Sprinklr's Sentiment model classifies messages into Positive, Negative, and Neutral as per the sentiment of text used in the messages. This can be used to measure customer sentiment towards brands, campaigns, executives, products, events, etc., and to extract actionable insights to improve brand sentiment and trust.

The following use cases demonstrate how Sprinklr's Sentiment model validation projects can be applied, but they are flexible and can be customized to meet different needs.

• Custom Spam Categories: Develop custom categories for spam filtering based on the specific needs of the organization. This can help reduce the amount of irrelevant or unwanted content that employees or customers receive.

• Custom Sentiment Model: Build a custom sentiment model that accurately analyses text data, such as customer feedback, social media posts, and reviews.

Sprinklr's Advanced Insights models, including the Product and Location Insights models, use AI to generate phrase-level insights from various data sources, such as surveys, reviews, and social media channels.  

These use-cases illustrate how Sprinklr's PI and LI model validation projects can be utilized, but they can be tailored to address diverse requirements.

• Customer Service Experience: Analysing customer feedback to determine the level of satisfaction or dissatisfaction with the company's products or services. This can help identify areas for improvement and enhance customer engagement.

• Employee Engagement: Monitoring employee sentiment to gauge their level of satisfaction with their job and work environment. This can be useful for identifying areas where the company can improve employee engagement and retention.

• Identifying Employee Conversations: Identifying employee conversations outside of job portals that pertain to complaints or prospective leads for recruitment. This can help the organization address potential issues and opportunities and optimize recruitment efforts.

Difference between Sentiment v/s Product Insights & Location Insights Models

Sentiment models are specifically designed to predict the overall sentiment of a message, while Product Insights and Location Insights models are designed to provide more detailed insights about specific phrases within the message, including sentiment.

When using AI Studio, the user can select the source language for Sentiment validation models, but for Product Insights and Location Insights models, the user has the option to select the source messages at a much more granular level. This includes selecting the Level 1 categories as well as their corresponding L2 and L3 categories, enabling the user to gain a deeper understanding of the insights and sentiment expressed in the message.

By allowing the user to select the source messages at a granular level, AI Studio enables the user to gain a more comprehensive understanding of the insights and sentiment expressed in the message, which can be incredibly useful in various applications, such as Customer Feedback Analysis, Market Research, and Brand Reputation Management.