Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: Systems and methods are provided for analyzing social media content. In exemplary embodiments, the invention can include obtaining a plurality of data items communicated through at least one social media platform over a time interval, with each data item from the plurality of data items being associated with a time value within the time interval; analyzing at least a subset of the plurality of data items to assign each data item from the subset to a respective category from a plurality of categories; and generating for at least one category from the plurality of categories, a representation of data items assigned to the at least one category as a function of time over the time interval for presenting via a user interface.

Abstract: 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.

Abstract: Improved searching of digital content using a large corpus of content collected from content generating websites is described. A search query received from a user is compared to the collected content to determine how often the elements of the search query are repeated in the collected content and whether these elements have frequently co-occurred with other elements in the content. Co-occurring elements are presented to the user so that the user can select one or more elements that best describe her intent in conducting the search. An updated search query is formed based on the information received from the user. The updated query is used to retrieve a number of documents and the retrieved documents are classified to distinguish relevant documents from those irrelevant to the user's intent. Documents classified as relevant are presented to the user.

Abstract: 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.

Abstract: 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.