Dominant Location

The Dominant Location classifier is a specialized text classifier that operates on long-form content. It is meant to identify only one location out of all the mentioned locations in the news and report it as the dominant_location based on their frequency in the input document.


TypeSpeedPartner Type
Stream Integrated ClassifierInstantDatastreamer Internal

Example Use Cases

The Dominant Location classifier analyzes input documents and pre-extracted location entities. Suppose that there are multiple locations mentioned in the text, the classifier analyzes each of them and extracts only one of them as the most dominant location based on their frequency. In addition, it also presents a confidence score as well.


The Dominant location classifier provides two fields within "dominant_location". The "label" presents the name of location and the "confidence" score which is a number within a range of [0, 1]. The higher the confidence the more reliable the answer.

      "label": "Toronto",
      "confidence": 0.87