AI uncovers Bible's 'likely authors' as scientists reveal hidden clues in ancient text
Scientists are using artificial intelligence to decode mysterious writing styles in the Bible – and could settle biblical disputes
Experts have uncovered hidden language patterns and identified likely authors of some of the Bible's oldest books – using groundbreaking artificial intelligence (AI).
A team of international researchers led by Duke University in the US has used AI technology to peel back layers of biblical history.
READ MORE: 'I sold my face to AI for £1,500'
The team scanned through the first nine books of the Hebrew Bible – known as Enneateuch – using advanced linguistic analysis and a custom-built AI model.
They identified three completely distinct writing styles. These patterns point to different authors or scribal groups behind the sacred texts, providing new evidence in debates about the Bible's authors that have raged for centuries.
"We found that each group of authors has a different style – surprisingly, even regarding simple and common words such as 'no,' 'which,' or 'king.' Our method accurately identifies these differences," said Thomas Römer, professor at the Collège de France.
The project was led by mathematician Shira Faigenbaum-Golovin, who first began this research in 2010 by analysing handwriting on ancient pottery fragments from 600 BC.
"We concluded that the findings in those inscriptions could offer valuable clues for dating texts from the Old Testament," Faigenbaum-Golovin said. "That's when we started putting together our current team, who could help us analyze these biblical texts."
Now Faigenbaum-Golovin is leading a team of mathematicians, archaeologists, linguists and computer scientists to combine science with scripture.
The AI model divided the text into three main writing styles: The Priestly source, the Deuteronomistic History, and the Book of Deuteronomy itself.
While some chapters neatly fit into one of these groups, the team were surprised to find sections of the Ark Narrative in 1 Samuel didn't match any of the three, suggesting yet another unknown in the Bible's creation.
Looking forward, the team believes the same technique could be used for other historical documents.
"If you're looking at document fragments to find out if they were written by Abraham Lincoln, for example, this method can help determine if they are real or just a forgery," said Faigenbaum-Golovin.
The authors conclude in the study: "Our paper sheds new light on the question of authorship of biblical texts by offering interpretable, statistically significant evidence of the existence of linguistic characteristics in the writing of biblical authors/redactors, that can be identified automatically.
"Our methodology thus provides a new tool to address disputed matters in biblical studies."
The team are now looking at using the same methodology to unearth new discoveries about other ancient texts.
"It's such a unique collaboration between science and the humanities," said Faigenbaum-Golovin. "It's a surprising symbiosis, and I'm lucky to work with people who use innovative research to push boundaries."
Keen to hear more about science news? Sign up to The Weird Science Drop newsletter, by author Daniel Smith.
Each newsletter, published on Substack, will feature regular sections such as Weird Science News, Photo of the Week, Infographic Magic, plus a surprise Weird Science weekly special.
Sign up for The Weird Science Drop here
The study is published in the journal PLOS One.