Yiu-Kai Ng of the Computer Science Department at Brigham Young University, in Provo, Utah, USA, suggests that promoting good reading habits in children is critical to their learning and development as mature members of a thriving society. Writing in the International Journal of Business Intelligence and Data Mining, he also suggests that we need novel ways to recommend reading matter to children that is not based simply on popularity.
Given the prevalence of the internet and mobile phone apps, there is surely a way to extract reading habits and create a so-called recommendation engine based on wider data points than simple popularity. The development of such a tool would allow customisation and personalisation to come to the fore and at the same time avoid what one might perceive as a reading “echo chamber” based on a few popular authors. This is especially important in a multicultural world where exposure to diversity is increasingly important to help us combat bigotry and prejudice and to create a more accepting world as our children grow.
Ng and colleagues have now developed “CBRec”. This is a book recommendation system for children that uses matrix factorisation and content-based filtering approaches to offer suggestions of what the child should read next with greater potential for their enjoying and learning from those books. The new system avoids the need for any kind of social “tags” that might be gleaned from adult users of online social networking sites but at the same time also considers age and reading level.
Given that there are tens of thousands of books for children published every year, this tool could become a significant part of engaging young readers with a wider authorship than the bestsellers lists might otherwise offer them.
Ng, Y-K. (2020) ‘CBRec: a book recommendation system for children using the matrix factorisation and content-based filtering approaches‘, Int. J. Business Intelligence and Data Mining, Vol. 16, No. 2, pp.129-149.