Algorithms are coming for Hebrew paleography!

NORTHWEST SEMITIC EPIGRAPHY: Algorithmic handwriting analysis of the Samaria inscriptions illuminates bureaucratic apparatus in biblical Israel (Shira Faigenbaum-Golovin, Arie Shaus, Barak Sober, Eli Turkel, Eli Piasetzky, Israel Finkelstein, Plos One).

Abstract

Past excavations in Samaria, capital of biblical Israel, yielded a corpus of Hebrew ink on clay inscriptions (ostraca) that documents wine and oil shipments to the palace from surrounding localities. Many questions regarding these early 8th century BCE texts, in particular the location of their composition, have been debated. Authorship in countryside villages or estates would attest to widespread literacy in a relatively early phase of ancient Israel's history. Here we report an algorithmic investigation of 31 of the inscriptions. Our study establishes that they were most likely written by two scribes who recorded the shipments in Samaria. We achieved our results through a method comprised of image processing and newly developed statistical learning techniques. These outcomes contrast with our previous results, which indicated widespread literacy in the kingdom of Judah a century and half to two centuries later, ca. 600 BCE.

This story has received some attention in the media, but I think it is all based on the Plos One article and the following Tel Aviv University press release. It gives additional commentary by the authors: Study Reveals Two Writers Penned Landmark Inscriptions in Eighth-Century BCE Samaria. Discovery illuminates bureaucratic apparatus of ancient kingdom of Israel, say TAU researchers. A key point:

"If only two scribes wrote the examined Samaria texts contemporaneously and both were located in Samaria rather than in the countryside, this would indicate a palace bureaucracy at the peak of the kingdom of Israel's prosperity," Prof. Finkelstein explains.

"Our results, accompanied by other pieces of evidence, seem also to indicate a limited dispersion of literacy in Israel in the early eighth century BCE," Prof. Piasetzky says.

I noted the previous research mentioned in the abstract above here.

In the past, the media published some overblown claims about algorithms applied to ancient languages. But the algorithms keep getting better. Recent studies like this one look cautious and credible. Background here, here, here, here, and links.

We may have reached the point when algorithms can outdo humans at Hebrew paleography.

Visit PaleoJudaica daily for the latest news on ancient Judaism and the biblical world.