Automatic gleaning of semantic information in social networks
View Patent ↗Disclosed are method and apparatus for identifying members of a social network who have a high likelihood of providing a useful response to a query. A query engine examines the personal pages of a set of members and automatically gleans semantic information relevant to the query. From the automatically-gleaned semantic information, a score indicative of the likelihood that the member may provide a useful response is calculated.
1. A method for generating a set of candidates who may provide a useful response to a query submitted by a querier in a first social networking site associated with a first social network, comprising:
receiving the query;
automatically gleaning semantic information from a first personal page in the first social networking site, the first personal page associated with a member of the first social network;
calculating a first score based on the semantic information automatically gleaned from the first personal page, the semantic information being relevant to the query and associated with a plurality of fields on the first personal page, wherein calculating the first score comprises:
assigning a value to each of the plurality of fields on the first personal page based on relevance to the query of information contained in each of the plurality of fields on the first personal page, wherein a value of one of the plurality of fields on the first personal page is not equal to a value of one other of the plurality of fields on the first personal page, and
determining a statistical probability based on values of the plurality of fields on the first personal page;
finding an identifier of a second personal page uniform resource locator on the first personal page identifying a second personal page associated with the member in a second social networking site;
automatically gleaning semantic information from the second personal page;
calculating a second score based on the semantic information automatically gleaned from the second personal page;
adding the member to the set of candidates based on the first score and the second score; and
automatically sending a message containing the query to the set of candidates.
2. The method of claim 1 , wherein calculating the second score comprises:
assigning a value to each of a plurality of fields on the second personal page based on relevance to the query of information contained in each of the plurality of fields on the second personal page, wherein a value of one of the plurality of fields on the second personal page is not equal to a value of one other of the plurality of fields on the second personal page; and
determining a statistical probability based on values of the plurality of fields on the second personal page.
3. The method of claim 1 , wherein adding the member to the set of candidates based on the first score and the second score comprises:
comparing the first score to a threshold score;
comparing the second score to the threshold score; and
adding the member to the set of candidates when the first score and the second score are greater than the threshold score.
4. The method of claim 1 , further comprising:
rank-ordering the set of candidates based on the first score associated with each specific candidate in the set of candidates and the second score associated with each specific candidate in the set of candidates.
5. The method of claim 1 , wherein the member is an addressee in a set of addressees.
6. The method of claim 5 , wherein the set of addressees is based on the query.
7. The method of claim 5 , wherein the set of addressees is a predetermined set of addressees.
8. The method of claim 7 , wherein the predetermined set of addressees comprises at least one of:
a set of friends associated with the querier;
a group associated with the querier; and
a set of addressees specified by the querier.
9. The method of claim 5 , further comprising:
for each addressee in the set of addressees:
automatically gleaning semantic information from each of the first personal page and the second personal page associated with the addressee;
calculating the first score and the second score associated with the addressee, the first score based on the semantic information automatically gleaned from the first personal page associated with the addressee and the second score based on the semantic information automatically gleaned from the second personal page associated with the addressee; and
adding the addressee to the set of candidates based on the first score associated with the addressee and based on the second score associated with the addressee.
10. The method of claim 1 , further comprising:
finding a friend on the first personal page associated with the member;
automatically gleaning semantic information from a third personal page, the third personal page associated with the friend;
calculating a third score based on the semantic information automatically gleaned from the third personal page, wherein calculating the third score comprises:
assigning a value to each of a plurality of fields on the third personal page based on relevance to the query of information contained in each of the plurality of fields on the third personal page, wherein a value of one of the plurality of fields on the third personal page is not equal to a value of one other of the plurality of fields on the third personal page, and
determining a statistical probability based on values of the plurality of fields on the third personal page; and
adding the friend to the set of candidates based on the third score.
11. An apparatus comprising;
a processor; and
a memory to store computer program instructions, the computer program instructions when executed on the processor cause the processor to perform operations comprising:
receiving the query;
automatically gleaning semantic information from a first personal page in the first social networking site, the first personal page associated with a member of the first social network;
calculating a first score based on the semantic information automatically gleaned from the first personal page, the semantic information being relevant to the query and associated with a plurality of fields on the first personal page, wherein calculating the first score comprises:
assigning a value to each of the plurality of fields on the first personal page based on relevance to the query of information contained in each of the plurality of fields on the first personal page, wherein a value of one of the plurality of fields on the first personal page is not equal to a value of one other of the plurality of fields on the first personal page, and
determining a statistical probability based on values of the plurality of fields on the first personal page;
finding an identifier of a second personal page uniform resource locator on the first personal page identifying a second personal page associated with the member in a second social networking site;
automatically gleaning semantic information from the second personal page;
calculating a second score based on the semantic information automatically gleaned from the second personal page;
adding the member to the set of candidates based on the first score and the second score; and
automatically sending a message containing the query to the set of candidates.
