On December 16, 2020, during the Wikimedia Research Showcase, the results of scientific works conducted by members of the Department of Information Systems in the area of information quality assessment in multilingual Wikipedia were presented. In particular, the models of automatic evaluation of the reliability of sources in this popular encyclopedia were discussed.
Information in Wikipedia can be edited in over 300 languages independently. Therefore often the same subject in Wikipedia can be described differently depending on language edition. In order to compare information between them one usually needs to understand each of considered languages. Team of the Department of Information Systems (DIS) works on solutions that can help to automate this process. They leverage machine learning and artificial intelligence algorithms. The crucial component, however, is assessment of article quality therefore we need to know how to define and extract different quality measures.
During the event Dr. Włodzimierz Lewoniewski briefly introduced some of the recent activities of the DIS related to quality assessment of multilingual content in Wikipedia. In particular, he demonstrated some of the approaches for the reliability assessment of sources in Wikipedia articles. Such solutions can help to enrich various language editions of Wikipedia and other knowledge bases (such as DBpedia and Wikidata) with information of better quality.
Presentation on quality assessment of Wikipedia and its sources:
The Monthly Wikimedia Research Showcase is a public event with presentations of recent research by the Wikimedia Foundation’s Research Team and guest presenters from the academic community. The showcase is hosted at the Wikimedia Foundation every 3rd Wednesday of the month at 11.30 Pacific Time and is live-streamed on YouTube. Below is a video from the December 2020 edition:
For more information about the Wikimedia Research can be found on Twitter and MediaWiki