2025-08-07 –, NAKURU
Language: English
🎥 Session recording: https://youtu.be/t3BFx7qS7vU?list=PLhV3K_DS5YfJtMBKTkOdmzfP3ENS24BJ-&t=20033 🎥
"Hunting for Lost Heritage": how to create thousands of new items on Wikidata about "lost heritage", using data mining on existing images on Wikimedia Commons.
A lot of content has been produced with crowdsourcing by Wikimedia users, not only on Wikipedia. Hundreds of thousands of photographs of cultural heritage were uploaded in the last 20 years and are available on Wikimedia Commons, still not linked to structured data on Wikidata, often of unknown historical buildings, like ruined churches in Southern Italy. We will demostrate that is possible to use data mining techniques on Wikimedia projects and build on Wikidata a more comprehensive open catalogue of Cultural heritage in Italy from crowdsourced contents. We will present the result of phase 1 and 2 of this project, where OpenRefine was used to create thousands of new items on Wikidata about "lost heritage" of Italy, and discuss of the possible use of AI to speed-up the process in phase 3.
A presentation is available in https://commons.wikimedia.org/wiki/File:Hunting_for_lost_heritage_on_Wikimedia.pdf
- What other themes or topics does your session fit into? Please choose from the list of tags below.
-
Collaboration
- How does your session relate to the event theme: Wikimania@20: Inclusivity. Impact. Sustainability?
-
Being based on the re-use of existing data on Commons, this is a very low-budget project than could be adoped and run in autonomy by many Wikimedia contributors worldwide. It aims to expand the consciousness of importance of cultural heritage, and in particular of local cultural heritage. Tools used are completely free and open source.
- What is the experience level needed for the audience for your session?
-
Everyone can participate in this session
- How do you plan to deliver this session? You will be asked to confirm this closer to the date in case of changes to the format.
-
Dialing in from a remote location
- Should your session be selected for the program, do you agree to release your session and supporting materials on-wiki and on the eventyay platform under CC BY-SA 4.0?
-
I agree
An active contributor to Wikipedia since 2004, he's one of the admins of it.wiki since 2005. He's a member of Wikimedia Italy staff as a trainer and GLAM specialist. As a Wikipedian in residence he collaborated on many OpenGLAM projects. Since 2021 he has been among the first two Wikimedians in residence at an Italian university. He created 3 MOOCs for students, teachers and cultural institutions. He’s migrating the Museo Egizio di Torino catalogues to Wikimedia projects.