{"id":21209,"date":"2019-05-27T07:07:40","date_gmt":"2019-05-27T06:07:40","guid":{"rendered":"https:\/\/developer.kore.ai\/v8-0\/?p=21209"},"modified":"2021-03-25T17:13:41","modified_gmt":"2021-03-25T17:13:41","slug":"sentiment-management","status":"publish","type":"post","link":"https:\/\/developer.kore.ai\/v8-0\/docs\/bots\/advanced-topics\/sentiment-management\/","title":{"rendered":"Sentiment Management"},"content":{"rendered":"<section class=\"l-section wpb_row height_auto\"><div class=\"l-section-h i-cf\"><div class=\"g-cols vc_row type_default valign_top\"><div class=\"vc_col-sm-12 wpb_column vc_column_container\"><div class=\"vc_column-inner\"><div class=\"wpb_wrapper\">\r\n\t<div class=\"wpb_text_column \">\r\n\t\t<div class=\"wpb_wrapper\">\r\n\t\t\t<p><strong><span style=\"font-weight: 400\">Emotion tones are critical indicators in understanding the attitudes and opinions of users interacting with the bots. <\/span>Sentiment Management<\/strong> allows the developer to define and trigger events based on the user\u2019s emotion or sentiment.<\/p>\n<p><strong>Notes<\/strong>:<\/p>\n<ul>\n<li>This feature was introduced in ver 7.0.<\/li>\n<li>This feature is not supported in all languages, <a href=\"\/docs\/bots\/how-tos\/multi-lingual-bot-behavior\/#Feature_Support\" rel=\"noopener noreferrer\" target=\"_blank\">see here for details<\/a>.<\/li>\n<\/ul>\n<p><span style=\"font-weight: 400\"> Negative emotion scenarios like anger or disgust would typically be considered for transferring the conversation to a live agent<\/span>.<\/p>\n<p>The Natural Language Processing (NLP) interpreter can parse user utterances for specific words and phrases, and then provide an average tone score based on the connotation, word placement, and any added modifiers. (<a href=\"\/docs\/bots\/advanced-topics\/working-with-tone-processing\/\">See here for more on Tone Analysis<\/a>)<\/p>\n<p>The tone or sentiment scores can be stored as context and used to drive the flow of a dialog task via conditional transition statements. You can use these scores to steer user-bot conversations or seamlessly invoke escalation to a live agent.<\/p>\n\r\n\t\t<\/div>\r\n\t<\/div>\r\n<div class=\"w-separator size_small with_line width_default thick_1 style_solid color_border align_center\"><div class=\"w-separator-h\"><\/div><\/div>\r\n\t<div class=\"wpb_text_column \">\r\n\t\t<div class=\"wpb_wrapper\">\r\n\t\t\t<h2><span class=\"ez-toc-section\" id=\"Configuration\">Configuration<\/span><\/h2>\n<p>You can define multiple sentiment events from the <b>Intelligence<\/b><span style=\"font-weight: 400\"> under <\/span><b>Natural Language<\/b>.<\/p>\n<p>Use <b>New Event<\/b> to define an event to capture the user emotion.<\/p>\n<p><a ref=\"magnificPopup\" href=\"\/wp-content\/uploads\/sites\/16\/sa-blank.png\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-21219\" src=\"\/wp-content\/uploads\/sites\/16\/sa-blank.png\" alt=\"\" width=\"820\" height=\"461\" srcset=\"https:\/\/kore-wordpress.s3.us-east-2.amazonaws.com\/developer.kore.ai\/wp-content\/uploads\/sites\/16\/20221201100041\/sa-blank.png 820w, https:\/\/kore-wordpress.s3.us-east-2.amazonaws.com\/developer.kore.ai\/wp-content\/uploads\/sites\/16\/20221201100041\/sa-blank-300x169.png 300w\" sizes=\"auto, (max-width: 820px) 100vw, 820px\" \/><\/a><\/p>\n\r\n\t\t<\/div>\r\n\t<\/div>\r\n\r\n\t<div class=\"wpb_text_column \">\r\n\t\t<div class=\"wpb_wrapper\">\r\n\t\t\t<p><span style=\"font-weight: 400\">Following parameters can be configured for a sentiment event:<\/span><\/p>\n<ul>\n<li style=\"font-weight: 400\"><b>Event Name<\/b><span style=\"font-weight: 400\"> &#8211; Name for the Event.