Coefficients attribution for different objects based on natural language processing
In one embodiment, a method includes receiving free-form text from users of an online social network, wherein the free-form text of each input corresponds to an object associated with the online social network; determining a plurality of affinity declarations from the free-form text that are associated with the object; determining, for each affinity declaration, an affinity coefficient between a respective user and the object; and upon determining that the affinity coefficient for a threshold number of users exceeds a threshold value, creating a page associated with the object for display on the online social network.
1. A method comprising:
receiving, from each of a plurality of client devices that each correspond to a plurality of users of an online social network, a plurality of inputs that comprise free-form text, wherein the free-form text of each input corresponds to an object associated with the online social network;
determining, through application of natural-language processing of the free-form text, a plurality of affinity declarations associated with the object, wherein each affinity declaration is comprised in the free-form text;
determining, for each affinity declaration, an affinity coefficient between a respective user of the plurality of users and the object;
for each of the determined affinity coefficients, dynamically adjusting the determined affinity coefficient based on social-networking information of the respective user, wherein the social-networking information reinforces or reduces the determined affinity coefficient; and
upon determining that the determined affinity coefficient for a threshold number of the respective users exceeds a threshold value, creating a hub page associated with the object for display on the online social network.
2. The method of claim 1 , further comprising:
publishing the hub page in association with the online social network; and
sending, to each of one or more of the client devices, a recommendation to interact with the published hub page.
3. The method of claim 2 , wherein the sending the recommendation is based on the affinity coefficient between the respective user and the object.
4. The method of claim 1 , wherein the object is associated with a person, location, company, or organization.
5. The method of claim 1 , further comprising:
accessing a social graph comprising a plurality of nodes and a plurality of edges connecting the nodes, each of the edges between two of the nodes representing a single degree of separation between them, the nodes comprising:
a plurality of user nodes that each correspond to one of the plurality of users of the online social network; and
a plurality of concept nodes that each correspond to a concept associated with the online social network.
6. The method of claim 5 , wherein the creating the hub page associated with the object comprises creating a concept node corresponding to the object.
7. The method of claim 1 , wherein the affinity coefficient is based on natural language processing.
8. The method of claim 1 , wherein the determining an affinity coefficient between the respective user and the object comprises extracting context data from the free-form text, the context data comprising a time, a location, or an interaction with the object that is associated with the free-form text.
9. The method of claim 1 , wherein the object is a first object and is a more specific instance of a second object, wherein the second object is already associated with a page displayed on the online social network.
10. One or more computer-readable non-transitory storage media embodying software that is operable when executed to:
receive, from each of a plurality of client devices that each correspond to a plurality of users of an online social network, a plurality of inputs that comprise free-form text, wherein the free-form text of each input corresponds to an object associated with the online social network;
determine, through application of natural-language processing of the free-form text, a plurality of affinity declarations associated with the object, wherein each affinity declaration is comprised in the free-form text;
determine, for each affinity declaration, an affinity coefficient between a respective user of the plurality of users and the object; and
for each of the determined affinity coefficients dynamically adjust the determined affinity coefficient based on social-networking information of the respective user wherein the social-networking information reinforces or reduces the determined affinity coefficient; and
upon determining that the determined affinity coefficient for a threshold number of the respective users exceeds a threshold value, create a hub page associated with the object for display on the online social network.
11. The media of claim 10 , wherein the software is further operable when executed to:
publish the hub page in association with the online social network; and
send, to each of one or more of the client devices, a recommendation to interact with the published hub page.
12. The media of claim 11 , wherein the sending the recommendation is based on the affinity coefficient between the respective user and the object.
13. The media of claim 10 , wherein the object is associated with a person, location, company, or organization.
14. The media of claim 10 , wherein the software is further operable when executed to:
access a social graph comprising a plurality of nodes and a plurality of edges connecting the nodes, each of the edges between two of the nodes representing a single degree of separation between them, the nodes comprising:
a plurality of user nodes that each correspond to one of the plurality of users of the online social network; and
a plurality of concept nodes that each correspond to a concept associated with the online social network.
15. The media of claim 14 , wherein the creating the page associated with the object comprises creating a concept node corresponding to the object.
16. The media of claim 10 , wherein the affinity coefficient is based on natural language processing.
17. A system comprising: one or more processors; and a memory coupled to the processors comprising instructions executable by the processors, the processors being operable when executing the instructions to:
receive, from each of a plurality of client devices that each correspond to a plurality of users of an online social network, a plurality of inputs that comprise free-form text, wherein the free-form text of each input corresponds to an object associated with the online social network;
determine, through application of natural-language processing of the free-form text, a plurality of affinity declarations associated with the object, wherein each affinity declaration is comprised in the free-form text;
determine, for each affinity declaration, an affinity coefficient between a respective user of the plurality of users and the object; and
upon determining that the affinity coefficient for a threshold number of users exceeds a threshold value, create a page associated with the object for display on the online social network.
18. The system of claim 17 , wherein the processors are further operable when executing the instructions to:
publish the page in association with the online social network; and
send, to each of one or more of the client devices, a recommendation to interact with the published page.
19. The system of claim 17 , wherein the determining an affinity coefficient between the respective user and the object comprises extracting context data from the free-form text, the context data comprising a time, a location, or an interaction with the object that is associated with the free-form text.
20. The system of claim 17 , wherein the object is a first object and is a more specific instance of a second object, wherein the second object is already associated with a page displayed on the online social network.