{"id":21209,"date":"2019-05-27T07:07:40","date_gmt":"2019-05-27T06:07:40","guid":{"rendered":"https:\/\/developer.kore.ai\/v10-1\/?p=21209"},"modified":"2022-10-04T06:55:39","modified_gmt":"2022-10-04T05:55:39","slug":"sentiment-management","status":"publish","type":"post","link":"https:\/\/developer.kore.ai\/v10-1\/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><span style=\"font-weight: 400\">Emotion tones are critical indicators in understanding the attitudes and opinions of users interacting with Virtual Assistants. <\/span><strong>Sentiment Management<\/strong><span style=\"font-weight: 400\"> allows the developer to define and trigger events based on the user\u2019s emotion or sentiment.<\/span><\/p>\n<table style=\"width: 100%;border-collapse: collapse;background-color: #fffbea\">\n<tbody>\n<tr>\n<td style=\"width: 100%\">\n<p><strong>Notes<\/strong><\/p>\n<ul>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">This feature was introduced in v7.0.<\/span><\/li>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">This feature is not supported in all languages. <\/span><a href=\"https:\/\/developer.kore.ai\/v10-1\/docs\/bots\/how-tos\/multi-lingual-bot-behavior\/#Feature_Support\"><span style=\"font-weight: 400\">Click here for details<\/span><\/a><span style=\"font-weight: 400\">.<\/span><\/li>\n<\/ul>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p>\u00a0<\/p>\n<p><span style=\"font-weight: 400\">Negative emotion scenarios like anger or disgust are typically considered factors that would determine a transfer of the conversation to a live agent.<\/span><\/p>\n<p><a href=\"https:\/\/kore.ai\/platform\/design-and-build\/natural-language-processing\/\"><span style=\"font-weight: 400\">The Natural Language Processing (NLP)<\/span><\/a><span style=\"font-weight: 400\"> 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. (<\/span><a href=\"https:\/\/developer.kore.ai\/v10-1\/docs\/bots\/advanced-topics\/working-with-tone-processing\/\"><span style=\"font-weight: 400\">Click here for more on Tone Analysis<\/span><\/a><span style=\"font-weight: 400\">)<\/span><\/p>\n<p><span style=\"font-weight: 400\">The tone or sentiment scores are stored as context and used to drive the flow of a dialog task through conditional transition statements. You can use these scores to steer user-assistant conversations or seamlessly invoke escalation to a live agent.<\/span><\/p>\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>\n<h2><span class=\"ez-toc-section\" id=\"Configuration\"><span style=\"font-weight: 400\">Configuration<\/span><\/span><\/h2>\n<p><span style=\"font-weight: 400\">You can define multiple sentiment events from under Build &gt; Intelligence &gt; Sentiment Management. Click <\/span><strong>New Event<\/strong><span style=\"font-weight: 400\"> to define an event based on which to capture the user\u2019s emotion.<\/span><\/p>\n<p><span style=\"font-weight: 400\"><a href=\"https:\/\/kore-wordpress.s3.us-east-2.amazonaws.com\/developer.kore.ai\/v10-1\/wp-content\/uploads\/sites\/35&lt;a href=\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-large wp-image-47537\" src=\"https:\/\/kore-wordpress.s3.us-east-2.amazonaws.com\/developer.kore.ai\/v10-1\/wp-content\/uploads\/sites\/35\/20221004065155\/new-event-1024x434.png\" alt=\"\" width=\"640\" height=\"271\" srcset=\"https:\/\/kore-wordpress.s3.us-east-2.amazonaws.com\/developer.kore.ai\/v10-1\/wp-content\/uploads\/sites\/35\/20221004065155\/new-event-1024x434.png 1024w, https:\/\/kore-wordpress.s3.us-east-2.amazonaws.com\/developer.kore.ai\/v10-1\/wp-content\/uploads\/sites\/35\/20221004065155\/new-event-300x127.png 300w, https:\/\/kore-wordpress.s3.us-east-2.amazonaws.com\/developer.kore.ai\/v10-1\/wp-content\/uploads\/sites\/35\/20221004065155\/new-event.png 1922w\" sizes=\"auto, (max-width: 640px) 100vw, 640px\" \/><\/a><\/span><\/p>\n<p><span style=\"font-weight: 400\">The following parameters can be configured for a sentiment event:<\/span><\/p>\n<ul>\n<li style=\"font-weight: 400\"><strong>Event Name<\/strong><span style=\"font-weight: 400\"> \u2013 Name of the event.<\/span><\/li>\n<li style=\"font-weight: 400\"><strong>Event Trigger<\/strong><span style=\"font-weight: 400\"> \u2013 Defines how often the sentiment must be checked. It can be set to:<\/span><\/li>\n<ul>\n<li style=\"font-weight: 400\"><strong>On Task Completion<\/strong><span style=\"font-weight: 400\"> \u2013 Sentiment is checked only after completion of a task.<\/span><\/li>\n<li style=\"font-weight: 400\"><strong>After Every User Utterance<\/strong><span style=\"font-weight: 400\">\u2013 Sentiment is checked after every utterance from the end-user. The event is evaluated before proceeding with the conversation using the incoming utterance.<\/span><\/li>\n<\/ul>\n<li style=\"font-weight: 400\"><strong>Emotion Configurations<\/strong>\n<ul>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">The Session-level tone value is a consolidated tone value across all user messages in a conversation session.<\/span><\/li>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">The Message-level tone value is a tone value calculated for a given message from the user.<\/span><\/li>\n<\/ul>\n<\/li>\n<ul>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">Select the required emotions to be captured from a list of six tones, anger, disgust, fear, sadness, joy, and positive.<\/span><\/li>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">Select if the tone should be considered at the <\/span><em><span style=\"font-weight: 400\">Session<\/span><\/em><span style=\"font-weight: 400\"> level or <\/span><em><span style=\"font-weight: 400\">Message<\/span><\/em><span style=\"font-weight: 400\"> level<\/span><\/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><a href=\"https:\/\/developer.kore.ai\/v10-1\/docs\/bots\/advanced-topics\/working-with-tone-processing\/\"><span style=\"font-weight: 400\">Click here for more<\/span><\/a><span style=\"font-weight: 400\"> on Tone Analysis).