Computer application content detection and feedback

A computer system for automatically detecting and altering inappropriate content on a computing application, comprising:

• one or more processors, one or more computer-readable memories, one or more computer-readable tangible storage devices, and program instructions stored on at least one of the one or more computer-readable tangible storage devices 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:
• in response to detecting an attempt to electronically post content on the computing application, wherein detecting the attempt to electronically post the content further comprises receiving a trigger notification from the computing application indicating that the content has been entered into a dialogue box associated with the computing application and that a user using a computer device has initiated posting the content using the computer device, and before allowing the post to be posted:
• parsing the content, using natural language processing and computer vision algorithms, to identify one or more parts of the content, wherein the one or more parts of the content comprises at least one of text and an image,
• determining whether the one or more parts of the content comprises inappropriate content based on a users context, a public context, and a community context by applying one or more algorithms to the one or more parts of the content based on information associated with one or more computing applications and by predicting whether potential viewers of the one or more parts of the content view the one or more parts as inappropriate based on the applied one or more algorithms,
• wherein predicting whether the potential viewers of the one or more parts of the content view the one or more parts as inappropriate from the users context and the community context further comprises using the one or more algorithms to predict user sentiments with regard to the content from a plurality of users by automatically tracking and extracting online information associated with the plurality of users from one or more user accounts, using the natural language processing and the computer vision algorithms to identify and compare a first set of similar content to the content to be posted based on the tracked and extracted online information associated with the plurality of users from the one or more user accounts, and predicting the user sentiments with regard to the content to be posted by determining the user sentiments toward the first set of similar content using the one or more algorithms including the natural language processing algorithms,
• wherein predicting whether the potential viewers of the one or more parts of the content view the one or more parts as inappropriate from the public context and the community context further comprises using the one or more algorithms to predict public sentiment with regard to the content by automatically tracking websites and applications and extracting publicly available online information unassociated with the plurality of users and the one or more user accounts, using the natural language processing and the computer vision algorithms to identify and compare a second set of similar content to the content to be posted based on the tracked websites, the tracked applications, and the extracted publicly available online information unassociated with the plurality of users and the one or more user accounts, and predicting the public sentiment with regard to the content to be posted by determining the public sentiment toward the second set of similar content using the one or more algorithms including the natural language processing algorithms, and
• generating and displaying both a first set of feedback based on the predicted user sentiment and a second set of feedback based on the predicted public sentiment, wherein generating and displaying the first set of feedback and the second set of feedback further comprises, in response to determining that the one or more parts of the content includes inappropriate content based on the applied one or more algorithms and the potential viewers, generating and displaying revisions altering the attempted post wherein the generated revisions comprise a first set of revisions based on the predicted user sentiment and a second set of revisions based on the predicted public sentiment.

A computer program product for automatically detecting and altering inappropriate content on a computing application, comprising:

• one or more tangible computer-readable storage devices and program instructions stored on at least one of the one or more tangible computer-readable storage devices, the program instructions executable by a processor, the program instructions comprising:
• in response to detecting an attempt to electronically post content on the computing application, wherein detecting the attempt to electronically post the content further comprises receiving a trigger notification from the computing application indicating that the content has been entered into a dialogue box associated with the computing application and that a user using a computer device has initiated posting the content using the computer device, and before allowing the post to be posted:
• parsing the content, using natural language processing and computer vision algorithms, to identify one or more parts of the content, wherein the one or more parts of the content comprises at least one of text and an image,
• determining whether the one or more parts of the content comprises inappropriate content based on a users context, a public context, and a community context by applying one or more algorithms to the one or more parts of the content based on information associated with one or more computing applications and by predicting whether potential viewers of the one or more parts of the content view the one or more parts as inappropriate based on the applied one or more algorithms,
• wherein predicting whether the potential viewers of the one or more parts of the content view the one or more parts as inappropriate from the users context and the community context further comprises using the one or more algorithms to predict user sentiments with regard to the content from a plurality of users by automatically tracking and extracting online information associated with the plurality of users from one or more user accounts, using the natural language processing and the computer vision algorithms to identify and compare a first set of similar content to the content to be posted based on the tracked and extracted online information associated with the plurality of users from the one or more user accounts, and predicting the user sentiments with regard to the content to be posted by determining the user sentiments toward the first set of similar content using the one or more algorithms including the natural language processing algorithms,
• wherein predicting whether the potential viewers of the one or more parts of the content view the one or more parts as inappropriate from the public context and the community context further comprises using the one or more algorithms to predict public sentiment with regard to the content by automatically tracking 11 of 28 websites and applications and extracting publicly available online information unassociated with the plurality of users and the one or more user accounts, using the natural language processing and the computer vision algorithms to identify and compare a second set of similar content to the content to be posted based on the tracked websites, the tracked applications, and the extracted publicly available online information unassociated with the plurality of users and the one or more user accounts, and predicting the public sentiment with regard to the content to be posted by determining the public sentiment toward the second set of similar content using the one or more algorithms including the natural language processing algorithms, and
• generating and displaying both a first set of feedback based on the predicted user sentiment and a second set of feedback based on the predicted public sentiment, wherein generating and displaying the first set of feedback and the second set of feedback further comprises, in response to determining that the one or more parts of the content includes inappropriate content based on the applied one or more algorithms and the potential viewers, generating and displaying revisions altering the attempted post wherein the generated revisions comprise a first set of revisions based on the predicted user sentiment and a second set of revisions based on the predicted public sentiment.