<\/span><\/li>\n<li style=\"font-weight: 400\"><b>Event Trigger<\/b><span style=\"font-weight: 400\"> &#8211; Defines how often the sentiment should be checked. It can be set to: <\/span>\n<ul>\n<li style=\"font-weight: 400\"><b>On Task Completion<\/b><span style=\"font-weight: 400\"> &#8211; Sentiment will be checked only after completion of a task (dialog, action, alert and information task)<\/span><\/li>\n<li style=\"font-weight: 400\"><b>After Every User Message<span style=\"font-weight: 400\"> &#8211; Sentiment will be checked after every message from the end user. The event will be evaluated before proceeding with the conversation using the incoming utterance.<\/span><\/b><\/li>\n<\/ul>\n<\/li>\n<li style=\"font-weight: 400\"><strong>Emotion Configurations<\/strong><span style=\"font-weight: 400\"> &#8211;<\/span>\n<ul>\n<li style=\"font-weight: 400\">Select the required emotions to be captured from a list of six tones &#8211; <span style=\"font-weight: 400\">angry, <\/span><span style=\"font-weight: 400\">disgust, <\/span><span style=\"font-weight: 400\">fear, <\/span><span style=\"font-weight: 400\">sad, <\/span><span style=\"font-weight: 400\">joy, and <\/span><span style=\"font-weight: 400\">positive.<\/span><\/li>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">Select if the tone should be considered at the &#8216;Session&#8217; level or &#8216;Message&#8217; level<\/span>\n<ul>\n<li style=\"font-weight: 400\"><strong>Session level<\/strong><span style=\"font-weight: 400\"> tone value is a consolidated tone value across all user messages in a conversation session.<\/span><\/li>\n<li style=\"font-weight: 400\"><strong>Message-level<\/strong><span style=\"font-weight: 400\"> tone value is a tone value calculated for a given message from the user.<\/span><\/li>\n<\/ul>\n<\/li>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">Define the range to be considered for each of these tones, the range can be between -3 to +3<\/span><span style=\"font-weight: 400\">. <\/span>(<a href=\"\/docs\/bots\/advanced-topics\/working-with-tone-processing\/\">See here for more<\/a> on Tone Analysis)<\/li>\n<li style=\"list-style-type: none\">When multiple emotions are selected, the event will be triggered when ALL the tone rules are met. In case you want the event to be triggered when any one tone rule is met, add them as separate rules.<\/li>\n<li style=\"font-weight: 400\"><b>Event Configuration<\/b> &#8211; The result of the event trigger could be either to <b>Run a Dialog<\/b> or <b>Run a Script.<\/b><a ref=\"magnificPopup\" href=\"\/wp-content\/uploads\/sites\/16\/sa-eventconfig.png\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-21220\" src=\"\/wp-content\/uploads\/sites\/16\/sa-eventconfig.png\" alt=\"\" width=\"820\" height=\"461\" srcset=\"https:\/\/kore-wordpress.s3.us-east-2.amazonaws.com\/developer.kore.ai\/wp-content\/uploads\/sites\/16\/20221201100040\/sa-eventconfig.png 820w, https:\/\/kore-wordpress.s3.us-east-2.amazonaws.com\/developer.kore.ai\/wp-content\/uploads\/sites\/16\/20221201100040\/sa-eventconfig-300x169.png 300w\" sizes=\"auto, (max-width: 820px) 100vw, 820px\" \/><\/a><\/li>\n<\/ul>\n<\/li>\n<\/ul>\n\r\n\t\t<\/div>\r\n\t<\/div>\r\n<div class=\"w-separator size_small with_line width_default thick_1 style_solid color_border align_center\"><div class=\"w-separator-h\"><\/div><\/div>\r\n\t<div class=\"wpb_text_column \">\r\n\t\t<div class=\"wpb_wrapper\">\r\n\t\t\t<h2><span class=\"ez-toc-section\" id=\"Event_Flow\"><span style=\"font-weight: 400\">Event Flow<\/span><\/span><\/h2>\n<p>Emotion tones are continuously updated whenever a message received from the users and as such the sentiment events are also continuously evaluated. When an event\u2019s criteria are met, the platform will trigger the defined behavior.