You can use the Pega 7 Platform to analyze unstructured text that may come in through different channels: emails, social networks, chat channels, and so on.
Pega Platform provides the following methods of text analysis:
You can build machine learning models for sentiment analysis and text classification and deploy those models using Text Analyzer rules.
To train a text analytics model, you must upload training data with sample texts and associated outcomes. For a sentiment analysis, these sample records must be associated with a positive, neutral or negative outcome. For text classification, the outcome must be one of the categories in the taxonomy. In the process of creating a model, the data is split into a training sample and a test sample. The training sample is used to train the model. The test sample is the hold-out sample that is used validate the model. When a model is built, you can validate its performance.
If no training data is available, a text classification model can also be created based on category keywords included in the taxonomy (this is rule-based classification analysis). You cannot create your own machine learning models for intent detection or entity extraction. Entity extraction models can be defined by using RUTA scripts.
Text analytics in the Pega Platform is run through a Text Analyzer rule. A text analyzer parses text, automatically recognizes the language, and processes the models. A text analyzer rule may refer to one or more models of the methods that are listed above.