User Insights - Sentiment Analysis

Aisera’s Sentiment Analysis is known as User Insights within the Agent Assist application/bot.

It uses natural language processing (NLP) and machine learning techniques to analyze and interpret the emotions expressed in text data from an utterance or the conversation thread associated with a user query. This process helps our customers understand the sentiment of their end users (employees or customers). Tracking the sentiment in conversations can provide valuable insights for improving service quality and customer satisfaction.

Key Components include,

1. Data Collection: Gathering textual data from different sources such as conversation history, helpdesk emails or tickets, feedback and survey responses.

2. Text Processing: Cleaning and preparing the text data for analysis. This includes removing irrelevant information, normalizing text, and handling various language nuances.

3. Sentiment Detection: Using NLP algorithms to detect the sentiment expressed in the text. Aisera’s sentiment scores are categorized as

   1. Very Positive

   2. Positive

   3. Neutral

   4. Negative

   5. Very Negative

4. Contextual Understanding: Analyzing the context in which words are used to improve the accuracy of sentiment detection. This is crucial as the same word can convey different sentiments in different contexts.

5. Visualization and Reporting: Presenting the results of the sentiment analysis in a meaningful way, often through dashboards and reports that highlight trends, patterns, and areas needing attention.

Some of the top use cases include:

1. Incident Management: Detecting frustration or dissatisfaction in user reports to prioritize and expedite resolution.

2. Service Desk Operations: Monitoring agent interactions to ensure a positive customer experience and provide training based on identified service gaps.

3. Feedback Analysis: Analyzing feedback from customer satisfaction surveys to identify trends and areas for service improvement.

Custom Analytics

The Aisera platform provides the capability to create custom dashboards highlighting the Requests by Sentiment.

By clicking on individual bar graphs, you can drill down into the detailed Request view page and filter by specific sentiments, as shown in the image below.

This granular view shows individual requests categorized by Resolution, Fulfillment Source, and Fulfillment Type that were classified with a Negative sentiment.

If you add the Feedback Answer column, as shown in the following image, you see that although some of the requests had Knowledge Articles that were returned as fulfillments, the user did not provide feedback. In this use case, No Answer is considered a Negative sentiment.

DEX

The Aisera platform supports DEX use cases end-to-end and Dex tools such as Intunes, Nexthink, and Lakeside. Aisera software can analyze, process, and ingest events or alerts from DEX tools and then perform actions and workflows that resolve issues for service agents.

The Aisera Administration application comes with pre-built DEX workflows to execute and orchestrate. These can be modified to create new DEX workflows. DEX use cases range from user experience, performance issues, incident management, change management, and Device issues.

The Aisera platform also supports DEX integration with ITSM tools and can process tickets from ITSM systems to perform actions. Tickets from ITSM sysstems can be shared or analyzed by the Aisera software via APIs and alerts or notifications.