Bible breakthrough as AI unveils ancient book's 'likely authors'

Graphical representation of the team’s results.. By comparing word usage and sentence patterns, their AI-based statistical model identified three distinct writing styles, or scribal traditions, shown here in yellow, blue and green. (Image provided by the authors) (Image: Shira Faigenbaum-Golovin/Israel Finkelstein et al)

Experts have used cutting-edge artificial intelligence (AI) to uncover concealed linguistic patterns and pinpoint the probable authors of some of the Bible's most ancient texts.

An international team of researchers spearheaded by Duke University in the United States has deployed AI technology to strip away centuries of biblical history.

The academics examined the first nine books of the Hebrew Bible – referred to as the Enneateuch – employing sophisticated linguistic analysis alongside a specially developed AI model.

They discovered three entirely separate writing styles. These distinctive patterns suggest different authors or scribal groups were responsible for the sacred scriptures, offering fresh evidence in the centuries-old debate surrounding the Bible's authorship.

"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 groundbreaking project was spearheaded by mathematician Shira Faigenbaum-Golovin, who initially embarked on this research in 2010 by examining handwriting on ancient pottery shards dating back to 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."

Faigenbaum-Golovin is now spearheading a team comprising mathematicians, archaeologists, linguists and computer scientists in an ambitious effort to merge scientific analysis with biblical scholarship.

The artificial intelligence model identified three distinct writing styles within the text: The Priestly source, the Deuteronomistic History, and the Book of Deuteronomy itself.

Whilst certain chapters aligned neatly with one of these categories, the researchers were taken aback to discover that portions of the Ark Narrative in 1 Samuel didn't correspond to any of the three styles, hinting at yet another mystery surrounding the Bible's composition.

The team believes this technique could prove invaluable for authenticating other historical documents in future.

"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," Faigenbaum-Golovin explained.

The study's authors state: "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 researchers are now exploring how the same approach might unlock fresh insights into other ancient manuscripts. "It's such a unique collaboration between science and the humanities," expressed Faigenbaum-Golovin.

"It's a surprising symbiosis, and I'm lucky to work with people who use innovative research to push boundaries."