Search system and method having quality scoring
A search system and method generates a quality score and/or a political lean score for a piece of content and returns the one or more scores to the user when returning search results from a query to the user. In one embodiment, the system and method may use artificial intelligence/machine learning to determine the one or more scores for each piece of content.
1. A search system, comprising:
a computer system having a processor and a plurality of lines of instructions that are executed by the processor that is configured to:
retrieve a plurality of pieces of content;
generate a plurality of score factors for each piece of content of the plurality of pieces of content, the plurality of score factors being a byline factor, a title exaggeration factor, a subjectivity factor, a clickbait factor, a personal attack factor and a lack of site disclosure factor;
generate a quality score for each piece of content based on the plurality of score factors;
store, for each piece of content, the quality score and a political lean score, the quality score indicating a quality of the piece of content and the political lean score indicating a political bias of the piece of content;
receive a search query having one or more query terms;
retrieve one or more pieces of content that match the one or more query terms; and
generates a search user interface having a summary of each of the matching one or more pieces of content and the stored quality score and the political lean score for each matching piece of content.
2. The system of claim 1 , wherein the processor is further configured to crawl a corpus of pieces of content, ingest the crawled pieces of content and perform machine learning to generate the quality score and the political lean score.
3. The system of claim 1 , wherein the processor is further configured to generate a search factors user interface that displays the plurality of score factors that together generate the quality score.
4. The system of claim 3 , wherein the processor that generates the plurality of score factors is further configured to perform a machine learning process to generate each score factor.
5. The system of claim 1 , wherein the processor is further configured to generate a filter user interface to adjust the matching pieces of content.
6. The system of claim 1 , wherein each piece of content is a news piece of content.
7. The system of claim 1 , wherein each of the plurality of score factors is a journalistic principle and the processor is further configured to generate, using a machine learning model for each journalistic principle, a journalistic principle score for each of the plurality of journalistic principles for the piece of content and use a meta learning model that aggregates the journalistic principle score for each of the plurality of journalistic principles for the piece of content to generate the quality score of the piece of content.
8. A search method comprising:
retrieving, at a search system, a plurality of pieces of content;
generating a plurality of score factors for each piece of content of the plurality of pieces of content, the plurality of score factors being a byline factor, a title exaggeration factor, a subjectivity factor, a clickbait factor, a personal attack factor and a lack of site disclosure factor;
generating a quality score for each piece of content based on the plurality of score factors;
storing, at the search system, the quality score and a political lean score, the quality score indicating a quality of the piece of content and the political lean score indicating a political bias of the piece of content;
receiving, at the search system, a search query having one or more query terms;
retrieving, at the search system, one or more pieces of content that match the one or more query terms; and
displaying, on a display of a computer, a search user interface having a summary of each of the matching one or more pieces of content and the generated quality score and the political lean score for each matching piece of content.
9. The method of claim 8 further comprising crawling a corpus of pieces of content, ingesting the crawled pieces of content and performing machine learning to generate the quality score and the political lean score.
10. The method of claim 8 , wherein displaying the generated quality score further comprises displaying the plurality of score factors that together generate the quality score.
11. The method of claim 10 , wherein generating the plurality of score factors further comprises performing a machine learning process to generate each score factor.
12. The method of claim 8 , wherein displaying the generated quality score further comprises displaying a filter user interface to adjust the matching pieces of content.
13. The method of claim 8 , wherein each piece of content is a news piece of content.
14. The method of claim 8 , wherein each of the plurality of score factors is a journalistic principle and generating the quality score for the piece of content further comprises generating, using a machine learning model for each journalistic principle, a journalistic principle score for each of the plurality of journalistic principles for the piece of content and using a meta learning model that aggregates the journalistic principle score for each of the plurality of journalistic principles for the piece of content to generate the quality score of the piece of content.
15. An apparatus for generating a score for a piece of content
a computer system having a processor and a plurality of lines of instructions that are executed by the processor that is configured to:
retrieve a plurality of pieces of content;
generate a plurality of score factors for each piece of content of the plurality of pieces of content, the plurality of score factors being a byline factor, a title exaggeration factor, a subjectivity factor, a clickbait factor, a personal attack factor and a lack of site disclosure factor;
generate a quality score for each piece of content based on the plurality of score factors;
store, for each piece of content, the quality score and a political lean score, the quality score indicating a quality of the piece of content and the political lean score indicating a political bias of the piece of content; and
wherein each score factor is a journalistic principle and the quality score is generated by the processor being further configured to generate, using a machine learning model for each journalistic principle, a journalistic principle score for each journalistic principle for the piece of content and use a meta learning model that aggregates the journalistic principle score for each journalistic principle for the piece of content to generate the quality score of the piece of content.
16. The apparatus of claim 15 , wherein the processor is further configured to crawl a corpus of pieces of content, ingest the crawled pieces of content and perform machine learning to generate the quality score and the political lean score.
17. The apparatus of claim 15 , wherein the processor is further configured to generate a filter user interface to adjust the matching pieces of content.
18. The apparatus of claim 15 , wherein each piece of content is a news piece of content.