Imagine that you just finished reading a review paper on heart failure. How would you feel if you were given recommendations on what to read next and each of them featured another review paper on heart failure? In some cases (e.g, if you were not satisfied with the first review), this might do the trick, but more often than not, you’d probably like to move on to another topic that really interests you.

Here at TrendMD we think the world of academia is brainwashed by relatedness (think of PubMed related links). Scholarly recommendations, have often been presented as “related links” and have provided just that by relying primarily upon contextual relevancy. At TrendMD, we strive to find the most interesting content for each and every person through personalized recommendations that are interesting to that person but not necessarily related to what they were just reading.

Recently, we dug into our data to see how this notion of “Most Related ≠ Most Interesting” plays out in numbers:

We grouped the content in our index into 7 categories (eHealth, cardiology, nephrology, surgery, emergency medicine, internal medicine, endocrinology) and compared the average click-through rate on related content recommendations (from the same category as the current article) vs. unrelated content recommendations (from a different category from the current article).

We found that unrelated content recommendations generated a 24% higher CTR on average!

With more and more data like this, perhaps the “relatedness brainwash” will start to wear off and it will become clearer that the best way to deeply engage audiences is to tailor recommendations to each individual person.

Have questions? Email me at [email protected]