{"id":49783,"date":"2022-12-22T00:46:45","date_gmt":"2022-12-22T00:46:45","guid":{"rendered":"https:\/\/developer.kore.ai\/v10-1\/?p=49783"},"modified":"2023-03-23T11:21:59","modified_gmt":"2023-03-23T11:21:59","slug":"conversational-insights","status":"publish","type":"post","link":"https:\/\/developer.kore.ai\/v10-1\/docs\/bots\/analyzing-your-bot\/conversational-insights\/","title":{"rendered":"Conversation Insights"},"content":{"rendered":"
<\/div>\r\n\t
\r\n\t\t
\r\n\t\t\t

Once a virtual assistant is published, it is important to understand and analyze the performance. Kore.ai platform provides various dashboards and one of them being <\/span>NLP Insights<\/a> that captures details like Intent Found, Intent Not Found, Unhandled Utterances, etc. However, to categorize the utterances as True Positives (TP), True Negatives (TN), False Positives (FP), and False Negatives (FN),\u00a0 you need to go through all the utterances across multiple tabs in NLP Insights. There could be millions of utterances that a bot designer needs to review, which could be tedious and time-consuming.\u00a0<\/span><\/p>\n

The <\/span>Conversation Insights<\/b> under Analyze<\/strong> in the Kore.ai XO Platform groups the utterances in a cluster, based on their semantic meaning and provides a name to each of these groups, which avoids the need to analyze all the utterances of the cluster.\u00a0 Based on the utterances that are identified or unidentified, these cluster groups can be part of one or more intents. Below is a snapshot of where intents and utterance groups are plotted in a treemap. <\/span>For more information on TP, TN, FP, FN scenarios, see <\/span>Appendix.<\/span><\/a>
\n\"\"<\/span><\/a><\/p>\n\n\n\n
Note<\/em><\/strong>: The Kore.ai platform groups together all the similar utterances to form a cluster and gives a name to each created cluster. Conversation Insights allows the bot designers to identify FPs, FNs, create new intents and perform many more actions. Cluster labeling is crucial in decision making in such scenarios.<\/span><\/em><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n\r\n\t\t<\/div>\r\n\t<\/div>\r\n<\/div><\/div><\/div><\/div><\/div><\/section>
<\/div>\r\n\t
\r\n\t\t
\r\n\t\t\t

The utterances in the platform are grouped together using an algorithm to create clusters. The most frequently occurring subject-verb-object<\/strong> is identified to create a label for the cluster.<\/p>\n

For e.g, In the utterance When will I get my ATM Card?, verb = get: subject = card; object = atm and the cluster label is created accordingly.<\/p>\n

Clustering Views<\/span><\/h2>\n

In Conversation Insights, the relationship between intents and clusters is represented visually in two different ways:<\/span><\/p>\n