Video sentiment analysis tool for video messaging

Abstract

Embodiments of the invention provide a method, system and computer program product for video sentiment analysis in video messaging. In an embodiment of the invention, a method for video sentiment analysis in video messaging includes receiving different video contributions to a thread in a social system executing in memory of a computer and sensing from a plurality of the video contributions a contributor sentiment. Thereafter, a sentiment value for the different video contributions is computed and a sentiment value for a selected one of the video contributions is displayed in a user interface to the thread for an end user contributing a new video contribution to the thread.

1 . A method for video sentiment analysis in video messaging, the method comprising:
 receiving different video contributions to a thread in a social system executing in memory of a computer;   sensing from a plurality of the video contributions a contributor sentiment;   determining a contributor sentiment from a plurality of video contributions;   computing a sentiment value for the sensed contributor sentiment of the different video contributions;   comparing the new sentiment value to the sentiment value of the thread; and,   in response to determining that a threshold disparity exists between the compared values, displaying in a user interface to the thread a prompt to upload a different video contribution with a sentiment more consistent with the sentiment of the thread.   
     
     
         2 . The method of  claim 1 , wherein the sensing is facial recognition in order to determine an emotion of a contributor of a corresponding one of the video contributions. 
     
     
         3 . The method of  claim 1 , wherein the sensing is a sound analysis in order to determine a tone of a contributor of a corresponding one of the video contributions. 
     
     
         4 . The method of  claim 1 , wherein the sensing is a textual parsing of content of each of the video contributions in order to determine a level of jargon of a corresponding one of the video contributions. 
     
     
         5 . The method of  claim 1 , wherein the sensing is each of facial recognition in order to determine an emotion of a contributor of each of the video contributions, a sound analysis in order to determine a tone of a contributor of each of the video contributions, and a textual parsing of content of each of the video contributions in order to determine a level of jargon of a corresponding one of the video contributions, and wherein the computed sentiment for the selected one of the video contributions is a combination of a numerical value computed for a sensed emotion for the selected one of the video contributions, a numerical value computed for a level of jargon for the selected one of the video contributions and a numerical value computed for a level of sarcasm for the selected one of the video contributions. 
     
     
         6 . The method of  claim 1 , further comprising displaying in the user interface to the thread an aggregate sentiment for all of the video contributions. 
     
     
         7 . The method of  claim 1 , further comprising:
 receiving from a contributor a reply video contribution to the thread;   sensing from the reply video contribution a contributor sentiment;   computing a sentiment value for the reply video contribution; and,   prompting the contributor to provide a different video contributor responsive or edit video response to a determination of a threshold inconsistency between the sentiment value computed for the reply video contribution and the sentiment value computed for the different video contributions.   
     
     
         8 . A data processing system configured for video sentiment analysis in video messaging, the system comprising:
 a computer with memory and at least one processor;   a social system executing in the memory of the computer; and,   a video sentiment analysis module comprising program code executing in the memory of the computer, the program code performing:   receiving different video contributions to a thread in a social system executing in memory of a computer;   sensing from a plurality of the video contributions a contributor sentiment   determining a contributor sentiment from a plurality of video contributions;   computing a sentiment for the sensed contributor sentiment of the different video contributions;   comparing the new sentiment value to the sentiment value of the thread; and   in response to determining that a threshold disparity exists between the compared values, displaying in a user interface to the thread a prompt to upload a different video contribution with a sentiment more consistent with the sentiment of the thread.   
     
     
         9 . The system of  claim 8 , wherein the sensing is facial recognition in order to determine an emotion of a contributor of a corresponding one of the video contributions. 
     
     
         10 . The system of  claim 8 , wherein the sensing is a sound analysis in order to determine a tone of a contributor of a corresponding one of the video contributions. 
     
     
         11 . The system of  claim 8 , wherein the sensing is a textual parsing of content of each of the video contributions in order to determine a level of jargon of a corresponding one of the video contributions. 
     
     
         12 . The system of  claim 8 , wherein the sensing is each of facial recognition in order to determine an emotion of a contributor of each of the video contributions, a sound analysis in order to determine a tone of a contributor of each of the video contributions, and a textual parsing of content of each of the video contributions in order to determine a level of jargon of a corresponding one of the video contributions, and wherein the computed sentiment for the selected one of the video contributions is a combination of a numerical value computed for a sensed emotion for the selected one of the video contributions, a numerical value computed for a level of jargon for the selected one of the video contributions and a numerical value computed for a level of sarcasm for the selected one of the video contributions. 
     
     
         13 . The system of  claim 8 , wherein the program code further displays in the user interface to the thread an aggregate sentiment for all of the video contributions. 
     
     
         14 . A computer program product for video sentiment analysis in video messaging, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a device to cause the device to perform a method comprising:
 receiving different video contributions to a thread in a social system executing in memory of a computer;   sensing from a plurality of the video contributions a contributor sentiment;   determining a contributor sentiment from a plurality of video contributions;   computing a sentiment value for the sensed contributor sentiment of the different video contributions;   comparing the new sentiment value to the sentiment value of the thread; and,   in response to determining that a threshold disparity exists between the compared values, displaying in a user interface to the thread a prompt to upload a different video contribution with a sentiment more consistent with the sentiment of the thread.   
     
     
         15 . The computer program product of  claim 14 , wherein the sensing is facial recognition in order to determine an emotion of a contributor of a corresponding one of the video contributions. 
     
     
         16 . The computer program product of  claim 14 , wherein the sensing is a sound analysis in order to determine a tone of a contributor of a corresponding one of the video contributions. 
     
     
         17 . The computer program product of  claim 14 , wherein the sensing is a textual parsing of content of each of the video contributions in order to determine a level of jargon of a corresponding one of the video contributions. 
     
     
         18 . The computer program product of  claim 14 , wherein the sensing is each of facial recognition in order to determine an emotion of a contributor of each of the video contributions, a sound analysis in order to determine a tone of a contributor of each of the video contributions, and a textual parsing of content of each of the video contributions in order to determine a level of jargon of a corresponding one of the video contributions, and wherein the computed sentiment for the selected one of the video contributions is a combination of a numerical value computed for a sensed emotion for the selected one of the video contributions, a numerical value computed for a level of jargon for the selected one of the video contributions and a numerical value computed for a level of sarcasm for the selected one of the video contributions. 
     
     
         19 . The computer program product of  claim 14 , wherein the method further includes displaying in the user interface to the thread an aggregate sentiment for all of the video contributions. 
     
     
         20 . The computer program product of  claim 14 , wherein the method further includes:
 receiving from a contributor a reply video contribution to the thread;   sensing from the reply video contribution a contributor sentiment;   computing a sentiment value for the reply video contribution; and,   prompting the contributor to provide a different video contribution responsive to a determination of a threshold inconsistency between the sentiment value computed for the reply video contribution and the sentiment value computed for the different video contributions.