Data Slicer Dimensions

Data Slicer Dimensions are a suite of advanced analytics for unstructured text data. Different “dimensions of analysis” available include Sentiment, Topics, Themes, Scores, Summaries, Recommendations, and more.

Understanding Dimensions in Dashbot

Most simply, Dimensions refer to the different types of analytics that Dashbot offers for unstructured data. These analytics use AI to drive new information from the raw text itself and offer a powerful solution for structuring data at scale and making comparisons.

Core Concept: Asks questions of your data.

You are probably familiar with a sentiment analysis used to categorize unstructured data according to positive, negative and neutral tone. Any approach to calculating sentiment may be thought of as posing a simple, straightforward research question:

❓ Sentiment asks: What is the tone of the conversation? Answers: positive, negative, neutral

The resulting value of positive, negative or neutral is the answer to that question. Executed across hundreds or thousands of conversations reveals the overall proportion of answers—which is how the metric is presented (e.g., 27% of conversations with customer support in March were characterized by a negative tone).

Dimensions in Data Slicer similarly pose questions:

❓ Outcome asks: What was the outcome of the conversation? Answers: resolved, escalated, abandoned

Executed across thousands of support conversations the overall proportion of escalations becomes clear (e.g., 19% of live chat Support conversations were escalated to a manager in June)

What questions can Data Slicer Dimensions answer?

When you begin to think of analytics as “research questions” the full potential of Data Slicer’s Dimensions begins to emerge.

Our A.I. models are capable of posing a wide range of questions about any unstructured dataset, including (but not limited to) categorization, scoring, summarization, and even recommendations.

👉 Products - What products were mentioned in the conversation? Annotation
👉 Predicted Rating - How would the customer rate their interaction on a scale of 1-10? Scoring
👉 Predicted Feedback - How would the customer describe the conversation? Summarization
👉 Predicted Solution - What could be done to resolve the issue going forward? Recommendation

Answering open ended questions.

A key feature of dimensions is the ability to pose open ended questions.

Beyond manual tagging, traditional text analytics rely on users building complex keyword searches, training machine learning models or using out-of-the box segmentations—and with every approach categories are determined in advance

In contrast, Data Slicer dimensions may dynamically categorize data based on the context and content of the conversations. This method is more adaptable and responsive to emerging themes and topics within the data.
👉 Reason - What is the reason the customer reached out to support?
👉 Category - What is the overall theme of the conversation?
👉 Category Cluster - What is the highest level theme of the conversation?

Answer clustering to create levels of analysis

Some Dimensions employ answer clustering to create a hierarchy of analysis. In addition to Reasons \Categories \Category Clusters, other dimensions employ answer clustering as well.

👉 Predicted Solution - What is the topic of the conversation?

👉 Predicted Solution Cluster - What are the themes of the conversation?