<\/p>\n<ul>\n<li>If the configuration used is to \u2018<strong>Initiate task<\/strong>\u2019, then the current task is discarded and bot switches to the new task according to the event configuration.\n<ul>\n<li>Any other implicitly paused tasks will also be discarded.<\/li>\n<li>Tasks that are kept on hold using Hold &amp; Resume settings will be resumed as per Hold &amp; Resume configuration.<\/li>\n<li>If the dialog selected to be triggered for the sentiment event is not available for any reason, then a standard response is displayed. Refer to the standard response with the title \u2018<em>Dialog task required for conversation is not available<\/em>\u2019 for more information. (<a href=\"\/docs\/bots\/bot-intelligence\/default-dialog\/#Managing_Standard_Responses\" target=\"_blank\" rel=\"noopener noreferrer\">more on standard responses<\/a>).<\/li>\n<\/ul>\n<\/li>\n<li>If the configuration used is to \u2018<strong>Run script<\/strong>\u2019, then the platform will execute the script and continue with the task execution. In case of any errors executing the script associated with the sentiment event, then a standard response is displayed. You may refer to the standard response titled \u2018<em>Error in continuing the conversation due to incorrect bot definition<\/em>\u2019 for more information. (<a href=\"\/docs\/bots\/bot-intelligence\/default-dialog\/#Managing_Standard_Responses\" target=\"_blank\" rel=\"noopener noreferrer\">more on standard responses<\/a>).<\/li>\n<li>In case of a conflict between a sentiment event and direct intent invocation by the user, sentiment event is given precedence.<\/li>\n<li>When tone criteria for two or more sentiment events are satisfied at the same instance, then the platform will prefer the sentiment event with the highest order of precedence used in defining the events.<\/li>\n<\/ul>\n<h5>Execution Flow for Universal Bots<\/h5>\n<ul>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">Events configured at universal bot will be honored over the events defined in the child bots<\/span><\/li>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">If an event at universal bot is qualified, then the corresponding behavior will be triggered<\/span><\/li>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">If an event at universal bot is not qualified or not defined, then the events defined for the child bot that the user is interacting with will be evaluated and triggered if qualified. <\/span><\/li>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">If no child bot is being executed, then child bot events will not be evaluated.<\/span><\/li>\n<\/ul>\n\r\n\t\t<\/div>\r\n\t<\/div>\r\n<div class=\"w-separator size_small with_line width_default thick_1 style_solid color_border align_center\"><div class=\"w-separator-h\"><\/div><\/div>\r\n\t<div class=\"wpb_text_column \">\r\n\t\t<div class=\"wpb_wrapper\">\r\n\t\t\t<h2><span class=\"ez-toc-section\" id=\"Reset_Tone\">Reset Tone<\/span><\/h2>\n<p><span style=\"font-weight: 400\">By default, sentiment values are reset at the beginning of every user conversation session.<\/span><\/p>\n<p><span style=\"font-weight: 400\">Apart from the beginning of the conversation session, the platform resets the sentiment values (i.e. tone scores) once the associated events are triggered. The reset behavior is based on the type of event trigger:<\/span><\/p>\n<ul>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">If a Script is run, then the values would be reset after successful execution of the script.