Method and system for expertise mapping based on user activity in recommender systems
View Patent ↗The system and method analyzes activities of users in a recommender system to identify experts. Two types of experts may be identified: authoritative experts and hub experts. An authoritative expert is a user who creates items or documents in a given field that are acted upon by a large number of users within a community who are well connected in the given field. A hub expert is a user who is aware of important items or documents within a given field and uses, works or acts upon items or documents produced by authoritative experts. The system and method also identifies authoritative items (e.g., documents). An authoritative item or document is one which has been acted upon by a large number of users within a community who are well connected in the given field (i.e., hub experts).
1. A method for identifying hub experts within a community of users and authoritative documents in a recommender system, comprising:
identifying documents in a particular field provided by users within the community;
for each identified document:
determining which users within the community have acted upon the identified document;
determining which of the users who have acted upon the identified document are aware of other relevant documents in the particular field and have not directly produced documents in the particular field; and
defining those users as hub experts in the particular field;
determining which identified documents have been acted upon by a predetermined number of hub experts;
defining those documents as authoritative documents; and
associating the hub experts with the authoritative documents;
wherein the steps of defining the hub experts and authoritative documents comprise:
defining a connectivity matrix M, wherein element M ij is non-zero if and only if there is an arc from node i to node j;
wherein for a given node i, a i is an authority value and h i is a hub value, such that:
a
i
=
∑
j
M
ji
h
j
and
h
i
=
∑
j
M
ij
a
j
whose solutions are the principal eigenvectors of M′M_ and MM′, respectively; and
defining vectors a=[a 1 , a 2 , . . . a n ]′ and h=[h 1 , h 2 , . . . h n ]′, such that a=M′h=M′Ma, and h=Ma=MM′h
wherein node I represents an authoritative document and node j represents a hub expert; and wherein a represents an authority value for an authoritative document and wherein h represents a hub value for a hub expert;
generating a list of hub experts associated with the authoritative documents.
2. The method of claim 1 , further comprising associating names of the hub experts with the authoritative documents.
3. The method of claim 1 , acting upon the document comprises one of reading the document, reviewing the document, commenting on the document and recommending the document.
4. The method of claim 3 , wherein recommending the document comprises submitting a numerical rating.
5. The method of claim 3 , wherein recommending the document comprises a submitting a numerical rating and a comment.
6. The method of claim 1 , wherein M ij is 1 if and only if there is an arc from node i to node j.
7. The method of claim 1 , wherein M ij is max-|rij-Rj|, where max denotes the maximal rating possible, rij denotes the rating of user i for document j and Rj denotes the average rating of document j so far.
8. A method for identifying hub experts and authoritative experts within a community of users in a recommender system, comprising:
identifying documents in a particular field created by users within the community;
for each identified document:
determining which users within the community have acted upon the identified document;
determining which of the users who have acted upon the identified document are aware of other relevant documents in the particular field and have not directly produced documents in the particular field; and
defining those users as hub experts in the particular field;
determining which users creating identified documents have had their identified documents acted upon by a predetermined number of hub experts;
defining those users as authoritative experts; and
associating the hub experts with the authoritative experts;
wherein the steps of defining hub experts and authoritative experts comprise:
defining a connectivity matrix M, wherein element M ij is non-zero if and only if there is an arc from node i to node j;
wherein for a given node i, a i is an “authority” value and h i is a “hub” value, such that:
a
i
=
∑
j
M
ji
h
j
and
h
i
=
∑
j
M
ij
a
j
whose solutions are the principal eigenvectors of M′M_ and MM′, respectively; and
defining vectors a=[a 1 , a 2 , . . . a n ]′ and h=[h 1 , h 2 , . . . h n ]′ such that a=M′h=M′Ma, and h=Ma=MM′h
wherein node I represents an authoritative expert and node j represents a hub expert; and
wherein a represents an authority value for an authoritative expert and wherein h represents a hub value for a hub expert;
generating a list of hub experts associated with the authoritative experts.
9. The method of claim 8 , further comprising associating names of the hub experts with the authoritative experts.
10. The method of claim 8 , acting upon an document comprises one of reading the document, reviewing the document, commenting on the document and recommending the documents.
11. The method of claim 10 , wherein recommending the document comprises submitting a numerical rating.
12. The method of claim 10 , wherein recommending the document comprises a submitting a numerical rating and a comment.
13. The method of claim 8 , wherein an arc between users B and A is only added if the ratings of A and B for the current document are within the same range, wherein the ratings do not differ by a predetermined value.
14. A recommender system for recommending documents to users in a community of interest, comprising:
a memory storing: documents provided by users in a particular field within the community; and for each identified document: ratings for the document made by other users in the system and a list of any hub expert users associated with the document; and
a processor identifying documents in the particular field provided by users within the community; each identified document: for determining which users within the community have acted upon the identified document; determining which of the users who have acted upon the identified document are aware of other relevant documents in the particular field and have not directly produced documents in the particular field; and defining those users as hub experts in the particular field; determining which identified items have been acted upon by a predetermined number of hub experts; and defining those documents as authoritative documents and associating hub experts with authoritative documents;
the processor for defining a connectivity matrix M, wherein element M ij is non-zero if and only if there is an arc from node i to node j; wherein for a given node i, a i is an authority value and h i is a hub value, such that:
a
i
=
∑
j
M
ji
h
j
and
h
i
=
∑
j
M
ij
a
j
whose solutions are the principal eigenvectors of M′M_ and MM′, respectively; and defining vectors a=[a 1 , a 2 , . . . a n ]′ and h=[h 1 , h 2 , . . . h n ]′ such that a=M′h=M′Ma, and h=Ma=MM′h
wherein node I represents an authoritative document and node j represents a hub expert; and wherein a represents an authority value for an authoritative document and wherein h represents a hub value for a hub expert;
processor generating a list of hub experts associated with the authoritative documents.
15. A recommender system for identifying an expert within a community of users in a recommender system, comprising:
a memory storing: documents provided by users in a particular field within the community; and for each identified document: ratings for the document made by other users in the system; a list of authoritative experts and a list of any hub expert users associated with the authoritative experts; and
a processor identifying documents in a particular field created by users within the community; each identified document: for determining which users within the community have acted upon the identified document; determining which of the users who have acted upon the identified document are aware of other relevant documents in the particular field and have not directly produced documents in the particular field; and for defining those users as hub experts in the particular field; determining which users creating identified documents have had their identified documents acted upon by a predetermined number of hub experts; and for defining those users as authoritative experts; and for associating hub experts with authoritative experts;
the processor defining a connectivity matrix M, wherein element M ij is non-zero if and only if there is an arc from node i to node j; wherein for a given node i, a i is an authority value and h i is a hub value, such that:
a
i
=
∑
j
M
ji
h
j
and
h
i
=
∑
j
M
ij
a
j
whose solutions are the principal eigenvectors of M′M 13 and MM′, respectively; and defining vectors a=[a 1 , a 2 , . . . a n ]′ and h=[h 1 , h 2 , . . . h n ]′ such that a=M′h=M′Ma, and h=Ma=MM′h
wherein node I represents an authoritative expert and node j represents a hub expert; and
wherein a represents an authority value for an authoritative expert and wherein h represents a hub value for a hub expert;
generating a list of hub experts associated with the authoritative experts.