RECOMMENDING AUTHORS TO EXPAND PERSONAL LEXICON

• US 20190325020A1
• Filed: 04/18/2018
• Published: 10/24/2019
• Est. Priority Date: 04/18/2018
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Catalano, Pasquale A., Werner, John S., Crimmins, Andrew G., Tsfasman, Arkadiy O.
• Granted Patent: US 11,010,553 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 16/31 Indexing; Data structures therefor; Storage structures
• CPC Class Codes: G06F 16/313 Selection or weighting of terms for indexing
• CPC Class Codes: G06F 16/337 Profile generation, learning or modification
• CPC Class Codes: G06F 16/38 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
• CPC Class Codes: G06F 16/9038 Presentation of query results
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 40/20 Natural language analysis semantic analysis of natural language G06F40/30
• CPC Class Codes: G06F 40/242 Dictionaries
• CPC Class Codes: G06F 40/284 Lexical analysis, e.g. tokenisation or collocates
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

A computer implemented method is provided for recommending at least one author of a plurality of authors to a user based on a learned lexicon of the user. First communication content pertaining to a user is obtained. Second communication content pertaining to an author is obtained. A lexicon of the user is learned from the first communication content to identify a set of words known to the user. High frequency words are identified from the second communication content of the author, the high frequency words being one or more words having an occurrence frequency in the second communication content that is higher than a first predetermined threshold occurrence frequency level. The author is suggested to the user upon detecting that the high frequency words are not in the lexicon of the user.

Claims

1. A computer-implemented method for recommending at least one author, of a plurality of authors, to a user based on a learned lexicon of the user, the computer-implemented method comprising:

receiving, by a system comprising one or more processors, first communication content pertaining to a user, the first communication content comprising one or more content sources read by the user or written by the user;

receiving, by the system, second communication content pertaining to an author, the second communication content comprising one more content sources written by the author;

learning, by the system, a lexicon of the user from the first communication content to identify a set of words known to the user;

identifying, by the system, high frequency words from the second communication content of the author, the high frequency words comprising one or more words having an occurrence frequency in the second communication content that is higher than a first predetermined threshold occurrence frequency level; and

suggesting, by the system, the author to the user upon detecting that the high frequency words are not in the lexicon of the user.

2. The computer-implemented method of claim 1, wherein receiving first communication content pertaining to a user comprises:

receiving a lexicon profile of a user from a client device associated with the user, wherein the lexicon profile includes links to social data sources associated with the user, wherein the social data sources comprise sources read by the user and/or sources written by the user.

3. The computer-implemented method of claim 1, wherein learning a lexicon of the user from the first communication content to identify a set of words known to the user comprises:

generating tokens corresponding to the first communication content by applying natural language processing; and

generating a frequency index for the user based on the tokens generated from the first communication content, wherein the first communication content comprises data sources written by the user and data sources read by the user; and

identifying, from the frequency index for the user, a first subset of tokens that have an occurrence frequency in the first communication content that is higher than a second predetermined threshold occurrence frequency level, wherein the identified set of words known to the user comprise the subset of tokens identified from the frequency index for the user.

4. The computer-implemented method of claim 3, wherein the frequency index of the user assigns higher weights to tokens that are generated from the data sources written by the user as compared to tokens that are generated from data sources read by the user.

5. The computer-implemented method of claim 3, wherein identifying high frequency words from the second communication content of the author comprises:

obtaining a reference frequency index for a plurality of authors, the reference frequency index comprising tokens generated from communication content pertaining to each author of a plurality of authors;

generating tokens corresponding to the second communication content by applying natural language processing;

generating a frequency index for the author based on the tokens generated from the second communication content;

updating the reference frequency index based on the tokens generated from the second communication content;

identifying, from the frequency index of the author and the reference frequency index, a subset of tokens that have a higher occurrence frequency in the frequency index of the author as compared to in the reference frequency index;

screening the frequency index of the author against the updated reference frequency index to remove the subset of tokens; and

identifying, as the high frequency words, a subset of tokens of the screened frequency index of the author that have an occurrence frequency higher than the first predetermined threshold occurrence frequency level, wherein the identified high frequency words comprise the identified one or more tokens.

6. The computer-implemented method of claim 5, wherein suggesting the author to the user upon detecting that the high frequency words are not in the lexicon of the user comprises:

comparing the subset of tokens of the screened frequency index of the author to tokens of the frequency index of the user to determine whether the high frequency words exist in the lexicon of the user;

upon determining that the high frequency words of the author do not exist in the lexicon of the user, adding the author to a recommendation list; and

transmitting the recommendation list to the user.

7. The computer-implemented method of claim 1, wherein at least one source of the first communication content is a history of websites viewed, a history of books read, an online journal history, a publication, a social media post, an email, a SMS text message, or a locally stored document.

8. A computer program product for recommending at least one author, of a plurality of authors, to a user based on a learned lexicon of the user, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a system comprising one or more processors to cause the system to perform a method, the method comprising:

receiving, by the system, first communication content pertaining to a user, the first communication content comprising one more content sources written by the user or read by the user;

receiving, by the system, second communication content pertaining to an author, the second communication content comprising one more content sources written by the author;

learning, by the system, a lexicon of the user from the first communication content to identify a set of words known to the user;

identifying, by the system, high frequency words from the second communication content of the author, the high frequency words comprising one or more words having an occurrence frequency in the second communication content that is higher than a first predetermined threshold occurrence frequency level; and

suggesting, by the system, the author to the user upon detecting that the high frequency words are not in the lexicon of the user.

