Implement Text Analytics for Theme Explorer only

Important: Normally, Medallia Text Analytics implementations include configuration for both themes and topics. For these implementations, follow the steps in Implement Text Analytics.
If you must implement Text Analytics for Theme Explorer only, complete the following steps:
  1. Navigate to the Reporting > Text Processing > Global Text Analytics Settings > Settings screen, and verify that these settings are properly set (or change the settings if they are not):
    • Marking Surveys Enabled is on.
    • Automatic Processing Enabled is on.
      Note: By default, this property is turned off on sandboxes. For more information, see Sandboxes.

  2. Navigate to the Reporting > Text Processing > Topic & Theme Tagging > Settings screen, and verify that these settings are properly set (or change the settings if they are not):

    • Topic Alert Blocking Enabled is on.

    • Automatic Tagging Enabled is on.

    • If the company is using one or more languages with sentiment support, SENTIMENT_SUPPORT is selected for the TextAnalyticsVersion property. For more information, see Text Analytics supported languages.

      Note: After you enable SENTIMENT_SUPPORT, you cannot change the option back to TOPICS_ONLY.

    • CalculateImpactForLowSample is on.

    • Enable MATCH processing is on.
    • Use spellchecking is off.
  3. Specify a main score.

    The main score should be the key customer loyalty metric that your company uses throughout Experience Cloud. NPS and average overall satisfaction are common main scores.

    1. Navigate to the Company > Profile > Company Settings screen.
    2. Specify the MainScoreField property by selecting the name of the K-field you want to use as the main score.
      Important: Even if there is only one program in your environment today, you should create a K-field to store the value of the Q-field instead of specifying the Q-field directly. Using a K-field helps accommodate future expansions.
    3. Click Save.

  4. Create one or more Tag pools.

    1. Complete the prerequisite steps described in Implement Text Analytics.
    2. In Classic Setup, navigate to the Reporting > Topic & Theme Tagging > Auto Tagging Pools screen.
    3. Click New to create a new tag pool.
    4. In the Name property, give the tag pool a descriptive name, such as [COMPANY NAME] Call Center Feedback.
      Tip: The Comment Set filter in Theme Explorer displays the name of the tag pools, so make sure the name is appropriate.
    5. Click Save.
      Note: You might see a warning message at the top of the page, instructing you to assign a unit group or Q-fields. Ignore this message. it will disappear after you finish configuring the tag pool.
    6. If you want to limit which roles can administer the tag pool, complete the following steps.
      Note: Limiting tag pool administration does not affect reporting.
      1. Turn on the Enable tag pool topic set access by role property, and then click Save.

        This causes the MemberRoles property to appear.

      2. In the MemberRoles property, select the roles that can administer the selected tag pool.
    7. In the MemberUnitGroups property, choose the highest level unit groups that contain comments from the programs you want to pull from.
      • If you are creating only one tag pool for all comments, choose All <company> Units.
      • If you are creating a tag pool for comments that belong to a specific program only, choose the highest-level unit group associated with that program.
    8. In the MemberSurveyFields property, choose the comment Q-fields from which you want to retrieve comments.

      If you have multiple tag pools, your Q-fields do not need to be unique. Text Analytics processes comments from the specified unit groups for a given Q-field.

      Restriction: The alternative sets of selected fields must have an Encoding property value of TEXT or TRANSLATABLE. Because of this restriction, investigate the alternative set of any fields you want to add. For example, do not add a field that returns an integer. For more information about the Encoding property, see Alternative sets.
      Restriction: Do not use K-fields and A-fields in tag pools as they may cause performance issues. Use only Q-fields and E-fields.

      Newly added fields are included immediately in Text Analytics processing as new records are received.

      As you add fields to the word group, a message may appear below the new word group's Name that "The following fields are waiting to be processed:...." This message refers to historical processing only, and does not require additional action for new record processing. If you later modify any of these fields, records associated with those fields are marked for automatic reprocessing.

    For more detailed information about this process, see Creating a tag pool.

  5. Configure machine translations if you need the system to process comments in languages other than English.

    Machine translation is the use of software to translate text. Medallia uses SYSTRAN, Amazon Translate, and Google Translate for machine translations. Users with certain permissions can edit comments on the Responses Form report that have been machine translated. Enable this feature if your company requests it. For more information, see Translating comments.

  6. Optionally, configure sentiment:

    1. Navigate to the Reporting > Text Processing > Topic & Theme Tagging > Settings screen.

    2. Change TextAnalyticsVersion to SENTIMENT_SUPPORT.

      Important: Once you change the TextAnalyticsVersion property to SENTIMENT_SUPPORT, you cannot undo this action and go back to TOPICS_ONLY.

    3. Click Save.

      After saving, you see boxes populated with the Q-fields from your tag pool (starting halfway down the page).

    4. For questions with an inherently positive or negative sentiment, apply that sentiment to the question fields. Text Analytics takes the default sentiment into account when calculating sentiment for text entered in these fields.

      • Move any Q-fields with a positive context (such as, Tell us how we exceeded your expectations) into the MemberPositiveSurveyFields box.
      • and move any Q-fields with a negative context (such as, Tell us what we could have done better) into the MemberNegativeSurveyFields box.

      Fields not moved in either box are assumed to have neutral sentiment by default.

    5. Navigate to the Reporting > Text Processing > Topic & Theme Tagging > Sentiment screen.
    6. To force neutral sentiment for specific channels or fields, set one or more of the following properties and then click Save.
      • Neutral sentiment for Agent side of conversational data — When on, sentiment for the agent side of all conversational data, such as data in the q_speech_comment and q_conversational_transcript_comment fields, is calculated as neutral.
      • Neutral sentiment for Customer side of conversational data — When on, sentiment for the customer side of all conversational data is calculated as neutral.
      • Comment Fields for which Sentiment is Disabled — Fields in the ride-side box are forced to have neutral sentiment. For example, you might want case notes fields to be neutral.
        Note: Fields selected in the Comment Fields for which Sentiment is Disabled property override settings for those fields in the MemberPositiveSurveyFields and MemberNegativeSurveyFields properties.

    7. Navigate to the Reporting > Text Processing > Global Text Analytics Settings > Settings screen.

    8. For each of the languages you are processing with Text Analytics, turn on the Use Medallia AI Sentiment Model property if it appears. See Text Analytics supported languages for the list of languages with sentiment processing available.

    9. Click Save.
      Note: Immediately after you save the page, the sentiment analysis process is applied to all incoming surveys.

    10. (Optional) Navigate to the Reporting > Text Processing > Sentiment Reporting screen to alter the default reporting options that apply to sentiment. See Properties of the Sentiment Reporting screen, below, for a description of each reporting option.

    11. Validate your configuration and initiate comment processing after the initial setup process is complete. Make sure to choose a processing option that applies sentiment. See Text Analytics processing and initialization for more information.

    For more detailed information, see Configuring sentiment.

  7. Configure Theme Explorer, as described in Configure Theme Explorer.