https://phys.org/news/2026-03-ancient-alphabets-insights-uncover-hidden.html
With artificial intelligence (AI) as an essential tool, San Diego State University researchers have discovered surprising similarities among ancient writing systems from Africa and the Caucasus region of Eurasia. Their study suggests that the Armenian alphabet may be more closely related in structure to the ancient Ethiopic writing system than linguists and historians previously thought. The paper is published in the journal Digital Scholarship in the Humanities.
For many years, historians noticed some Armenian, Georgian and Caucasian Albanian letters look similar to letters from Ethiopic, also known as Ge'ez, a writing system developed in the Horn of Africa more than 1,600 years ago.
Most of these early studies, however, relied on scholars' own visual inspection of the letters to determine whether they appeared alike.
Researchers from the Department of Mechanical Engineering in the College of Engineering tested this idea using AI instead of human judgment. They trained a computer program to study more than 28,000 images of Ethiopic characters so it could learn the basic shapes and patterns in the writing system. The program learned to recognize curves, straight lines, angles and the overall structure of each letter.
Importantly, the computer had no data on history, religion, geography or culture. It only looked at shapes. After learning the Ethiopic characters, the program compared them to letters from the Armenian, Georgian and Caucasian Albanian alphabets. It then calculated how similar the shapes were.
Daniel Zemene et al, Machine learning techniques for exploring influence, commonalities, and shared origin of scripts: cases of Ethiopic, Armenian, Georgian, and Caucasian Albanian scripts, Digital Scholarship in the Humanities (2026). DOI: 10.1093/llc/fqag029
(Score: 2, Touché) by Anonymous Coward on Friday April 03, @04:27AM (2 children)
as Markov rolls over in his grave.
(Score: 3, Touché) by driverless on Friday April 03, @08:03AM (1 child)
Great, now we have Markov models doing digital graphology. I'm just waiting to see an "AI" study showing how Aztec (Nahuatl) pictograms are related to Egyptian hieroglyphs.
(Score: 3, Touché) by Freeman on Friday April 03, @01:10PM
The only logical explanation is that the "Aliens" guy was right. Soon, history rewritten by AI.
Joshua 1:9 "Be strong and of a good courage; be not afraid, neither be thou dismayed: for the Lord thy God is with thee"
(Score: 5, Informative) by bzipitidoo on Friday April 03, @04:01PM
Some years ago, I found a couple of questions to embarrass the average English teacher: 1. Why is 'A' the first letter of the alphabet? (Where'd this "alphabetic order" come from?) And 2. Why does 'A' look the way it does, two sloping lines and a bar? Most won't have any idea. The one word answer is "history".
In more detail, starting about 3500 years ago, the Phoenicians/Canaanites spread the idea of a small alphabet representing sounds, rather than a large alphabet of objects like Egyptian hieroglyphs. They still bowed to pictograms -- 'A' is a picture of an ox, a triangular face with two horns. As to the order, things closest to home and of greatest importance were put at the start of their alphabet. B is a one room house. In the 19th century, C (gamma) was thought to be a camel but it is actually a throwing stick. D (delta) is a door, and it seems that with the triangular shape of delta, that's more of a tent door. I thought that "cattle owners (A) live in houses (B), and camel owners (C) live in tents (D)" might have been a way to remember the start of the alphabetic order, except that C isn't for camel, so, so much for that idea. Further down the alphabet, you have letters such as 'M' which is a representation of waves, a traveling sort of symbol.
As to numeric digits, it seems pretty clear that '1' is a single tally stick, and '2' and '3' each have their respective number of points on their left side, with the curves merely to connect those points. '4' I guess to be a shorthand representation of the ultimate embodiment of that numeric value, the square. I think also that 5 is a representation of a hand, the top being a fuzzy representation of the fingers (and thumb), and the bottom representing the palm. So, maybe '6' is '5' with one more finger? '7' I have always found curiously brief. Each digit had been growing in linear length and/or quantity of bends and angles, then '7' simplifies down to 2 lines. Then we rebound with '8', and back away again with '9', hmm. Is it that '7' was considered a lucky number?
As to the research in TFA, well, I don't know. They're talking about possible influence from Ethiopia 1600 years ago, when Phoenician goes back twice as far. Yet the time period, 5th century, does coincide with the collapse of the Roman Empire, barbarian invasions, and the decline of both Latin and Greek writing. Perhaps such things as Cyrillic could spread more easily because it was filling the void the Roman collapse left behind. I gather there seems to have been a big lingual shift in the Middle East in the 1st century, with a lot of ancient languages being lost around that time. The Roman conquest of Ptolemaic Egypt pressured the people to forget Egyptian hieroglyphs, and it seems they largely did. Aramaic was the lingua franca of those days, and even it declined greatly. It wasn't forgotten, but after Alexander the Great conquered the Persian Empire and the successor polity, the Seleucid Empire, relegated Aramaic to a lesser status with their Hellenization and preference for Greek, it did change significantly. In such an environment, an already near extinct writing system such as Cuneiform couldn't hang on.