Data analytics system and methods for text data

A non-transitory, machine-readable storage medium, comprising executable instructions that, when executed by a processing system including a processor, facilitate performance of operations, the operations comprising:

• performing a first statistical, natural-language processing analysis on a first text document to determine a first plurality of topics based on a first vector of word counts in the first text document;
• performing a second statistical, natural-language processing analysis on a second text document to determine a second plurality of topics based on a second vector of word counts in the second text document;
• combining the first plurality of topics and the second plurality of topics to create a plurality of topic-document pairs;
• identifying a respective bias for each of the plurality of topic-document pairs, resulting in a plurality of biases;
• creating a plurality of topic clusters based on the first plurality of topics, the second plurality of topics, and the plurality of biases;
• and
• generating presentable content depicting each of the plurality of topic clusters according to a corresponding image configuration.

A method, comprising:

• performing, by a processing system comprising a processor, a first statistical, natural-language processing analysis on a first text document to determine a first plurality of topics based on a first vector of word counts in the first text document;
• performing, by the processing system, a second statistical, natural-language processing analysis on a second text document to determine a second plurality of topics based on a second vector of word counts in the second text document;
• combining, by the processing system, the first plurality of topics and the second plurality of topics to create a plurality of topic-document pairs;
• identifying, by the processing system, a respective bias for each of the plurality of topic-document pairs, resulting in a plurality of biases;
• and
• creating, by the processing system, a plurality of topic clusters based on the first plurality of topics, the second plurality of topics, and the plurality of biases.