It’s long been known that the Bible had several authors – but just how many, and which bits they wrote, has been subject to much argument.
Now, computer scientists and Bible scholars at several Israeli universities plan to try and cut through the debate by applying an algorithm that they say can identify the different authorial voices.
Several years ago Professor Koppel of Bar-Ilan University led a team that developed a computer algorithm that can examine an anonymous text and determine whether the author is male or female, with more than 80 percent accuracy.
Now, he and colleagues have devised a similar algorithm that automatically divides a composite document into distinct authorial strands.
It works by automatically identifying small clusters of text that differ in their choices among available synonyms. For example, one cluster will consistently use the word ‘makel’ to mean ‘staff’, and another consistently use ‘mateh’, which means the same thing.
By applying these techniques, the researchers were able to show that when two Bible books, such as Jeremiah and Ezekiel, were randomly mixed together, the merged book could be automatically – and almost perfectly – separated out into its constituent components.
The team says the result result is of ‘potentially overwhelming’ importance to Bible scholarship. When applied to books for which the underlying author isn’t known, it could suggest which parts are likely to share an author.