Abstract: A method for generating and displaying an icon associated with a topic in place of filtered content, the icon associated with functionality allowing for displaying of the filtered content, includes applying, by a filtering engine, a topic-based filter to at least a portion of a data stream. The filtering engine directs a first modification to a user interface displaying the at least the portion of the data stream, the modification comprising redacting the at least the portion of the data stream and displaying at least one icon in place of the at least the portion of the data stream, the at least one icon associated with a topic of the at least the portion of the data stream. The filtering engine receives user input via the at least one icon and directs the displaying of the at least the portion of the data stream.

Abstract: Disclosed herein are systems and methods for modeling controversy as a combination of at least contention and importance with respect to a given population. An example system for modeling controversy within a population includes an interface, memory, and processor. The interface is configured to obtain information regarding stances of individuals in the population on a topic. The processor is configured to determine, and store in the memory, a representation of contention on the topic among individuals of the population. The representation of contention is based on the stances of individuals in the population. The processor is further configured to determine, and store in the memory, a representation of importance of the topic within the population. The processor is configured to create, and store in the memory, a model of controversy for the topic based on the representations of contention and importance.

Abstract: User responses to prompts or queries are classified or scored using explainable artificial intelligence (XAI) according to levels of a defined proficiency scale for selected subject matter. Recommendations for improving user proficiency are generated using XAI based on the proficiency classifications or scores and underlying rationales leading to those classifications or scores. XAI can be employed for identifying user responses that are consistent with predetermined cheating patterns. Prompts and queries can be presented, user responses classified or scored, and recommendation generated in a single session, i.e., in near real time. Disclosed methods can be advantageously employed for assessing user proficiency, and providing recommendations for improving proficiency, in a wide variety of subject areas, including spoken, written, or signed human languages.

Abstract: A probabilistic framework to detect controversy on the web. The prior kNN-WC algorithm is recast into a theoretical framework and a new language model introduced. Language models are constructed that are used to calculate probabilities. The probabilities are compared to determine whether or not a certain document is controversial.

Abstract: Disclosed herein are systems and methods for modeling controversy as a combination of at least contention and importance with respect to a given population. An example system for modeling controversy within a population includes an interface, memory, and processor. The interface is configured to obtain information regarding stances of individuals in the population on a topic. The processor is configured to determine, and store in the memory, a representation of contention on the topic among individuals of the population. The representation of contention is based on the stances of individuals in the population. The processor is further configured to determine, and store in the memory, a representation of importance of the topic within the population. The processor is configured to create, and store in the memory, a model of controversy for the topic based on the representations of contention and importance.

Abstract: A probabilistic framework to detect controversy on the web. The prior kNN-WC algorithm is recast into a theoretical framework and a new language model introduced. Language models are constructed that are used to calculate probabilities. The probabilities are compared to determine whether or not a certain document is controversial.