Abstract: Disclosed is a flexible, scalable method for automatically distinguishing between the ‘mainstream’ and ‘fringe’ in any text dataset, such as unstructured social media data. The disclosed method allows analysts quickly to pinpoint text articulating fringe beliefs or theories, without prior knowledge of the nature of the fringe beliefs, and can be applied to text data in any language, provided the data can be represented electronically. The method works automatically and without any preconceived notions of what is important or what vocabulary is used in the context of certain beliefs. An analyst's attention is then quickly focused either on new conspiracy theories taking hold (potentially allowing decision-makers to act to interdict the ‘next QAnon insurrection’), or on well-founded beliefs that simply are not yet mainstream. Either way, analysts are empowered better to ‘connect the dots’ for a more complete understanding of the information environment.

Abstract: Disclosed is a flexible, scalable method for automatically distinguishing between the ‘mainstream’ and ‘fringe’ in any text dataset, such as unstructured social media data. The disclosed method allows analysts quickly to pinpoint text articulating fringe beliefs or theories, without prior knowledge of the nature of the fringe beliefs, and can be applied to text data in any language, provided the data can be represented electronically. The method works automatically and without any preconceived notions of what is important or what vocabulary is used in the context of certain beliefs. An analyst's attention is then quickly focused either on new conspiracy theories taking hold (potentially allowing decision-makers to act to interdict the ‘next QAnon insurrection’), or on well-founded beliefs that simply are not yet mainstream. Either way, analysts are empowered better to ‘connect the dots’ for a more complete understanding of the information environment.

Abstract: Disclosed are improvements to a method for account reconciliation comprising improved, extended, and more flexible algorithms for (1) automatically determining what transaction features are best candidates for matching diverse datasets; (2) automatically determining how logically to subdivide accounting datasets prior to reconciliation; (3) matching groups of transactions (allowing one-to-many, many-to-one, and many-to-many matches instead of just one-to-one matches); (4) making use of more types of transaction feature, including transaction dates (where proximity of two transactions in date may be significant even if the dates do not exactly match). The improved method is, therefore, better able to perform its intended function of identifying matching transactions. It is applicable to a wider class of problems while still saving significant costs and labor, and still retaining flexibility in not requiring source data in a particular format, and not being domain-dependent or requiring extensive user setup.

Abstract: Disclosed is a generalized method for automated account reconciliation capable of matching transactions in one accounting dataset to transactions in another accounting dataset with little initial data preparation. The method is highly flexible in that it does not require source data in a particular format, can accept both structured and unstructured (e.g. descriptive text) data as input, is not domain- or language-dependent, and requires little to no training or user-provided heuristics. The method is also adjustable depending on a user's tolerance of error. Based on probability and information theory, computational linguistics, and statistics, the method can complete accounting reconciliation problems in significantly less time than is possible manually, and with just as high accuracy. Especially for large reconciliation problems, the method can save an overwhelming portion of the cost associated with this kind of task in the past.

Abstract: A technique for information retrieval includes parsing a corpus to identify a number of wordform instances within each document of the corpus. A weighted morpheme-by-document matrix is generated based at least in part on the number of wordform instances within each document of the corpus and based at least in part on a weighting function. The weighted morpheme-by-document matrix separately enumerates instances of stems and affixes. Additionally or alternatively, a term-by-term alignment matrix may be generated based at least in part on the number of wordform instances within each document of the corpus. At least one lower rank approximation matrix is generated by factorizing the weighted morpheme-by-document matrix and/or the term-by-term alignment matrix.

Abstract: A technique for information retrieval includes parsing a corpus to identify a number of wordform instances within each document of the corpus. A weighted morpheme-by-document matrix is generated based at least in part on the number of wordform instances within each document of the corpus and based at least in part on a weighting function. The weighted morpheme-by-document matrix separately enumerates instances of stems and affixes. Additionally or alternatively, a term-by-term alignment matrix may be generated based at least in part on the number of wordform instances within each document of the corpus. At least one lower rank approximation matrix is generated by factorizing the weighted morpheme-by-document matrix and/or the term-by-term alignment matrix.