Links may not function; however, this content may be relevant to outdated versions of the product.
Labeling text with categories
Efficiently analyze large volumes of text and assign each sentence to a predefined category by using the text categorization feature. With text categorization, you can quickly react to what your customers are saying and aptly address their inquiries or concerns.
The text categorization feature assigns the analyzed text to one or more predefined categories. Pega Platform provides you with three types of text categorization, depending on what you want to detect:
- Topic detection
- Topic detection determines the underlying topic of a single piece of text or an entire
document to efficiently route an incoming customer query to the right agent.
For example, in a chat window on the Emu Airlines website, a customer writes I want to book a ticket from London to Tokyo. Topic detection automatically assigns the message to the Booking a flight category based on similar customer messages and the book and ticket keywords. The company application routes all messages from the Booking a flight category to the corresponding customer service team. As a result, Emu Airlines reduces the response time to customer queries and improves the quality of their customer service.
Topic detection supports both machine learning and keyword-based categorization.
For more information, see Detecting the topics of text fragments.
- Intent detection
- Intent detection analyzes a unit of text, for example, a comment on your company social
media profile, to determine the intent of the author. For example, intent detection
classifies the sentence How do I create an account at uPlusTelco?
as an inquiry.
Intent detection supports machine learning categorization.
For more information, see Recognizing user intent.
- Sentiment detection
- Sentiment detection recognizes the feelings (attitudes, emotions, opinions) that
characterize a unit of text and then assigns the analyzed text to one of the following
sentiment categories: positive, neutral, or negative. For example, the sentence
I am happy with uPlusTelco's customer service. is determined as
Sentiment detection supports machine-learning categorization.
Previous topic Out-of-the-box text analytics models Next topic Detecting the topics of text fragments