Systems and methods for ingesting and parsing datasets generated from disparate data sources

A tangible, non-transitory computer-readable medium comprising instructions that, when executed by processing circuitry, are configured to cause the processing circuitry to perform operations comprising:

• defining a plurality of vectors by generating a vector for each text file of a plurality of text files, wherein a value of a dimension of each vector of the plurality of vectors corresponds to a frequency of occurrence associated with a word in a respective text file of the plurality of text files;
• generating a matrix corresponding to the plurality of vectors;
• determining topics associated with each text file of the plurality of text files by decomposing the matrix using a non-negative matrix factorization algorithm to generate a term-topic matrix indicative of strengths of association between words in the respective text files of the plurality of text files and associated topics and to generate a topic-document matrix indicative of strengths of association between the associated topics and the respective text files;
• and
• generating a graphical user interface (GUI) for display on a device, wherein the GUI comprises a plurality of images representing the plurality of text files, the plurality of images being positioned relative to one another based on respective relative distances between the plurality of text files, the respective relative distances being indicative of a quantity of topics shared between the plurality of text files as determined via decomposing the matrix, and smaller relative distances being indicative of greater quantities of topics shared.

A computer system, comprising:

• processing circuitry;
• and
• a memory comprising instructions that, when executed by the processing circuitry, are configured to cause the processing circuitry to perform operations comprising:
• generating a vector for each text file of a plurality of text files to define a plurality of vectors, wherein a value of a dimension of each vector of the plurality of vectors corresponds to a frequency of occurrence of a word in a respective text file of the plurality of text files;
• generating a matrix corresponding to the plurality of vectors;
• generating a term-topic matrix indicative of strengths of association between the words in the respective text files of the plurality of text files and topics for the respective text files by decomposing the matrix using a non-negative matrix factorization algorithm;
• generating a topic-document matrix indicative of strengths of association between the topics and the respective text files of the plurality of text files by decomposing the matrix using the non-negative matrix factorization algorithm;
• and
• generating a graphical user interface (GUI) for display on a device, wherein the GUI comprises a plurality of images representing the plurality of text files, the plurality of images being positioned relative to one another based on respective distances spanning between the plurality of text files, the respective distances being indicative of a quantity of topics shared between the plurality of text files as determined based on the term-topic matrix and the topic-document matrix such that the respective distances are inversely related to the quantity of topics shared.