Replace the OCR engine
It's well past time that the OCR engine was replaced with one fit for the 21st Century.
The present one omits thousands, if not millions, of random words for no obvious reason, and not because the image is flawed, and often ignores the column boundaries. On many pages the OCR result is missing completely.
A modern fit-for-purpose OCR engine would make a massive improvement.
Extremely disappointed with the Optical Character Recognition OCR software. Makes me suspicious. Is the British Newspaper Archive just a front for some more sinister organisation set up to hide information by wasting the searchers time and making them give up out of sheer frustration. Is it just a front for Orwell's Ministry of Information?
Graham Wootten commented
Quite agree. It is absolutely useless!