<\/span><\/li>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">In case of a Dialog task being triggered, the values are transferred to the new Dialog task&#8217;s (triggered by the sentiment event) context and reset in the original global context.<\/span><\/li>\n<\/ul>\n\r\n\t\t<\/div>\r\n\t<\/div>\r\n<div class=\"w-separator size_small with_line width_default thick_1 style_solid color_border align_center\"><div class=\"w-separator-h\"><\/div><\/div>\r\n\t<div class=\"wpb_text_column \">\r\n\t\t<div class=\"wpb_wrapper\">\r\n\t\t\t<p><strong>Recommended Reading<\/strong>:<\/p>\n<p>You might want to read about Tone Analysis, <a href=\"\/docs\/bots\/advanced-topics\/working-with-tone-processing\/\" rel=\"noopener noreferrer\" target=\"_blank\">refer here for details<\/a>.<\/p>\n\r\n\t\t<\/div>\r\n\t<\/div>\r\n<div class=\"w-separator size_small with_line width_default thick_1 style_solid color_border align_center\"><div class=\"w-separator-h\"><\/div><\/div>\r\n\t<div class=\"wpb_text_column \">\r\n\t\t<div class=\"wpb_wrapper\">\r\n\t\t\t<div class=\"w-post-elm post_navigation layout_simple inv_false\">\n\t<a class=\"post_navigation-item order_first to_prev\" href=\"https:\/\/developer.kore.ai\/v8-0\/docs\/bots\/bot-intelligence\/interruption-handling-context-switching-intents\/\"><\/p>\n<div class=\"post_navigation-item-arrow\"><\/div>\n<div class=\"post_navigation-item-meta\">Previous<\/div>\n<div class=\"post_navigation-item-title\"><span>Dialog Management<\/span><\/div>\n<p>\t<\/a><br \/>\n<a class=\"post_navigation-item order_second to_next\" href=\"https:\/\/developer.kore.ai\/v8-0\/docs\/bots\/bot-intelligence\/default-dialog\/\"><\/p>\n<div class=\"post_navigation-item-arrow\"><\/div>\n<div class=\"post_navigation-item-meta\">Next<\/div>\n<div class=\"post_navigation-item-title\"><span>Default Conversations<\/span><\/div>\n<p>\t<\/a><\/div>\n\r\n\t\t<\/div>\r\n\t<\/div>\r\n<div class=\"w-separator size_small with_line width_default thick_1 style_solid color_border align_center\"><div class=\"w-separator-h\"><\/div><\/div><\/div><\/div><\/div><\/div><\/div><\/section>\n","protected":false},"excerpt":{"rendered":"Emotion tones are critical indicators in understanding the attitudes and opinions of users interacting with the bots. Sentiment Management allows the developer to define and trigger events based on the user\u2019s emotion or sentiment. Notes: This feature was introduced in ver 7.0. This feature is not supported in all languages, see here for details. Negative...","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[15],"tags":[],"class_list":["post-21209","post","type-post","status-publish","format-standard","hentry","category-advanced-topics"],"_links":{"self":[{"href":"https:\/\/developer.kore.ai\/v8-0\/wp-json\/wp\/v2\/posts\/21209","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/developer.kore.ai\/v8-0\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/developer.kore.ai\/v8-0\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/developer.kore.ai\/v8-0\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/developer.kore.ai\/v8-0\/wp-json\/wp\/v2\/comments?post=21209"}],"version-history":[{"count":22,"href":"https:\/\/developer.kore.ai\/v8-0\/wp-json\/wp\/v2\/posts\/21209\/revisions"}],"predecessor-version":[{"id":26290,"href":"https:\/\/developer.kore.ai\/v8-0\/wp-json\/wp\/v2\/posts\/21209\/revisions\/26290"}],"wp:attachment":[{"href":"https:\/\/developer.kore.ai\/v8-0\/wp-json\/wp\/v2\/media?parent=21209"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/developer.kore.ai\/v8-0\/wp-json\/wp\/v2\/categories?post=21209"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/developer.kore.ai\/v8-0\/wp-json\/wp\/v2\/tags?post=21209"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}