Optimized social networking summarizing method and system utilizing fact checking

• US 9,875,234 B2
• Filed: 05/15/2015
• Issued: 01/23/2018
• Est. Priority Date: 09/04/2014
• Status: Active Grant

• Current Assignee: Lucas Myslinski
• Original Assignee: Lucas Myslinski
• Inventors: Myslinski, Lucas J.
• Primary Examiner(s): Waldron, Scott A
• Assistant Examiner(s): Mina, Fatima
• Application Number:
  US14/713,096
• Publication Number:
  US 20160070786A1
• Time in Patent Office: 984 Days
• CPC Class Codes: G06F 16/2365 Ensuring data consistency and integrity
• CPC Class Codes: G06F 16/244 Grouping and aggregation
• CPC Class Codes: G06F 16/3331 Query processing
• CPC Class Codes: G06F 16/3334 Selection or weighting of terms from queries, including natural language queries
• CPC Class Codes: G06F 16/335 Filtering based on additional data, e.g. user or group profiles filtering in web context G06F16/9535, G06F16/9536
• CPC Class Codes: G06F 16/345 Summarisation for human users
• CPC Class Codes: G06F 16/90332 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 40/226 Validation
• CPC Class Codes: G06F 40/237 Lexical tools
• CPC Class Codes: G06F 40/284 Lexical analysis, e.g. tokenisation or collocates
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06F 40/58 Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation
• CPC Class Codes: G06Q 30/0255 based on user history
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

An optimized fact checking system analyzes and determines the factual accuracy of information and/or characterizes the information by comparing the information with source information. The optimized fact checking system automatically monitors information, processes the information, fact checks the information in an optimized manner and/or provides a status of the information. In some embodiments, the optimized fact checking system generates, aggregates, and/or summarizes content.

Claims

1. A method programmed in a non-transitory memory of a device comprising:

a. capturing social networking information, including the social networking information of a user, from a social networking system;

b. analyzing the social networking information of the user, including;

i. determining interests of the user; and

ii. storing the interests of the user in a data structure;

c. processing the social networking information, including parsing the social networking information into parsed information;

d. fact checking, with the device, the social networking information by comparing the parsed information with source information to generate fact checking results, including indicating when the parsed information is factually accurate and indicating when the parsed information is factually inaccurate;

e. summarizing the social networking information to generate a summary of the social networking information, including determining total strengths of sentences within the social networking information,

wherein a total strength of a sentence is based on a strength of a lexical chain, the interests of the user, and factual accuracy of the sentence based on the fact checking results generated by fact checking the social networking information,

wherein summarizing the social networking information utilizes the interests of the user stored in the data structure by increasing the strength of the lexical chain when a word in the lexical chain matches at least one of the interests in the data structure,

wherein lexical chaining includes selecting a set of candidate words or phrases, finding an appropriate chain using relatedness criteria among members of chains for each candidate word, and inserting a word in the lexical chain when the word is found,

wherein the total strength of the sentence is increased when the sentence is factually accurate,

wherein the summary of the social networking information includes the fact checking results; and

f. providing the summary of the social networking information in real-time.

2. The method of claim 1 wherein summarizing the social networking information includes decreasing the total strength of the sentence when the sentence is factually inaccurate.

3. The method of claim 1 wherein when the social networking information has not received a number of positive comments above a threshold, then a base number of sentences are utilized to generate the summary of the social networking information, and when the social networking information has received the number of positive comments above the threshold, then the base number of sentences plus an additional number of sentences are utilized to generate the summary of the social networking information.

4. The method of claim 1 wherein summarizing the social networking information utilizes the social networking information of the user to determine a focus of the social networking information.

5. The method of claim 1 wherein summarizing the social networking information includes determining a set of most factually accurate sentences combined with the lexical chaining to generate the summary of the social networking information.

6. The method of claim 1 further comprising generating advertisement information based on the summary of the social networking information, further wherein keywords of the lexical chain are analyzed to generate the advertisement information.

7. The method of claim 1 wherein the social networking information includes augmented reality-acquired device information acquired using an augmented reality device, and wherein the summary of the social networking information is displayed on the augmented reality device.

8. The method of claim 1 wherein providing the summary of the social networking information includes displaying selectable tiles, wherein selecting a tile of the selectable tiles causes a full content item to be displayed at a location of the sentence corresponding to the tile with the sentence highlighted.

9. The method of claim 1 wherein summarizing the social networking information utilizes two different summarizing implementations to generate two different summaries.

10. The method of claim 1 further comprising merging multiple content items with disparate views into a merged content item, including maintaining a relative position of each sentence when merging the multiple content items, wherein the social networking information comprises the merged content item.

11. The method of claim 1 wherein summarizing the social networking information includes analyzing a validity rating of an entity who provided the social networking information, wherein the validity rating is based on factual accuracy of content provided by the entity, and when the validity rating of the entity is below a first threshold, a base number of sentences are used for summarizing the social networking information, and when the validity rating of the entity is equal to or above the first threshold and below a second threshold, the base number of sentences plus a first number of additional sentences are used for summarizing the social networking information, and when the validity rating of the entity is equal to or above the second threshold, the base number of sentences plus a second number of additional sentences are used for summarizing the social networking information.

