Systems and methods for improved content accessibility scoring

Abstract

Provided herein are methods and systems for improved accessibility scoring for content items. A predicted accessibility score may be based on a plurality of multimodal features present within a content item. The plurality of multimodal features may include video features (e.g., based on video/image analysis), audio features (e.g., based on audio analysis), text-based features (e.g., based on closed-captioning analysis), features indicated by metadata (e.g., duration, genre, etc.), a combination thereof, and/or the like. A predicted accessibility score for a content item may indicate how accessible the content item may be for persons who are visually impaired, hearing impaired, cognitively impaired, etc., as well as for persons who desire to view content that requires less visual attention and/or audio attention as the case may be.

1 . A method comprising:
 receiving, by a computing device, an indication of a selection of a content item by a user, wherein the content item comprises a plurality of features, wherein the user is associated with a disability; and   outputting an indication of an accessibility score associated with the content item, wherein the accessibility score is based on the plurality of features of the content item being perceptible to the user with the disability.   
     
     
         2 . The method of  claim 1 , wherein at least one of: the accessibility score is indicative of a level of perceptibility of the content item for the user, or the plurality of features comprises an amount of dialog. 
     
     
         3 . The method of  claim 1 , wherein the indication of the selection of the content item comprises an indication of the user scrolling over one or more of a description for the content item or an identifier for the content item within a program guide. 
     
     
         4 . The method of  claim 1 , wherein the plurality of features are indicated by metadata associated with the content item. 
     
     
         5 . The method of  claim 1 , further comprising:
 determining, by a trained model, based on the plurality of features of the content item, the accessibility score for the content item.   
     
     
         6 . The method of  claim 1 , wherein the disability comprises visual impairment, wherein the plurality of features further comprise: one or more of a number of languages spoken, an indication of a narrator, an amount of on-screen textual features, or a number of scenes. 
     
     
         7 . The method of  claim 1 , wherein the disability comprises hearing impairment, wherein the plurality of features further comprise a number of characters, an indication of closed-captioning, or a scene change rate. 
     
     
         8 . A method comprising:
 determining, by a computing device, a plurality of features of each content item of a plurality of content items;   training, based on an accessibility score for each content item of the plurality of content items, and based on the plurality of features of each content item of the plurality of content items, a prediction model; and   outputting the prediction model, wherein the prediction model is configured to output an accessibility score for a content item.   
     
     
         9 . The method of  claim 8 , wherein the plurality of features comprise at least one of:
 a video feature,   an audio feature,   a feature indicated by metadata, or   an amount of dialog.   
     
     
         10 . The method of  claim 8 , wherein each accessibility score is indicative of a level of accessibility of the corresponding content item for a user with a disability, wherein the disability comprises one or more of visual impairment or hearing impairment. 
     
     
         11 . The method of  claim 8 , further comprising:
 receiving, at a user device, a selection of the content item; and   sending, by the user device to the computing device, an indication of the selection of the content item.   
     
     
         12 . The method of  claim 11 , further comprising at least one of:
 determining, based on the indication of the selection and the prediction model, the accessibility score for the content item;   sending the accessibility score for the content item; or   causing the accessibility score for the content item to be output.   
     
     
         13 . The method of  claim 11 , wherein the accessibility score for the content item is indicative of a level of accessibility of the content item for a user associated with the user device, and wherein the user is one or more of visually impaired or hearing impaired. 
     
     
         14 . The method of  claim 8 , wherein the plurality of features comprises one or more of:
 secondary audio programming, a number of languages spoken, an indication of a narrator, an amount of on-screen textual features, a number of scenes, a number of characters, an indication of closed-captioning, or a scene change rate   
     
     
         15 . A method comprising:
 determining, by a computing device, based on a plurality of features of a content item, an accessibility score for the content item;   receiving an indication of a selection of the content item by a user device; and   outputting, based on the indication of the selection, the accessibility score at the user device.   
     
     
         16 . The method of  claim 15 , wherein the plurality of features comprises at least one of:
 a video feature,   an audio feature,   a feature indicated by metadata, or   an amount of dialog.   
     
     
         17 . The method of  claim 15 , wherein the accessibility score for the content item is indicative of a level of accessibility of the content item for a user of the user device, wherein the user is one or more of visually impaired or hearing impaired. 
     
     
         18 . The method of  claim 15 , wherein the indication of the selection of the content item comprises an indication of a user of the user device scrolling over one or more of a description for the content item or an identifier for the content item within a program guide. 
     
     
         19 . The method of  claim 15 , further comprising:
 receiving first data associated with a plurality of content items, wherein the first data comprises an accessibility score for each content item of the plurality of video content items;   determining, based on the first data, the plurality of features, wherein each content item of the plurality of content items comprises at least one feature of the plurality of features; and   training, based on the first data, a prediction model, wherein the prediction model is configured to output accessibility scores for content items.   
     
     
         20 . The method of  claim 15 , wherein the plurality of features comprises one or more of: secondary audio programming, a number of languages spoken, an indication of a narrator, an amount of on-screen textual features, a number of scenes, a number of characters, an indication of closed-captioning, or a scene change rate.