New published paper about temporal bias in historical newspaper digitization

A new paper,  Temporal bias in historical newspaper digitization: evidence from reconstructing the British mandate trademark registry, was just published by the Journal of Documentation. A camera-ready draft is available to download.

The paper by Eran Toch, Bar Ifrah (a graduate student working on a graduate project), and Michael Birnhack from the Faculty of Law, describes how we reconstructed a database of trademarks (i.e., logos) from the Palestine Gazette, the official newspaper of the British Mandate government.

We developed a relatively simple learning algorithm that identifies trademark images and links them to textual information. Thanks to the newspaper’s fixed format, we were able to identify a systematic time-dependent bias, which can shape what we can see in digitized sources.

The reconstructed trademark registry is available online.