Posts by Kat Hagedorn

Formalizing Accessions from Patrons for HathiTrust: “Hey, would you like this book I've got?”

Over the past several months, Digital Content & Collections has worked on new procedures for handling accessions from patrons for HathiTrust. What happens if no HathiTrust contributing institution has their volume on their shelves, and the volume is a good addition to the HathiTrust corpus? In these cases, U-M Library steps into the breach. We can easily handle a small throughput of these volumes from HathiTrust, and we handle three kinds of accessions: physical, digital and virtual.

Quality in HathiTrust (Re-Posting)

Skew in a Google-digitized volume in HathiTrust

This is a re-posting of a HathiTrust blog post. HathiTrust receives well over a hundred inquiries every month about quality problems with page images or OCR text of volumes in HathiTrust. That’s the bad news. The good news is that in most of these cases, there is something they can do about it. A new blog post is intended to shed some light on the thinking and practices about quality in HathiTrust.

Practical Relevance Ranking for 11 Million Books, Part 3: Document Length Normalization

Relevance is a complex concept which reflects aspects of a query, a document, and the user as well as contextual factors. Relevance involves many factors such as the user's preferences, task, stage in their information-seeking, domain knowledge, intent, and the context of a particular search. This post is the third in a series by Tom Burton-West, one of the HathiTrust developers, who has been working on practical relevance ranking for all the volumes in HathiTrust for a number of years.

Practical Relevance Ranking for 11 Million Books

Relevance weight vs. term occurrences

Relevance is a complex concept which reflects aspects of a query, a document, and the user as well as contextual factors. Relevance involves many factors such as the user's preferences, task, stage in their information-seeking, domain knowledge, intent, and the context of a particular search. Tom Burton-West, one of the HathiTrust developers, has been working on practical relevance ranking for all the volumes in HathiTrust for a number of years.

Pager

Page 1 of 3