Abstract: Airline evaluation, comment recommendation, and finding prediction mapping are provided. Responsive to a first user partial entry in an evaluation category entry field, a first large language model (LLM) provides prompts of suggested categories. Selection of one of the prompts or user entry of an alternative category is received. Responsive to a partial entry of a task description, the first LLM provides prompts of suggested task descriptions. Selection of one of the prompts or user input of an alternative task description is received. Responsive to a partial entry of a comment, the first LLM provides prompts comprising subsets of words of suggested comments. Selection of one the prompts or input of an alternate comment is then received. A second LLM provides predicted findings based on the evaluation category, task description, and comment. Selection of one of the predicted findings or user input of an alternative finding is then received.

Abstract: Methods and systems for measuring and predicting content dissemination in social networks includes computing a “virality score” for popularity of social media content, a “pattern” of diffusion of the content, and a “hype” parameter of such content without requiring a “friendship graph” or “information diffusion” structured data. It also includes an iterative, predictive model, which predicts future performance (or future rate of dissemination) of the content while mitigating a class imbalance problem inherent in predicting viral posts, and which provides updates to the model based on actual performance results.

Abstract: Methods and systems for automatic generation of sports highlights are described, where AV media data of a sporting event (game) are analyzed to identify sports highlights using a data-graph-based technique for “in-game” highlights, and “out-of-game” AV media data (e.g. post-game commentary/analysis/news) are analyzed for out-of-game content (OGC) related to each of the selected in-game highlights to produce a collective AV narrative around each of the in-game highlights selected. The format and appearance of the final highlights AV media content or video are also adjustable by the user or the highlights producer to optimize the highlight viewing experience.

Abstract: Methods and systems for automatic generation of sports highlights are described, where AV media data of a sporting event (game) are analyzed to identify sports highlights using a data-graph-based technique for “in-game” highlights, and “out-of-game” AV media data (e.g. post-game commentary/analysis/news) are analyzed for out-of-game content (OGC) related to each of the selected in-game highlights to produce a collective AV narrative around each of the in-game highlights selected. The format and appearance of the final highlights AV media content or video are also adjustable by the user or the highlights producer to optimize the highlight viewing experience.

Abstract: Methods and systems for measuring and predicting content dissemination in social networks includes computing a “virality score” for popularity of social media content, a “pattern” of diffusion of the content, and a “hype” parameter of such content without requiring a “friendship graph” or “information diffusion” structured data. It also includes an iterative, predictive model, which predicts future performance (or future rate of dissemination) of the content while mitigating a class imbalance problem inherent in predicting viral posts, and which provides updates to the model based on actual performance results.