Abstract: Techniques for customizing multimedia content using data structures adapted to text samples. A method includes dividing a text sample into segments. Unique words are identified within the segments. For each unique word found in the segments, its neighboring words are identified. Based on sentiment values associated with those neighboring words, a sentiment of each unique is determined. Using the sentiments of the unique words, text skeletons are modified by inserting the unique words into corresponding locations within structured data of the text skeletons. The modified text skeletons may be inserted into multimedia content in order to customize that multimedia content to the text sample.

Abstract: A system and method for customizing multimedia content using text-based data structures adapted to text samples. A method includes dividing a text sample into segments of approximately the same size. A unique word occurring exactly once in two or more of the segments is identified. Neighboring words within a threshold distance of the unique word in each of the segments are identified. A first sentiment is determined based on the neighboring words for the unique word. A text skeleton is modified by inserting the unique word into the location in the structured dataset based on the determined first sentiment, wherein the text skeleton is a structured dataset including a location having a designated second sentiment matching the first sentiment. The modified text skeleton is inserted into a multimedia content item in order to create a customized multimedia content item for the text sample.