Analysis of the Readability Metric Results in Almeta News Feed

In this post, we’re analyzing the results returned by the readability metric in our news feed. If you haven’t checked our post about “How to measure the readability of a text?” before, you can read about it here.

How Are We Measuring the Readability?

The main part of analyzing a metric is to know how does it work. In the current version, we’re depending on the AARIBase metric for measuring the readability. So, let’s have a look first on how does AARIBase work.

Here’s the AARIBase formula:

AARIBase = (3.28 × NOC) + (1.43 × ACW) + (1.24 × AWS)

Where:

NOC: Number of characters.

ACW: Average character per word.

AWS: Not that AWS, It’s the Average words per sentence.

According to the considered factors in the previous formula and their weights, the following results can be concluded:

  • The NOC factor which has the largest weight causes a high sensitivity to the text length, longer texts will be less readable.
  • Texts with longer words will be less readable, this is because of the ACW factor in the formula, the NOC factors may have a little effect in this too.
  • Because of the AWS factor, texts with longer sentences will be less readable.

Almeta News Feed Results Analysis

One thing that’s remarkable in the results is that the readability decreases when the read-time increases. Articles with very high read-time have very low readability and vice versa.

Here are some examples:

This kind of results is reasonable according to our previous discussion on AARIBase formula, which is sensitive to the text length.

However, sometimes the articles may have the same read-time but they vary a lot in terms of readability. In this situation, mostly the length of the sentences is the factor that’s behind this contrast in the readability scores.

Here is an example of this situation:

In the previous example, you can examine that the sentences of the first article are longer than the sentences of the second article, which is reflected in the readability scores.

Conclusion

In this post, we showed the analysis of our readability metric. We first analyzed the formula of the AARIBase metric which is the used readability metric, then we reflected this analysis on the results returned in our news feed.

Do you know that we use all this and other AI technologies in our app? Look at what you’re reading now applied in action. Try our Almeta News app. You can download it from google play: https://play.google.com/store/apps/details?id=io.almeta.almetanewsapp&hl=ar_AR

Leave a Reply

Your email address will not be published. Required fields are marked *