Sentiment analysis of content using expression recognition
US11393250B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Jun 21, 2020 |
| Grant date | Jul 19, 2022 |
| Priority date | — |
| Expiry date | Apr 1, 2041 |
Classification
- Technology area (CPC H)Electricity
- CPC primaryH04N7/141
- WIPO fieldAudio-visual technology
- WIPO sectorElectrical engineering
Abstract
A computerized method for providing a sentiment score by evaluating expressions of participants during a video meeting is provided herein. The computerized method comprising: a Sentiment Analysis (SA) module. The SA module is: (i) retrieving one or more recordings of a video meeting from the database of video meeting recordings of each participant in the video meeting and associating the one or more recordings with a participant; (ii) dividing each retrieved recording into segments; (iii) processing the segments in a Facial Expression Recognition (FER) system to associate each segment with a timestamped sequence of expressions for each participant in the video meeting; and (iv) processing each segment in an Artificial Neural Network (ANN) having a dense layer, by applying a prebuilt and pretrained deep learning model, to yield a sentiment score for each statement for each participant.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.