Crimson Hexagon, Inc.

Runtime Collective Limited

Brandwatch

Christopher Bingham

Aykut Firat

Amaç Herdagdelen

Mitchell Brooks

Gary King

Francesco Liuzzi

Karim Abdul Munaff

Data characterizing a document including a target word and a plurality of potential meanings for the target word is received. A first set of context words is determined using a language model. The first set of context words is for the target word. A second set of context words is determined using a knowledge base and the language model. The second set of context words is for the plurality of potential meanings of the target word. A score is determined for each of the plurality of potential meanings by at least comparing the first set of context words and the second set of context words. A potential meaning selected from the plurality of potential meanings that has a highest score is selected as a disambiguation of the first word. Related apparatus, systems, techniques and articles are also described.

Entity disambiguation

Systems and methods are provided for analyzing people's interests, based on signals available within social media. In general, the systems and methods can include determining interests for a group of people that differentiate the group from another group. First, topics of interest for each individual can be calculated based on topics associated with their activity on social media websites and topics associated with people in their social media network. The interest topics of people in a first group can be compared to the interest topics of people in a second group to determine which interest topics have a high affinity for one group but not the other. The invention can further provide for visualization of the topic distribution between the two groups, which can include illustrations of the number of people in each group who are interested in a plurality of topics and/or the prevalence of each of the plurality of topics in the first group relative to the second group.

Analyzing interests based on social media data

Systems and methods are provided for classifying text based on language using one or more computer servers and storage devices. A computer-implemented method includes receiving a training set of elements, each element in the training set being assigned to one of a plurality of categories and having one of a plurality of content profiles associated therewith; receiving a population set of elements, each element in the population set having one of the plurality of content profiles associated therewith; and calculating using at least one of a stacked regression algorithm, a bias formula algorithm, a noise elimination algorithm, and an ensemble method consisting of a plurality of algorithmic methods the results of which are averaged, based on the content profiles associated with and the categories assigned to elements in the training set and the content profiles associated with the elements of the population set, a distribution of elements of the population set over the categories.

Systems and methods for calculating category proportions

Systems and methods are provided for classifying text based on language using one or more computer servers and storage devices. In general, the systems and methods can include a language classification module for classifying text of an input data set using the output of a training module. In an exemplary embodiment, a bootstrapping step feeds the output of the language classification module back into the training module to increase the accuracy of the language classification module. By iterating the language classification and training modules with input data having certain features, a user can tailor the language classification module for use with text having those or similar features.

Growing community of inventors

Cambridge, MA, United States of America

Christopher Bingham