Optimized method of and system for summarizing factually inaccurate information utilizing fact checking

• US 10,614,112 B2
• Filed: 09/09/2016
• Issued: 04/07/2020
• Est. Priority Date: 09/04/2014
• Status: Active Grant

• Current Assignee: Lucas Myslinski
• Original Assignee: Lucas Myslinski
• Inventors: Myslinski, Lucas J.
• Primary Examiner(s): Trujillo, James
• Assistant Examiner(s): Morris, John J
• Application Number:
  US15/260,965
• Publication Number:
  US 20160378746A1
• Time in Patent Office: 1,306 Days
• Field of Search: None
• 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) acquiring target information;

(b) processing the target information, including parsing the target information into parsed information;

(c) fact checking, with the device, the target 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;

(d) summarizing the target information to generate a summary of the target information utilizing lexical chaining and the fact checking results generated by fact checking the target information, including determining total strengths of sentences within the target information, wherein a total strength of a sentence is based on a lexical chain strength and a factual accuracy of the sentence, further wherein the total strength of the sentence is modified when the sentence is factually inaccurate, wherein the summary includes only the parsed information indicated as factually inaccurate; and

(e) providing the summary of the target information in real-time.

2. The method of claim 1 wherein when the target 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 target information, and when the target 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 target information.

3. The method of claim 1 wherein summarizing the target information utilizes social networking information of a user to determine a focus of the target information, wherein the user is provided the summary of the target information.

4. The method of claim 1 wherein summarizing the target information includes determining a set of most factually inaccurate sentences combined with lexical chaining to generate the summary of the target information.

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

6. The method of claim 1 wherein providing the summary of the target 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 a sentence corresponding to the tile with the sentence highlighted.

7. The method of claim 1 wherein summarizing the target information utilizes two different summarizing implementations to generate two different summaries, and comparing the two different summaries.

8. The method of claim 1 further comprising analyzing social networking information of a user, determining interests of the user based on analyzing the social networking information, storing the interests of the user in a data structure, and summarizing the target information utilizing the interests stored in the data structure by increasing the strength of a lexical chain when a word in the lexical chain matches the at least one of the interests in the data structure, wherein the user is provided the summary of the target information.

9. The method of claim 1 wherein summarizing the target information includes analyzing only factually inaccurate sentences of the target information for lexical chaining.

10. The method of claim 1 wherein summarizing the target information includes analyzing all sentences of the target information for lexical chaining but extracting only the factually inaccurate sentences with strongest chains.

11. The method of claim 1 wherein the summary includes a single factually inaccurate sentence with a highest confidence score.

12. The method of claim 1 wherein the summary includes a single factually inaccurate sentence in a strongest lexical chain.

13. 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 target information comprises the merged content item.

14. The method of claim 1 wherein summarizing the target information includes analyzing a validity rating of an entity who provided the target 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 target 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 target 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 target information.

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

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

17. The method of claim 1 wherein the target information includes a plurality of articles, and each article of the plurality of articles receives a factual accuracy rating based on fact checking, further wherein an article of the plurality of articles with a lowest factual accuracy rating is summarized with a base number of sentences, and articles with higher factual accuracy ratings are summarized with a modified number of sentences such that the article with the highest factual accuracy rating is summarized with a different number of sentences than the article with the lowest factual accuracy rating.

18. The method of claim 1 wherein the target information includes a plurality of articles, 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) acquiring target information;

(b) processing the target information, including parsing the target information into parsed information;

(c) fact checking, with the device, the target information by comparing the parsed information with source information to generate fact checking results, including indicating when the parsed information is factually accurate, indicating when the parsed information is questionable, and indicating when the parsed information is factually inaccurate;

(d) summarizing the target information to generate a summary of the target information utilizing lexical chaining and the fact checking results generated by fact checking the target information, including determining total strengths of sentences within the target information, wherein a total strength of a sentence is based on a lexical chain strength and a factual accuracy of the sentence, further wherein the total strength of the sentence is modified when the sentence is factually accurate, the total strength of the sentence is modified when the sentence is factually inaccurate, and the total strength of the sentence is unchanged when the sentence is questionable; and

(e) providing the summary of the target information in real-time.

20. A device comprising:

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

(i) acquiring target information;

(ii) processing the target information, including parsing the target information into parsed information;

(iii) fact checking, with the device, the target 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;

(iv) summarizing the target information to generate a summary of the target information utilizing lexical chaining and the fact checking results generated by fact checking the target information, including determining total strengths of sentences within the target information, wherein a total strength of a sentence is based on a lexical chain strength and a factual accuracy of the sentence, further wherein the total strength of the sentence is modified when the sentence is factually accurate, and the total strength of the sentence is modified when the sentence is factually inaccurate, wherein the sentences of the target information with factually accurate information are not utilized for generating the summary of the target information, wherein when the target 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 target information, and when the target 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 target information, wherein the summary includes only the sentences containing the parsed information indicated as factually inaccurate; and

(v) providing the summary of the target information in real-time; and

(b) a processor for processing the application.