Originality.AI, the cutting-edge software tool that is by far the most accurate AI detection tool on the market across all NLP models, and is also the only AI detection tool trained to be able to detect Paraphrased content (such as Quillbot), announces the release of their Readability Feature.
Their Readability feature was developed after conducting an extensive Data Analysis which examined the top 20 web pages for 1,000 popular keywords to find out which readability systems and metrics were most predictive of success in relation to their Google Rank. The finding from this study were interesting as they diverge from the well known and accepted recommendations of numerous readability methods:
Notable Findings:
- Although it is commonly accepted that content should target readers at a grade 10 education level, the data consistently revealed that the mean readability grade is grade 12 or higher in nearly every case, which also correlates with the top ranked pages on Google
- The findings of the study suggest avoiding readability systems like SMOG, Coleman-Liau, Flesch-Kincaid Grade, and Automated Readability systems, as their results showed a very high rate of skewed data (results were not normally distributed).
- Often quoted target readability scores were shown to be lower than the study would suggest. For example, Readable.com recommends these readability scores: FORCAST grade of 9-10, Gunning Fog score of 8, and Flesch Reading Ease of 60 - 70
- Our findings suggest that the top results in Google have the following readability scores: FORECAST 12-14, Gunning-Fog 11-13, Flesch Reading Ease 45-60, Dale Chall 6-7.
How can these widely accepted readability targets be inaccurate in determining the ideal scores for a general audience? One possible explanation is that these readability systems, originally developed between the 1940s and 1970s, may no longer accurately represent current literacy levels.
Concludes Jonathan Gillham, Founder and CEO of Originality.AI
Originality.AI's Readability Feature was developed with the intention of equipping both writers and publishers with a superior, modern and up to date tool that will help them to create and publish content that scores optimally based on the correct readability criteria proven by their data analysis study.
This Feature is now available on the Core APP and the API and is complimentary for those who are scanning content for plagiarism.