12. The apparatus of claim 11 , wherein calculating the second score comprises:
assigning a value to each of a plurality of fields on the second personal page based on relevance to the query of information contained in each of the plurality of fields on the second personal page, wherein a value of one of the plurality of fields on the second personal page is not equal to a value of one other of the plurality of fields on the second personal page; and
determining a statistical probability based on values of the plurality of fields on the second personal page.
13. The apparatus of claim 11 , wherein the member is an addressee in a set of addressees.
14. The apparatus of claim 13 , wherein the set of addressees is based on the query.
15. The apparatus of claim 13 , wherein the computer program instructions which, when executed on the processor, cause the processor to perform further operations comprising:
for each addressee in the set of addressees:
automatically gleaning semantic information from each of the first personal page and the second personal page associated with the addressee;
calculating the first score and the second score associated with the addressee, the first score based on the semantic information automatically gleaned from the first personal page associated with the addressee and the second score based on the semantic information automatically gleaned from the second personal page associated with the addressee; and
adding the addressee to the set of candidates based on the first score associated with the addressee and based on the second score associated with the addressee.
16. The apparatus of claim 11 , wherein the computer program instructions which, when executed on the processor, cause the processor to perform further operations comprising:
finding a friend on the first personal page associated with the member;
automatically gleaning semantic information from a third personal page, the third personal page associated with the friend;
calculating a third score based on the semantic information automatically gleaned from the third personal page, wherein calculating the third score comprises:
assigning a value to each of a plurality of fields on the third personal page based on relevance to the query of information contained in each of the plurality of fields on the third personal page, wherein a value of one of the plurality of fields on the third personal page is not equal to a value of one other of the plurality of fields on the third personal page, and
determining a statistical probability based on values of the plurality of fields on the third personal page; and
adding the friend to the set of candidates based on the third score.
17. A tangible computer readable medium storing computer program instructions for generating a set of candidates who may provide a useful response to a query submitted by a querier in a first social networking site associated with a first social network, which, when executed on a processor, cause the processor to perform operations comprising:
receiving the query;
automatically gleaning semantic information from a first personal page in the first social networking site, the first personal page associated with a member of the first social network;
calculating a first score based on the semantic information automatically gleaned from the first personal page, the semantic information being relevant to the query and associated with a plurality of fields on the first personal page, wherein calculating the first score comprises:
assigning a value to each of the plurality of fields on the first personal page based on relevance to the query of information contained in each of the plurality of fields on the first personal page, wherein a value of one of the plurality of fields on the first personal page is not equal to a value of one other of the plurality of fields on the first personal page, and
determining a statistical probability based on values of the plurality of fields on the first personal page;
finding an identifier of a second personal page uniform resource locator on the first personal page identifying a second personal page associated with the member in a second social networking site;
automatically gleaning semantic information from the second personal page;
calculating a second score based on the semantic information automatically gleaned from the second personal page;
adding the member to the set of candidates based on the first score and the second score; and
automatically sending a message containing the query to the set of candidates.
18. The tangible computer readable medium of claim 17 , wherein calculating the second score comprises:
assigning a value to each of a plurality of fields on the second personal page based on relevance to the query of information contained in each of the plurality of fields on the second personal page, wherein a value of one of the plurality of fields on the second personal page is not equal to a value of one other of the plurality of fields on the second personal page; and
determining a statistical probability based on values of the plurality of fields on the second personal page.
19. The tangible computer readable medium of claim 17 , wherein the computer program instructions which, when executed by the processor, cause the processor to perform further operations comprising:
finding a friend on the first personal page associated with the member;
automatically gleaning semantic information from a third personal page, the third personal page associated with the friend;
calculating a third score based on the semantic information automatically gleaned from the third personal page, wherein calculating the third score comprises:
assigning a value to each of a plurality of fields on the third personal page based on relevance to the query of information contained in each of the plurality of fields on the third personal page, wherein a value of one of the plurality of fields on the third personal page is not equal to a value of one other of the plurality of fields on the third personal page, and
determining a statistical probability based on values of the plurality of fields on the third personal page; and
adding the friend to the set of candidates based on the third score.
20. The tangible computer readable medium of claim 17 , wherein the computer program instructions which, when executed by the processor, cause the processor to perform further operations comprising:
rank-ordering the set of candidates based on the first score associated with each specific candidate in the set of candidates and based on the second score associated with each specific candidate in the set of candidates.