12. The method of claim 1 wherein the social networking information includes one or more data sources with opposing perspectives, wherein the one or more data sources comprise a first data source with a first opposing perspective, and the one or more data sources comprise a second data source with a second opposing perspective.

13. The method of claim 1 wherein the social networking information comprises aggregate information which comprises a plurality of articles about a same topic determined by comparing dates and matching keywords within the plurality of articles.

14. The method of claim 1 wherein the sentences of the social networking information with factually inaccurate information are not utilized for generating the summary of the social networking information.

15. The method of claim 1 wherein summarizing the social networking information utilizes confidence scores of the fact checking results to generate the summary of the social networking information.

16. The method of claim 1 wherein the social networking information has a factual accuracy rating, further wherein when the factual accuracy rating of the social networking information is below a threshold, the social networking information is summarized with a base number of sentences, and when the factual accuracy rating of the social networking information is equal to or above the threshold, the social networking information is summarized with the base number of sentences plus additional sentences.

17. The method of claim 1 wherein the social networking information includes a plurality of social networking content, and each social networking content of the plurality of social networking content receives a factual accuracy rating based on fact checking, further wherein a social networking content of the plurality of social networking content with a lowest factual accuracy rating is summarized with a base number of sentences, and the social networking content with higher factual accuracy ratings are summarized with the base number of sentences plus additional sentences such that the social networking content with the highest factual accuracy rating is summarized with the base number of sentences plus a maximum number of additional sentences.

18. The method of claim 1 wherein the social networking information includes a plurality of social networking content, wherein generating the summary includes generating a plurality of summaries and combining the plurality of summaries to form the summary such that a first sentence from a first summary of the plurality of summaries is provided first, a first sentence from a second summary of the plurality of summaries is provided second, and continuing in order until a last sentence from a last summary of the plurality of summaries is provided last.

19. A method programmed in a non-transitory memory of a device comprising:

a. capturing a first set of social networking information from a social networking system;

b. capturing a second set of social networking information, including the social networking information of a user, from the social networking system;

c. analyzing the second set of social networking information, including;

i. determining interests of the user; and

ii. storing the interests of the user in a data structure;

d. processing the first set of social networking information, including parsing the first set of social networking information into parsed information;

e. fact checking, with the device, the first set of social networking information by comparing the parsed information with source information to generate fact checking results, including indicating when the parsed information is factually accurate and indicating when the parsed information is factually inaccurate;

f. summarizing the first set of social networking information to generate a summary of the first set of social networking information, including determining total strengths of sentences within the first set of social networking information,

wherein a total strength of a sentence is based on a strength of a lexical chain, the interests of the user, and factual accuracy of the sentence based on the fact checking results generated by fact checking the first set of social networking information,

wherein summarizing the first set of social networking information utilizes the interests of the user stored in the data structure by increasing the strength of the lexical chain when a word in the lexical chain matches at least one of the interests in the data structure,

wherein lexical chaining includes selecting a set of candidate words or phrases, finding an appropriate chain using relatedness criteria among members of chains for each candidate word, and inserting a word in the lexical chain when the word is found,

wherein the total strength of the sentence is increased when the sentence is factually accurate,

wherein the summary of the first set of social networking information includes the fact checking results; and

g. providing the summary of the first set of social networking information in real-time.

20. A device comprising:

a. a non-transitory memory for storing an application for automatically performing the following steps;

i. capturing a first set of social networking information from a social networking system;

ii. capturing a second set of social networking information, including the social networking information of a user, from the social networking system;

iii. analyzing the second set of social networking information, including;

(1) determining interests of the user based on most frequently used words in the second set of social networking information; and

(2) storing the interests of the user in a data structure;

iv. processing the first set of social networking information, including parsing the first set of social networking information into parsed information;

v. fact checking, with the device, the first set of social networking information by comparing the parsed information with source information to generate fact checking results, including indicating when the parsed information is factually accurate and indicating when the parsed information is factually inaccurate;

vi. summarizing the first set of social networking information to generate a summary of the first set of social networking information, including determining total strengths of sentences within the first set of social networking information,

wherein a total strength of a sentence is based on a strength of a lexical chain, the interests of the user, and factual accuracy of the sentence based on the fact checking results generated by fact checking the first set of social networking information,

wherein summarizing the first set of social networking information includes utilizing the interests of the user stored in the data structure by increasing the strength of the lexical chain when a word in the lexical chain matches at least one of the interests in the data structure, and increasing the total strength of the sentence when the sentence is factually accurate, and decreasing the total strength of the sentence when the sentence is factually inaccurate,

wherein lexical chaining includes selecting a set of candidate words or phrases, finding an appropriate chain using relatedness criteria among members of chains for each candidate word, and inserting a word in the lexical chain when the word is found,

wherein the summary of the first set of social networking information includes the fact checking results; and

vii. providing the summary of the first set of social networking information in real-time; and

b. a processor for processing the application.