, you include only the data you selected in your filters. Quicklearn™ then recalculates the association between concepts, giving you new calculations that are displayed in the Volume, Sentiment, Drivers, and Galaxy features. The new project retains the metadata you added when you created the original project. 

The Create project from selected matches option is available in every feature, but the Galaxy is a helpful place to do it. 

  1. Filter your dataset to show the subset you want to analyze. 

  2. Click Create project.
    A Create project from matching documents window appears. 

  3. Add a name your project if you don’t want to keep the automatic one and optionally add a description. 

  4. Click Create project. Select Send me an email when this project is finished building if you’d like a notification when the project is uploaded.
    Create project button turns gray and the project begins uploading.

  5. Stay in the window until it changes to notify you that your new project is being built.

  6. Click Back to project list to view your other projects or click Close  to return to your original project. 

  7. Access your new project from the project list when it’s done uploading. 


Did you find it helpful? Yes No

Send feedback
Sorry we couldn't be helpful. Help us improve this article with your feedback.