Configuring general text prediction settings
Configure general parameters for your text prediction on the Settings tab. For example, you can select the types of outcomes that you want to predict: topics, sentiment, and entities. You can also configure language settings and topic granularity, define a neutral sentiment, and add preprocessing and postprocessing activities.
- Enabling outcomes in text predictions
A text prediction can analyze the text in your conversational channels to detect topics, sentiments, and entities. Depending on your business needs, select the outcomes that you want your text prediction to predict.
- Configuring language settings in text predictions
Define the languages to use with your text prediction and control how the prediction detects languages in an analyzed document. For example, you can enable a fallback language in case your text prediction does not detect the language when analyzing content that is written in multiple languages.
- Configuring topic settings in text predictions
Use topic settings to control how text is categorized, depending on the selected level of classification granularity. You can adjust text categorization according to your business needs, for example, to change the granularity of the analysis to document level if you analyze short chat messages.
- Configuring sentiment settings in text predictions
Define a sentiment score range to specify the type of sentiment feedback that you receive: positive, negative, or neutral.
- Configuring preprocessing models in text predictions
To identify the body, disclaimer, and signature components of emails in an email channel, you can configure a preprocessing model in the text prediction, for example, the default pxEmailParser rule. You can choose what type of analysis to perform on each email component, depending on your business needs.
- Configuring postprocessing activities in text predictions
Select a postprocessing activity to run on the results of the initial natural language processing (NLP) analysis of a text. For example, you can run the pxManageSmallTalkTopics activity to determine whether to consider the text small talk.
Previous topic Managing models in text predictions Next topic Enabling outcomes in text predictions