Enhancing video language learning by providing catered context sensitive expressions

A computer-implemented method for enhancing video-based language learning, comprising:

• storing, by a video server accessible by a user device over a network, a plurality of videos including audio that use one or more languages to be learned;
• storing, by a video metadata database, translations of sentences uttered in the plurality of videos, character profiles of characters appearing in the plurality of videos, and mappings between the sentences uttered in the plurality of videos and a learner profile, wherein the learner profile includes profile information relating to a given learner's social information;
• storing, by a learner profile database, learner profiles of learners of the one or more languages;
• finding, by a semantic analyzer and matching engine, for at least a given video from among the plurality of videos and the given learner, alternative sentences for and responsive to the translations of the sentences uttered in the given video that conflict with a respective one of the social information in the learner profiles for the given learner;
• and
• playing back, by a presentation system, the given video and providing, by the presentation system, to the given learner inappropriate sentences together with appropriate sentences for replacing the inappropriate sentences, the inappropriate sentences in a form of the translations of the sentences uttered in the given video that conflict with the respective one of the social information, and the appropriate sentences in a form of the translations thereof.

A computer program product for enhancing video-based language learning, the computer program product comprising a non-transitory computer readable storage medium having program instructions embodied therewith, the program instructions executable by a computer to cause the computer to perform a method comprising:

• storing, by a video server accessible by a user device over a network, a plurality of videos that use one or more languages to be learned;
• storing, by a video metadata database, translations of sentences uttered in the plurality of videos, character profiles of characters appearing in the plurality of videos, and mappings between the sentences uttered in the plurality of videos and a learner profile;
• storing, by a learner profile database, learner profiles of learners of the one or more languages;
• finding, by a semantic analyzer and matching engine, for at least a given video from among the plurality of videos and a given learner, alternative sentences for and responsive to the translations of the sentences uttered in the given video that conflict with a respective one of the learner profiles for the given learner;
• and
• playing back, by a presentation system on the user device, the given video and providing, by the presentation system on the user device, to the given learner inappropriate sentences together with appropriate sentences for replacing the inappropriate sentences, the inappropriate sentences in a form of the translations of the sentences uttered in the given video that conflict with the respective one of the social information, and the appropriate sentences in a form of the translations thereof.