Classifying post types on online social networks

One or more computer-readable non-transitory storage media embodying software that is operable when executed to:

• receive, by one or more computing devices from a third-party content provider, a link to a structured webpage document on an external server that is external to the online social network, via a first graphical user interface of the online social network, the link being associated with a post of the online social network by the third-party content provider;
• retrieve, by the one or more computing devices, the structured webpage document from the external server, the structured webpage document comprising content and one or more input fields in a graphical user interface of the structured webpage document;
• extract, by the one or more computing devices from the structured webpage document, a set of information of the content and of the input fields of the structured webpage document;
• evaluate, by the one or more computing devices, the extracted set of information from the structured webpage document to determine one or more feature-values of the structured webpage document;
• automatically classify, by the one or more computing devices using a machine-learning model, comprising one or more or a neural network or a support vector machine, and based on the determined one or more feature-values, the structured webpage document as an external lead-generation type webpage;
• send, to the third-party content provider responsive to determining that the machine-learning model has classified the structured webpage document as an external lead-generation type webpage, a notification comprising instructions for creating an internal lead-generation type post on the online social network corresponding to the external lead-generation type webpage, wherein the internal lead-generation type post is operable to extract social-networking information associated with users from an internal server of the online social network and auto-populate one or more fields of the internal lead-generation type post with the;
• and
• create, by the one or more computing devices, the internal lead generation type post on the online social network corresponding to the external lead-generation type webpage with the first graphical user interface of the online social network or a second graphical user interface of the online social network, wherein the one or more fields of the internal lead-generation type post are auto-populated with the extracted social-networking information and correspond respectively to the one or more input fields of the structured webpage document from the external server.

A system comprising:

• one or more processors;
• and a non-transitory memory coupled to the processors comprising instructions executable by the processors, the processors operable when executing the instructions to:
• receive, by one or more computing devices from a third-party content provider, a link to a structured webpage document on an external server that is external to the online social network, via a first graphical user interface of the online social network, the link being associated with a post of the online social network by the third-party content provider;
• retrieve, by the one or more computing devices, the structured webpage document from the external server, the structured webpage document comprising content and one or more input fields in a graphical user interface of the structured webpage document;
• extract, by the one or more computing devices from the structured document, a set of information of the content and of the input fields of the structured document;
• evaluate, by the one or more computing devices, the extracted set of information from the structured webpage document to determine one or more feature-values of the structured webpage document;
• automatically classify, by the one or more computing devices using a machine-learning model, comprising one or more of a neural network or a support vector machine, and based on the determined one or more feature-values, the structured webpage document as an external lead-generation type webpage;
• send, by the one or more computing devices to the third-party content provider responsive to determining that the machine-learning model has classified the structured webpage document as an external lead-generation type webpage, a notification comprising instructions for creating an internal lead-generation type post on the online social network corresponding to the external lead-generation type webpage, wherein the internal lead-generation type post is operable to extract social-networking information associated with users from an internal server of the online social network;
• and
• create, by the one or more computing devices, the internal lead generation type post on the online social network corresponding to the external lead-generation type webpage with the first graphical user interface of the online social network or a second graphical user interface of the online social network, wherein the one or more fields of the internal lead-generation type post are auto-populated with the extracted social-networking information and correspond respectively to the one or more input fields of the structured webpage document from the external server.