Smart Clustering Themes in Conversational Analytics are designed to empower users to understand their consumers' unmet needs and identify the top keywords and phrases in the agent-customer conversations. By harnessing the power of unsupervised clustering, this feature automatically extracts and synthesizes the most significant themes from conversations.    

Smart Clustering Themes help to uncover hidden discussions and sentiments, shifts, and emerging trends that may hold crucial insights. These insights can help users stay informed about the unknown aspects of consumer preferences and market dynamics.

What is Smart Theme Explorer?

Smart Themes Explorer, powered by Sprinklr AI, enables brands to understand unknown customer issues by surfacing them from the underlying conversations using unsupervised clustering.

Data Pre-Processing

The process of analyzing data in Smart Theme Explorer involves several steps, starting with data pre-processing. During this stage, the model filters out irrelevant messages, such as messages which are not a customer complaint, request, or enquiry, to focus only on relevant data.

Phrase Detection

The next step is phrase detection, which involves identifying relevant phrases in the messages to capture their essence and create clusters based on common themes. This includes customer attributes that describe what is being talked about in the messages.

Create Sub-Clusters Within Main Clusters

Once the phrases are detected, the model looks for associations between them to create sub-clusters within the main clusters. This is done through subject-subject, subject-attribute, and attribute-attribute associations, which help understand what entities are being talked about together or in similar contexts and what is being spoken about an entity. This process helps identify meaningful relationships between the subjects and attributes and define sub-clusters for a given cluster.