Creating keyword-based topic models
Efficiently connect your customers with the right consultant without having to provide training data to the topic model. Instead, you can use a list of topic-specific keywords to train the model.
The topic model then scans the customer message in search of the specified keywords, and uses the results to assign the message to a corresponding topic, for example, Action > User Support.
Keyword-based topic detection acts as a substitute for, or supplement to, machine learning topic detection. For more information about the differences between topic model types, see Comparing keyword-based and machine learning topic detection.
- Ensure that the system locale language settings are set to UTF-8.
- Specify a repository for text analytics models. For more information, see Specifying a database for Prediction Studio records.
To create a keyword-based topic model, perform the following procedures:
- Setting up a keyword-based topic model
Create a keyword-based topic model by specifying the model name, language, and corresponding ruleset. After you create the model, complete the model configuration by defining a taxonomy of topics and keywords.
- Creating a taxonomy for keyword-based topic detection
After you create a topic model, define the topics that you want to detect in a piece of text. For each topic, add a list of keywords that define the topic. Based on these keywords, topic detection then assigns topics to an analyzed piece of text.
- Importing a taxonomy for keyword-based topic detection
After you create a topic model, import a taxonomy that contains defined topics and keywords for topic detection. Based on the keywords, topic detection assigns topics to the analyzed piece of text.