Method and system for expansion to everyday language by using word vectorization technique based on social network content
Provided is a method and system for expanding to an everyday language using a word vectorization technique based on social network content. A content providing method includes collecting social network content on the Internet; expanding corresponding content information to a word set of words included in the social network content with respect to target content that is to be serviced to a client; and providing the target content to the client with respect to user information associated with the client using the word set.
1. A computer implemented content providing method, comprising:
collecting social network content on Internet;
vectorizing content words included in the social network content;
constructing a plurality of keyword databases by classifying the vectorized content words such that each of the keyword databases includes a vector table and a vector conversion matrix;
selecting one or more of the keyword databases corresponding to target content that is to be serviced to a client;
converting one or more words corresponding to corresponding content information associated with the target content to a vector form, the corresponding content information including a corresponding target keyword and a corresponding category name associated with the target content;
expanding the corresponding content information to a word set of synonym words by referring to the selected one or more of the keyword databases in a vector space; and
providing the target content to the client with respect to user information associated with the client using the word set.
2. The method of claim 1 , wherein
the constructing comprises constructing the plurality of keyword databases each based on a corresponding classification criterion of the social network content, and
the expanding comprises generating a synonym set for the corresponding content information by referring to one of the keyword databases of the corresponding classification criterion.
3. The method of claim 1 , wherein
the constructing comprises constructing each of the plurality of keyword databases for a corresponding language with respect to the social network content, and
the expanding comprises expanding the word set to at least one object language for the corresponding content information by referring to a corresponding one of the keyword databases for the corresponding language.
4. The method of claim 1 , wherein the constructing comprises:
preprocessing the content words included in the social network content using a natural language processing technique; and
generating the keyword databases each including the vector table by vectorizing the preprocessed content words.
5. The method of claim 1 , wherein the constructing comprises updating the keyword databases by periodically collecting the social network content.
6. The method of claim 1 , wherein
the providing comprises providing the word set to the client and transferring the target content to the client in response to a content request from the client, and
the client requests the target content based on a result of comparing the user information to the word set.
7. The method of claim 1 , wherein the providing comprises receiving the user information from the client and transferring the target content to the client based on a result of comparing the user information to the word set.
8. A non-transitory computer-readable recording medium storing instructions that, when executed by a processor, cause the processor to implement a content providing method in conjunction with a computer system, the method comprising:
collecting social network content on Internet;
vectorizing content words included in the social network content;
constructing a plurality of keyword databases by classifying the vectorized content words such that each of the keyword databases includes a vector table and a vector conversion matrix;
selecting one or more of the keyword databases corresponding to target content that is to be serviced to a client;
converting one or more words corresponding to corresponding content information associated with the target content to a vector form, the corresponding content information including a corresponding target keyword and a corresponding category name associated with the target content;
expanding the corresponding content information to a word set of synonym words by referring to the selected one or more of the keyword databases in a vector space; and
providing the target content to the client with respect to user information associated with the client using the word set.
9. A computer-implemented content providing system, comprising:
at least one processor configured to execute non-transitory computer-readable instructions,
wherein the at least one processor is configured to,
collect social network content on Internet,
vectorize content words included in the social network content,
construct a plurality of keyword databases by classifying the vectorized content words such that each of the keyword databases includes a vector table and a vector conversion matrix,
select one or more of the keyword databases corresponding to target content that is to be serviced to a client,
convert one or more words corresponding to corresponding content information associated with the target content to a vector form, the corresponding content information including a corresponding target keyword and a corresponding category name associated with the target content,
expand the corresponding content information to a word set of synonym words by referring to the selected one or more of the keyword databases in a vector space and
provide the target content to the client with respect to user information associated with the client using the word set.
10. The content providing system of claim 9 , wherein
the at least one processor is configured to construct the plurality of keyword databases each based on a corresponding classification criterion of the social network content, and
generate a synonym set for the content information by referring to one of keyword databases of the corresponding classification criterion.
11. The content providing system of claim 9 , wherein
the at least one processor is configured to construct each of the plurality of keyword databases for a corresponding language with respect to the social network content, and
expand the word set to at least one object language for the corresponding content information by referring to a corresponding one of the keyword databases for the corresponding language.
12. The content providing system of claim 9 , wherein the at least one processor is configured to,
preprocess the content words included in the social network content using a natural language processing technique, and
generate the keyword databases each including the vector table by vectorizing the preprocessed content words.
13. The content providing system of claim 9 , wherein the at least one processor is configured to update the keyword databases by periodically collecting the social network content.
14. The content providing system of claim 9 , wherein
the at least one processor is configured to provide the word set to the client and to transfer the target content to the client in response to a content request from the client, and
the client requests the target content based on a result of comparing the user information to the word set.
15. The content providing system of claim 9 , wherein the at least one processor is configured to receive the user information from the client and to transfer the target content to the client based on a result of comparing the user information to the word set.