Sentiment analysis in a video conference

Patent metadata

Field	Value
Publication number	US-9646198-B2
Application number	US-201414570500-A
Country	US
Kind code	B2
Filing date	Dec 15, 2014
Priority date	Aug 8, 2014
Publication date	May 9, 2017
Grant date	May 9, 2017

Abstract

In an approach to determine a sentiment of an attendee of a video conference, the computer receives a video of an attendee of a video conference and, then, determines, based, at least in part, on the video of the attendee, a first sentiment of the attendee. Furthermore, in the approach the computer receives an indication of an attendee activity on a first application and determines, based, in part, on the attendee activity whether the first sentiment of the attendee is related to the video conference.

First claim

What is claimed is:

1. A method for determining a sentiment of an attendee of a video conference, the method comprising:
receiving, by one or more computing devices, a video of an attendee of a video conference;
determining, by one or more computing devices, based, at least in part, on the video of the attendee, a first sentiment of the attendee wherein the first sentiment includes at least a sentiment from a sentiment analysis of one or more facial expressions of the attendee and a sentiment from a sentiment analysis of a plurality of the attendee's spoken words;
determining, by one or more computing devices, that the sentiment from the sentiment analysis of the one or more facial expressions of the attendee and the sentiment from the sentiment analysis of the plurality of the attendee's spoken words are different;
receiving, by one or more computing devices, an indication of an attendee activity in at least a first application in a computing device accessed by the attendee;
determining, by one or more computing devices, whether the first sentiment of the attendee is related to the video conference based, in part, on the attendee activity in at least the first application; and
responsive to determining that the first sentiment of the attendee is not related to the video conference, discarding, by one or more computing devices, the first sentiment that is unrelated to the video conference.

2. The method of claim 1 , wherein the indication of attendee activity includes receiving, by one or more computing devices, one or more of attendee inputs to view an activity within at least the first application, receive a message, and generate at least one input to a user interface during the video conference.

3. The method of claim 1 further comprising, displaying, by one or more computing devices, at least one of a sentiment of the attendee or a video of the attendee in the video conference wherein the selection to display at least one of a sentiment of the attendee or a video of the attendee is either input by the attendee or a default setting of the video conference.

4. The method of claim 1 , wherein determining, by one or more computing devices, based, at least in part, on the video of the attendee, the first sentiment of the attendee further comprises using at least one of a facial recognition technique, a natural language processing technique, and a sentiment analysis technique.

5. The method of claim 1 wherein, determining, by one or more computing devices, based, at least in part, on the video of the attendee, a first sentiment of the attendee, further comprises:
compiling, by one or more computing devices, a first sentiment of a plurality of attendees of the video conference to determine a first aggregate sentiment of the plurality of attendees for the video conference, and
displaying, by one or more computing devices, the first aggregated sentiment in the video conference.

6. The method of claim 1 , further comprising:
monitoring, by one or more computing devices, the video of the attendee;
determining, by one or more computer devices, whether the sentiment of the attendee has changed; and
responsive to determining the sentiment of the attendee has changed, determining, by one or more computing devices, a second sentiment of the attendee.

7. The method of claim 1 , wherein determining, by one or more computing devices, the first sentiment of the attendee further comprises:
retrieving, by one or more computing devices, historical sentiment data of the attendee;
determining, by one or more computing devices, based, at least in part, on the historical sentiment data of the attendee, one or more characteristic facial expressions of the attendee; and
comparing, by one or more computing devices, the one or more characteristic facial expressions with the video of the attendee.

8. The method of claim 1 , wherein determining whether the first sentiment of the attendee is related to the video conference based, in part, on the attendee activity further comprises:
evaluating, by one or more computing devices, one or more of user input by the attendee during the video conference, a display of a message during the video conference, a message content, and a display of an output of an activity on at least the first application during the video conference; and
evaluating, by one or more computers, in real-time associated with the attendee activity in the video of the video conference, one or more of facial expressions of the attendee, one or more eye movements of the attendee, the plurality of the attendee's spoken words, at least one real-time sentiment in the video conference, and one or more discussions in the video conference to determine relevance of the first sentiment to the video conference.

9. A computer program product for determining a sentiment of an attendee of a video conference, the computer program product comprising:
one or more computer readable storage media and program instructions stored on the one or more computer readable storage media, the program instructions executable by a processor, the program instructions comprising:
program instructions to receive a video of an attendee of a video conference;
program instructions to determine, based, at least in part, on the video of the attendee, a first sentiment of the attendee wherein the first sentiment includes at least a sentiment from a sentiment analysis of one or more facial expressions of the attendee and a sentiment from a sentiment analysis of a plurality of the attendee's spoken words;
program instructions to determine that the sentiment from the sentiment analysis of the one or more facial expressions of the attendee and the sentiment from the sentiment analysis of the plurality of the attendee's spoken words are different;
program instructions to receive an indication of an attendee activity in at least a first application in a computing device accessed by the attendee;
program instructions to determine whether the first sentiment of the attendee is related to the video conference based, in part, on the attendee activity in at least the first application; and
responsive to determining that the first sentiment of the attendee is not related to the video conference, program instructions to discard the first sentiment that is unrelated to the video conference.

10. The computer program product of claim 9 , wherein receiving an indication of attendee activity include program instructions to receive one or more of attendee inputs to view an activity within at least the first application, receive a message, and generate at least one input to a user interface during the video conference.

11. The computer program product of claim 9 , further comprising program instructions to display at least one of a sentiment of the attendee or a video of the attendee in the video conference wherein the selection to display at least one of a sentiment of the attendee or a video of the attendee is either input by the attendee or a default setting of the video conference.

12. The computer program product of claim 9 , wherein the program instructions to determine, based, at least in part, on the video of the attendee, the first sentiment of the attendee further comprises using at least one of a facial recognition technique, a natural language processing technique, and a sentiment analysis technique.

13. The computer program product of claim 9 , wherein the program instructions to determine, based, at least in part, on the video of the attendee, a first sentiment of the attendee, further comprises:
program instructions to compile a first sentiment of a plurality of attendees of the video conference

Assignees

• IBM

Inventors

• Cunico Hernan A
• Silva Asima

Classifications

• H04L65/1066

  Session management · CPC title

• H04N7/152

  Multipoint control units therefor · CPC title

• G06N5/022

  Knowledge engineering; Knowledge acquisition · CPC title

• H04L65/403

  Arrangements for multi-party communication, e.g. for conferences (data switching systems for conference H04L12/18; arrangements for connecting several subscribers to a common circuit, i.e. affording conference facilities H04M3/56; television conferencing systems H04N7/15) · CPC title

• G06N5/04

  Inference or reasoning models · CPC title