Factcheck streaming in VR collaboration
An embodiment for factcheck streaming in a virtual reality (VR) collaboration is provided. The embodiment may include receiving a video of a VR collaboration and one or more inputs from a user. The embodiment may also include identifying a pre-determined boundary of the VR collaboration. The embodiment may further include executing a factcheck of one or more items of content. The embodiment may also include identifying at least one factually inaccurate item of content. The embodiment may further include in response to determining the at least one factually inaccurate item of content is able to be replaced, generating, by a pre-trained generative adversarial network (GAN) model, at least one factually accurate item of content. The embodiment may also include replacing the at least one factually inaccurate item of content with the generated at least one factually accurate item of content in the VR collaboration.
1 . A computer-based method of factcheck streaming in a virtual reality (VR) collaboration, the method comprising:
receiving a video of a VR collaboration and one or more inputs from a user relating to the video;
identifying a pre-determined boundary of the VR collaboration based on the one or more inputs;
executing a factcheck of one or more items of content within the pre-determined boundary;
identifying at least one factually inaccurate item of content in the one or more items of content;
determining whether the at least one factually inaccurate item of content is able to be replaced with at least one factually accurate item of content; and
in response to determining the at least one factually inaccurate item of content is able to be replaced:
generating, by a pre-trained generative adversarial network (GAN) model, the at least one factually accurate item of content; and
replacing the at least one factually inaccurate item of content with the generated at least one factually accurate item of content in the VR collaboration.
2 . The computer-based method of claim 1 , further comprising:
in response to determining the at least one factually inaccurate item of content is not able to be replaced:
removing, by the pre-trained GAN model, the at least one factually inaccurate item of content from the VR collaboration.
3 . The computer-based method of claim 2 , wherein identifying the pre-determined boundary of the VR collaboration further comprises:
identifying one or more types of content to factcheck in the VR collaboration based on the one or more inputs.
4 . The computer-based method of claim 2 , wherein identifying the at least one factually inaccurate item of content further comprises:
in response to determining the at least one factually inaccurate item of content is spoken content, adapting a color of a portion of text corresponding to the at least one factually inaccurate item of content in a transcript of the VR collaboration.
5 . The computer-based method of claim 2 , wherein replacing the at least one factually inaccurate item of content further comprises:
adapting a gesture of an avatar in the VR collaboration in response to determining the gesture acknowledges the at least one factually inaccurate item of content.
6 . The computer-based method of claim 2 , wherein executing the factcheck of the one or more items of content further comprises:
splitting the video of the VR collaboration into an audio part and a visual part, wherein the visual part is further split into a non-spoken text part and a visual object part, and wherein the factcheck is executed on the audio part and the visual part separately.
7 . The computer-based method of claim 6 , wherein the factcheck is executed on a frame-by-frame basis.
8 . A computer system, the computer system comprising:
one or more processors, one or more computer-readable memories, one or more computer-readable tangible storage medium, and program instructions stored on at least one of the one or more computer-readable tangible storage medium for execution by at least one of the one or more processors via at least one of the one or more computer-readable memories, wherein the computer system is capable of performing a method comprising:
receiving a video of a VR collaboration and one or more inputs from a user relating to the video;
identifying a pre-determined boundary of the VR collaboration based on the one or more inputs;
executing a factcheck of one or more items of content within the pre-determined boundary;
identifying at least one factually inaccurate item of content in the one or more items of content;
determining whether the at least one factually inaccurate item of content is able to be replaced with at least one factually accurate item of content; and
in response to determining the at least one factually inaccurate item of content is able to be replaced:
generating, by a pre-trained GAN model, the at least one factually accurate item of content; and
replacing the at least one factually inaccurate item of content with the generated at least one factually accurate item of content in the VR collaboration.
9 . The computer system of claim 8 , the method further comprising:
in response to determining the at least one factually inaccurate item of content is not able to be replaced:
removing, by the pre-trained GAN model, the at least one factually inaccurate item of content from the VR collaboration.
10 . The computer system of claim 9 , wherein identifying the pre-determined boundary of the VR collaboration further comprises:
identifying one or more types of content to factcheck in the VR collaboration based on the one or more inputs.
11 . The computer system of claim 9 , wherein identifying the at least one factually inaccurate item of content further comprises:
in response to determining the at least one factually inaccurate item of content is spoken content, adapting a color of a portion of text corresponding to the at least one factually inaccurate item of content in a transcript of the VR collaboration.
12 . The computer system of claim 9 , wherein replacing the at least one factually inaccurate item of content further comprises:
adapting a gesture of an avatar in the VR collaboration in response to determining the gesture acknowledges the at least one factually inaccurate item of content.
13 . The computer system of claim 9 , wherein executing the factcheck of the one or more items of content further comprises:
splitting the video of the VR collaboration into an audio part and a visual part, wherein the visual part is further split into a non-spoken text part and a visual object part, and wherein the factcheck is executed on the audio part and the visual part separately.
14 . The computer system of claim 13 , wherein the factcheck is executed on a frame-by-frame basis.
15 . A computer program product, the computer program product comprising:
one or more computer-readable tangible storage medium and program instructions stored on at least one of the one or more computer-readable tangible storage medium, the program instructions executable by a processor capable of performing a method, the method comprising:
receiving a video of a VR collaboration and one or more inputs from a user relating to the video;
identifying a pre-determined boundary of the VR collaboration based on the one or more inputs;
executing a factcheck of one or more items of content within the pre-determined boundary;
identifying at least one factually inaccurate item of content in the one or more items of content;
determining whether the at least one factually inaccurate item of content is able to be replaced with at least one factually accurate item of content; and
in response to determining the at least one factually inaccurate item of content is able to be replaced:
generating, by a pre-trained GAN model, the at least one factually accurate item of content; and
replacing the at least one factually inaccurate item of content with the generated at least one factually accurate item of content in the VR collaboration.
16 . The computer program product of claim 15 , the method further comprising:
in response to determining the at least one factually inaccurate item of content is not able to be replaced:
removing, by the pre-trained GAN model, the at least one factually inaccurate item of content from the VR collaboration.
17 . The computer program product of claim 16 , wherein identifying the pre-determined boundary of the VR collaboration further comprises:
identifying one or more types of content to factcheck in the VR collaboration based on the one or more inputs.
18 . The computer program product of claim 16 , wherein identifying the at least one factually inaccurate item of content further comprises:
in response to determining the at least one factually inaccurate item of content is spoken content, adapting a color of a portion of text corresponding to the at least one factually inaccurate item of content in a transcript of the VR collaboration.
19 . The computer program product of claim 16 , wherein replacing the at least one factually inaccurate item of content further comprises:
adapting a gesture of an avatar in the VR collaboration in response to determining the gesture acknowledges the at least one factually inaccurate item of content.
20 . The computer program product of claim 16 , wherein executing the factcheck of the one or more items of content further comprises:
splitting the video of the VR collaboration into an audio part and a visual part, wherein the visual part is further split into a non-spoken text part and a visual object part, and wherein the factcheck is executed on the audio part and the visual part separately.