EXPLOITING MULTI-MODAL AFFECT AND SEMANTICS TO ASSESS THE PERSUASIVENESS OF A VIDEO
First Claim
Patent Images
1. A method for determining the persuasiveness of a multimedia item, the method comprising, with a computing system comprising one or more computing devices:
- extracting a plurality of features from at least a portion of the multimedia item, the extracted features comprising a visual feature or an audio feature;
identifying a text item associated with the multimedia item;
extracting text from at least a portion of the text item;
analyzing the extracted features and the extracted text using a video persuasiveness model; and
generating a persuasiveness indication for the multimedia item based on the analysis using the video persuasiveness model.
2 Assignments
0 Petitions
Accused Products
Abstract
Technologies to detect persuasive multimedia content by using affective and semantic concepts extracted from the audio-visual content as well as the sentiment of associated comments are disclosed. The multimedia content is analyzed and compared with a persuasiveness model.
-
Citations
20 Claims
-
1. A method for determining the persuasiveness of a multimedia item, the method comprising, with a computing system comprising one or more computing devices:
-
extracting a plurality of features from at least a portion of the multimedia item, the extracted features comprising a visual feature or an audio feature; identifying a text item associated with the multimedia item; extracting text from at least a portion of the text item; analyzing the extracted features and the extracted text using a video persuasiveness model; and generating a persuasiveness indication for the multimedia item based on the analysis using the video persuasiveness model. - View Dependent Claims (2, 3, 4, 5, 6)
-
-
7. A multimodal data analyzer comprising instructions embodied in one or more non-transitory machine accessible storage media, the multimodal data analyzer configured to cause a computing system comprising one or more computing devices to:
-
extract a plurality of features from at least a portion of the multimedia item, the extracted features comprising a visual feature or an audio feature; identify a text item associated with the multimedia item; extract text from at least a portion of the text item; analyze the extracted features and the extracted text using a video persuasiveness model; and generate a persuasiveness indication for the multimedia item based on the analysis using the video persuasiveness model. - View Dependent Claims (8, 9, 10, 11, 12)
-
-
13. A method for building a model of audience impact of a video, with a computing system comprising one or more computing devices, the method comprising:
-
accessing a plurality of multimedia items and text items associated with the multimedia items; extracting audio and visual features from the multimedia items; extracting text from the text items; annotating the extracted audio features, visual features, and text items with an indicator of audience impact based on a semantic analysis or an affective analysis of the visual features, an affective analysis of the audio features, and a sentiment analysis of the extracted text; classifying each of the multimedia items based on a combination of the annotations; and storing the classifications in the audience impact model. - View Dependent Claims (14, 15, 16)
-
-
17. A video classifier device comprising instructions embodied in one or more non-transitory machine accessible storage media, the video classifier device configured to cause a computing system comprising one or more computing devices to:
-
access a plurality of multimedia items and text items associated with the multimedia items; extract audio and visual features from the multimedia items; extract text from the text items; annotate the extracted audio features, visual features, and text items with an indicator of audience impact based on a semantic analysis of the visual features, an affective analysis of the visual features, an affective analysis of the audio features, and a sentiment analysis of the extracted text; classify each of the multimedia items based on a combination of the annotations; and store the classifications in an audience impact model. - View Dependent Claims (18, 19, 20)
-
Specification