PEGACPDS88V1 practice question 6 of 25
A telecom company is interested in improving customer engagement on social medi a. However, there are hundreds of relevant messages posted every day, and it is not practical for customer service representatives (CSRs) to review and respond to all messages. Instead, CSRs should focus on negative messages. What do you need to analyze the incoming messages?
Full set: 140 questionsThe core requirement is to classify incoming social media messages into predefined categories, specifically "negative" versus "non-negative." A text categorization model is the specific Pega AI tool designed for this purpose. It analyzes unstructured text and assigns it to one or more defined categories based on its content, vocabulary, and linguistic patterns. In this scenario, the model would be trained to recognize language indicative of negative sentiment, allowing the system to automatically flag and route these messages to customer service representatives for review.
A. Predictive model: This is too general. While a text categorization model is a type of predictive model, option C is more specific and accurately describes the required function for classifying text content.
B. Adaptive model: Adaptive models are used to predict customer behavior (e.g., propensity to accept an offer) and learn from real-time responses. They are not the primary tool for classifying the sentiment of inbound text.
D. Text extraction model: This model is used to identify and extract specific pieces of information (entities) like names, locations, or account numbers from text, not to classify the overall sentiment or topic of the message.
1. Pega Academy | Pega Decisioning Consultant (8.8) | Module: Detecting sentiment in text | Lesson: Text categorization for sentiment analysis:
"You can use text categorization to automatically detect the sentiment of a piece of text. For example
you can analyze the contents of an email
a chat session
or a social media post to determine whether the customer's attitude is positive
negative
or neutral." This directly supports using text categorization for the described scenario.
2. Pega Academy | Pega Decisioning Consultant (8.8) | Module: Detecting topics and entities in text | Lesson: Text extraction for entity detection:
"Text extraction analysis allows you to extract entities
such as a name
a location
or a phone number
from a piece of text." This reference clarifies the purpose of text extraction and differentiates it from text categorization
confirming why option D is incorrect.
3. Pega Platform Documentation | Text analytics:
"Text categorization is the process of assigning one or more categories to a piece of text
based on its contents... For example
you can use text categorization to analyze the sentiment of a customer's email." This official documentation reinforces that text categorization is the correct tool for sentiment analysis.
Keep practicing
Take the free PEGACPDS88V1 practice test
Ten exam-style questions with answers and explanations, plus the exam facts and study guides.
More questions
Other PEGACPDS88V1 practice questions
- Question 1As a data scientist, you are tasked with creating a new prediction that estimates a custo…
- Question 2When developing a predictive model, the outcome value of a continuous model type can repr…
- Question 3Adaptive model predictors are selected from the____________.
- Question 4The Pega Customer Decision Hub™ delivers Next-Best-Actions consistently through multiple …
- Question 5What is the key component of a Next-Best-Action strategy?
- Question 7Pega Decision Management enables organizations to make next-best-action decisions. To whi…