9. The computer program product claim 8, wherein receiving first communication content pertaining to a user comprises:

receiving a lexicon profile of a user from a client device associated with the user, wherein the lexicon profile includes links to social data sources associated with the user, wherein the social data sources comprise sources read by the user and/or sources written by the user.

10. The computer program product of claim 8, wherein learning a lexicon of the user from the first communication content to identify a set of words known to the user comprises:

generating tokens corresponding to the first communication content by applying natural language processing; and

generating a frequency index for the user based on the tokens generated from the first communication content, wherein the first communication content comprises data sources written by the user and data sources read by the user; and

identifying, from the frequency index for the user, a first subset of tokens that have an occurrence frequency in the first communication content that is higher than a second predetermined threshold occurrence frequency level, wherein the identified set of words known to the user comprise the subset of tokens identified from the frequency index for the user.

11. The computer program product of claim 10, wherein the frequency index of the user assigns higher weights to tokens that are generated from the data sources written by the user as compared to tokens that are generated from data sources read by the user.

12. The computer program product of claim 10, wherein identifying high frequency words from the second communication content of the author comprises:

obtaining a reference frequency index for a plurality of authors, the reference frequency index comprising tokens generated from communication content pertaining to each author, of a plurality of authors;

generating tokens corresponding to the second communication content by applying natural language processing;

generating a frequency index for the author based on the tokens generated from the second communication content;

updating the reference frequency index based on the tokens generated from the second communication content;

identifying, from the frequency index of the author and the reference frequency index, a subset of tokens that have a higher occurrence frequency in the frequency index of the author as compared to in the reference frequency index;

screening the frequency index of the author against the updated reference frequency index to remove the subset of tokens; and

identifying, as the high frequency words, a subset of tokens of the screened frequency index of the author that have an occurrence frequency higher than the first predetermined threshold occurrence frequency level, wherein the identified high frequency words comprise the identified one or more tokens.

13. The computer program product of claim 12, wherein suggesting the author to the user upon detecting that the high frequency words are not in the lexicon of the user comprises:

comparing the subset of tokens of the screened frequency index of the author to tokens of the frequency index of the user to determine whether the high frequency words exist in the lexicon of the user;

upon determining that the high frequency words of the author do not exist in the lexicon of the user, adding the author to a recommendation list; and

transmitting the recommendation list to the user.

14. The computer program product of claim 8, wherein at least one a source of the first communication content is a history of websites viewed, a history of books read, an online journal history, a publication, a social media post, an email, a SMS text message, or a locally stored document.

16. A system for recommending at least one author of a plurality of authors to a user based on a learned lexicon of the user, the system comprising one or more processors configured to perform a method, the method comprising:

receiving, by the system comprising one or more processors, first communication content pertaining to a user, the first communication content comprising one or more content sources written by the user or read by the user;

receiving, by the system, second communication content pertaining to an author, the second communication content comprising one more content sources written by the author;

learning, by the system, a lexicon of the user from the first communication content to identify a set of words known to the user;

identifying, by the system, high frequency words from the second communication content of the author, the high frequency words comprising one or more words having an occurrence frequency in the second communication content that is higher than a first predetermined threshold occurrence frequency level; and

suggesting, by the system, the author to the user upon detecting that the high frequency words are not in the lexicon of the user.

17. The system of claim 16, wherein receiving first communication content pertaining to a user comprises:

receiving a lexicon profile of a user from a client device associated with the user, wherein the lexicon profile includes links to social data sources associated with the user, wherein the social data sources comprise sources read by the user and/or sources written by the user.

18. The system of claim 16, wherein learning a lexicon of the user from the first communication content to identify a set of words known to the user comprises:

generating tokens corresponding to the first communication content by applying natural language processing; and

generating a frequency index for the user based on the tokens generated from the first communication content, wherein the first communication content comprises data sources written by the user and data sources read by the user; and

identifying, from the frequency index for the user, a first subset of tokens that have an occurrence frequency in the first communication content that is higher than a second predetermined threshold occurrence frequency level, wherein the identified set of words known to the user comprise the subset of tokens identified from the frequency index for the user.

19. The system of claim 18, wherein identifying high frequency words from the second communication content of the author comprises:

obtaining a reference frequency index for a plurality of authors, the reference frequency index comprising tokens generated from communication content pertaining to each author of a plurality of authors;

generating tokens corresponding to the second communication content by applying natural language processing;

generating a frequency index for the author based on the tokens generated from the second communication content;

updating the reference frequency index based on the tokens generated from the second communication content;

identifying, from the frequency index of the author and the reference frequency index, a subset of tokens that have a higher occurrence frequency in the frequency index of the author as compared to in the reference frequency index;

screening the frequency index of the author against the updated reference frequency index to remove the subset of tokens; and

identifying, as the high frequency words, a subset of tokens of the screened frequency index of the author that have an occurrence frequency higher than the first predetermined threshold occurrence frequency level, wherein the identified high frequency words comprise the identified one or more tokens.

20. The system of claim 19, wherein suggesting the author to the user upon detecting that the high frequency words are not in the lexicon of the user comprises:

comparing the subset of tokens of the screened frequency index of the author to tokens of the frequency index of the user to determine whether the high frequency words exist in the lexicon of the user;

upon determining that the high frequency words of the author do not exist in the lexicon of the user, adding the author to a recommendation list; and

transmitting the recommendation list to the user.