Analysis of theme coverage of documents

At least one non-transitory computer-readable media configured to store one or more instructions that when executed by at least one processor cause or direct a system to perform operations, the operations comprising:

• obtaining a plurality of electronic documents;
• obtaining theme text indicative of a theme of interest to a user;
• determining a semantic similarity between the theme text and each of a plurality of text strings included in a weight vector that is used in identification of topics of the plurality of electronic documents, the weight vector including a plurality of weights that each correspond to a different one of the plurality of text strings;
• selecting a seed text from the plurality of text strings in response to a particular semantic similarity between the seed text and the theme text satisfying a semantic similarity threshold;
• changing a seed weight included in the weight vector electronic document in which the seed weight corresponds to the seed text, the changing of the seed weight being in response to selection of the seed text and biasing the identification of topics of the plurality of electronic documents in favor of the seed text as compared to one or more other text strings of the plurality of text strings;
• generating a representation of a topic model for display to the user, the topic model based on the plurality of electronic documents and the weight vector, the topic model identifying one or more topics of the plurality of electronic documents.

A system including one or more processors and one or more computer-readable media, the system configured to perform operations comprising:

• obtaining a plurality of electronic documents;
• obtaining theme text indicative of a theme of interest to a user;
• determining a semantic similarity between the theme text and each of a plurality of text strings;
• selecting a seed text from the plurality of text strings in response to a particular semantic similarity between the seed text and the theme text satisfying a semantic similarity threshold;
• changing a seed weight included in a weight vector that is used in identification of topics of the plurality of electronic documents, the weight vector including a plurality of weights that each correspond to a different one of the plurality of text strings in which the seed weight corresponds to the seed text, the changing of the seed weight being in response to selection of the seed text and biasing the identification of topics of the plurality of electronic documents in favor of the seed text as compared to one or more other text strings of the plurality of text strings;
• generating a representation of a topic model for display to the user, the topic model based on the plurality of electronic documents and the weight vector, the topic model identifying one or more topics of the plurality of electronic documents.