
The BestRef database contains results of assessment of over 3 million websites in different language versions of @Wikipedia.
Joined April 2020
- Tweets169
- Following53
- Followers116
- Likes281
🔍 How can AI help assess Wikipedia quality at scale?
At the conference “Open Knowledge: #Wikimedia & Research in the CEE Region”, Dr. Włodzimierz Lewoniewski presented research on #Wikipedia content, information sources, data visualizations.
More info: kie.ue.poznan.pl/en/news/mea…
BestRef retweeted
📏 Measuring #Wikipedia Quality at Scale: Assessment of Content, Information Sources, Data Visualizations. 👨🏫 Presented at #OpenKnowledge: #Wikimedia & #Research in the CEE Region.
🧩 Slides: doi.org/10.6084/m9.figshare.…
BestRef retweeted
"Can Language Models Play the Wikipedia Game?" (get from one article to another via article links) arxiv.org/html/2610.13948v1
"No model significantly outperformed humans, although the best models (GPT-o3 mini, GPT-4o, QwQ:32B, and DeepSeek-R1:70B) achieved comparable success."
BestRef retweeted
🌐🏆 The most prominent websites in Wikipedia information sources: to identify them, more than 400 million references from approximately 68 million articles across more than 300 #Wikipedia language editions were analyzed blog.wikirank.net/2026/the-m…
BestRef retweeted
🧩 A new interactive map of the most popular articles on English #Wikipedia is now available. You can use this tool to search for articles, explore them as colourful puzzle pieces, zoom in, and trace how readers move from one article to another. wikipedia-map.net/
BestRef retweeted
"WikiStar: A System for Shedding Light on the Hidden History of Scientific Wikipedia Articles", detecting edit types such as "technical term added" using an LLM classifier arxiv.org/html/2607.12441v3
(with human-annotated benchmark dataset)
📢 #BestRef July 2026 update!
🔬4.2 million websites from more than 400 million #Wikipedia references across 300+ language editions were analyzed.
🌍 This update provides a unique view of the sources @Wikipedia relies on most.
🔍 Try it now: bestref.net
BestRef retweeted
🌐 Which websites matter most as information sources on #Wikipedia?
📊 More than 400M citations from 68M articles across 300+ language editions were analyzed, taking into account both citation frequency and article popularity.
🚀 Explore more: en.lewoniewski.info/2026/mos…
BestRef retweeted
📊 The obvious way to measure popularity of #Wikipedia articles is to count how many people read it.
🌐 #Wikilink analysis asks a different question: how many other articles depend on this page as a reference point?
💡 Measuring Wikipedia by #Wikilinks: blog.wikirank.net/2026/most-…
BestRef retweeted
New paper with Dylan Walker, now open access in Management Science: "The AI Democratization Paradox."
We ask: when AI lowers barriers to knowledge production, does it democratize participation, or amplify existing inequality?
A thread on Wikipedia + AI translation.
BestRef retweeted
🎉 With Wikimania in full swing, the 2026 Wikimedian of the Year winners have been announced: French Wikipedia's Jules* (top honor), Laureates Dreamyshade & Barkeep49, Community Connector Chlod Alejandro, plus honorees Mari Avetisyan & Hijiri Umemoto. 🌍📚
diff.wikimedia.org/2026/07/2…
BestRef retweeted
"Multilingual Reference Need Assessment System for Wikipedia", using a BERT-based model arxiv.org/pdf/2603.17146
(Model card: meta.wikimedia.org/wiki/Mach… )
BestRef retweeted
🎬 Watch the dynamic history and evolution of #Wikisource from its inception in 2003 all the way to 2026! youtube.com/watch?v=7gJPkolu…
BestRef retweeted
Honored to have received the this award for our demo "Wikipedia Community Health Dashboards", check them out here:
vitalsigns.wmcloud.org/
Congrats to the winners of this year's best paper, best dataset paper, best poster paper, and best Web Agent demo/poster 🎉
#ICWSM2026
BestRef retweeted
"Multilingual and Cross-Lingual Citation Needed Detection on Wikipedia for Lower-Resource Languages" arxiv.org/pdf/2605.31136 (Data and code: github.com/gerritq/mcn )
"SLMs [small language models] outperform LLMs on monolingual CND"
BestRef retweeted
🇮🇹🎥 Introduzione alla valutazione automatica della qualità di #Wikipedia
youtube.com/watch?v=lrRqaRZI…
BestRef retweeted
In the latest issue of our newsletter:
* "Wikilambda the ultimate: the Wikimedia foundation’s search for the perfect language" (with Wikifunctions/Abstract Wikipedia)
And other recent research publications involving Wikidata and Wikipedia
meta.wikimedia.org/wiki/Rese…
BestRef retweeted
"@Wikipedia at 25: The Encyclopedia That Shouldn't Exist" @JemielniakD on how its governance structure, quality control mechanisms, and integration into educational practice make Wikipedia work.
osf.io/preprints/socarxiv/sh…
BestRef retweeted
🎬 The most cited articles on #Wikipedia.
📊 1.6 billion unique links between English Wikipedia pages were analyzed using dumps from May 2026.
#DataVisualization #DataViz #BarChart #OpenData #NetworkAnalysis #WikiLinks #DataScience
youtube.com/watch?v=waBg-LR6…
BestRef retweeted
"The Web of Knowledge: Encyclopedias and Authority in the Digital Age" (book review) ijoc.org/index.php/ijoc/arti…
"Wikipedia as epistemic infrastructure represents a new order of knowledge production"























![Figure 2: Dataset examples from the Wikipedia articles “London” and “Avatar (2009 film)” [from Quaremba et al. 2026, CC BY 4.0]](https://pbs.twimg.com/media/HKbofRlaMAAWMp7.png?name=small&format=webp)