<\/span><\/li>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">When multiple emotions are selected, the event is triggered when <\/span><strong>ALL <\/strong><span style=\"font-weight: 400\">the tone rules are met. In case you want the event to trigger when any tone rule is met, add them as separate rules.<\/span><span style=\"font-weight: 400\"><br \/><\/span><strong><em>Note<\/em><\/strong><em><span style=\"font-weight: 400\">: Post v8.1, the Platform can identify the emojis in user utterance and set the tone accordingly.<\/span><\/em><\/li>\n<p><a ref=\"magnificPopup\" href=\"https:\/\/kore-wordpress.s3.us-east-2.amazonaws.com\/developer.kore.ai\/v10-1\/wp-content\/uploads\/sites\/35\/20221004065148\/sentiment-event-config.png\"><img decoding=\"async\" src=\"https:\/\/kore-wordpress.s3.us-east-2.amazonaws.com\/developer.kore.ai\/v10-1\/wp-content\/uploads\/sites\/35\/20221004065148\/sentiment-event-config.png\" alt=\"\" width=\"479\" \/><\/a>\n<\/ul>\n<\/ul>\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>\n<h2><span class=\"ez-toc-section\" id=\"Event_Flow\"><span style=\"font-weight: 400\">Event Flow<\/span><\/span><\/h2>\n<p><span style=\"font-weight: 400\">Emotion tones are continuously updated whenever a message is received from the users and as such the sentiment events are also continuously evaluated. When an event\u2019s criteria are met, the Platform triggers the defined behavior.<\/span><\/p>\n<ul>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">If the configuration used is to <\/span><strong>Initiate a task<\/strong><span style=\"font-weight: 400\">, then the current task is discarded and the VA switches to the new task according to the event configuration.<\/span><\/li>\n<ul>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">Any other implicitly paused tasks will also be discarded.<\/span><\/li>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">Tasks that are kept on hold using Hold and Resume settings are resumed as per Hold and Resume configuration.<\/span><\/li>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">If the dialog selected to trigger for the sentiment event is not available for any reason, then a standard response is displayed. Refer to the standard response with the title <\/span><em><span style=\"font-weight: 400\">Dialog task required for conversation is not available<\/span><\/em><span style=\"font-weight: 400\"> for more information. (<\/span><a href=\"https:\/\/developer.kore.ai\/v10-1\/docs\/bots\/bot-intelligence\/default-dialog\/#Managing_Standard_Responses\"><span style=\"font-weight: 400\">more on standard responses<\/span><\/a><span style=\"font-weight: 400\">).<\/span><\/li>\n<\/ul>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">If the configuration used is to <\/span><strong>Run a Script<\/strong><span style=\"font-weight: 400\">, then the Platform executes the script and continues 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 <\/span><em><span style=\"font-weight: 400\">Error in continuing the conversation due to incorrect bot definition<\/span><\/em><span style=\"font-weight: 400\"> for more information. (<\/span><a href=\"https:\/\/developer.kore.ai\/v10-1\/docs\/bots\/bot-intelligence\/default-dialog\/#Managing_Standard_Responses\"><span style=\"font-weight: 400\">more on standard responses<\/span><\/a><span style=\"font-weight: 400\">).<\/span><\/li>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">In case of a conflict between a sentiment event and direct intent invocation by the user, sentiment event is given precedence.<\/span><\/li>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">When tone criteria for two or more sentiment events are satisfied at the same instance, then the Platform prefers the sentiment event with the highest order of precedence used in defining the events.<\/span><\/li>\n<\/ul>\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>\n<h2><span class=\"ez-toc-section\" id=\"Reset_Tone\"><span style=\"font-weight: 400\">Reset Tone<\/span><\/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 are reset after successful execution of the script.<\/span><\/li>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">In case a dialog task is triggered, the values are transferred to the new dialog task\u2019s (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>[vc_raw_html]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[\/vc_raw_html]<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 Virtual Assistants. Sentiment Management allows the developer to define and trigger events based on the user\u2019s emotion or sentiment. Notes This feature was introduced in v7.0. This feature is not supported in all languages. Click here for details. \u00a0 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\/v10-1\/wp-json\/wp\/v2\/posts\/21209","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/developer.kore.ai\/v10-1\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/developer.kore.ai\/v10-1\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/developer.kore.ai\/v10-1\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/developer.kore.ai\/v10-1\/wp-json\/wp\/v2\/comments?post=21209"}],"version-history":[{"count":28,"href":"https:\/\/developer.kore.ai\/v10-1\/wp-json\/wp\/v2\/posts\/21209\/revisions"}],"predecessor-version":[{"id":47541,"href":"https:\/\/developer.kore.ai\/v10-1\/wp-json\/wp\/v2\/posts\/21209\/revisions\/47541"}],"wp:attachment":[{"href":"https:\/\/developer.kore.ai\/v10-1\/wp-json\/wp\/v2\/media?parent=21209"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/developer.kore.ai\/v10-1\/wp-json\/wp\/v2\/categories?post=21209"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/developer.kore.ai\/v10-1\/wp-json\/wp\/v2\/tags?post=21209"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}