X-Git-Url: https://projects.mako.cc/source/state_of_wikimedia_research_2015/blobdiff_plain/10463fabeab4400b02b1cfa7bf06aea96214e621..c68a60b6fe8adc33137eac5435f7283b00b3e057:/20150717-wikimania_research.tex

diff --git a/20150717-wikimania_research.tex b/20150717-wikimania_research.tex
index 854624e..cc75b30 100644
--- a/20150717-wikimania_research.tex
+++ b/20150717-wikimania_research.tex
@@ -337,12 +337,55 @@
 
 \end{frame}
 
+\begin{frame}
+  \frametitle{How to measure the global influence of languages?}
+
+  \larger \larger
+
+  \e{Traditional} methods rely on:
+
+  \begin{itemize}
+    \larger \larger
+  \item \e{Population} of speakers
+  \item \e{Income} or political power of speakers
+  \end{itemize}
+
+  Paper presents \e{new network method} based on measuring
+  \e{co-speakers} of languages in several data sources including
+  Wikipedia.
+
+\end{frame}
+
 \begin{frame}
   \frametitle{Wikipedia as a source of data: Ronen et al.}
 
   \includegraphics[width=\textwidth]{figures/ronen_fig1.png}
+
+  \note{Two languages are connected when users that edit an article in
+    one Wikipedia language edition are significantly more likely to
+    also edit an article in the edition of the other language.
+
+    If an editor of Spanish is also likely to edit Galician, we'll
+    call those languages connected.}
 \end{frame}
 
+\begin{frame}
+  \frametitle{Wikipedia as a source of data: Ronen et al.}
+
+  \includegraphics[width=\textwidth]{figures/ronen_people.png}
+
+  \note{\begin{itemize}
+    \item The number of people per language (born 1800–1950) with
+      articles in at least 26 Wikipedia language editions as a
+      function of their language’s eigenvector centrality.
+    \item The bottom row shows the number of people per language (born
+      1800–1950) listed in \emph{Human Accomplishment} (a book by
+      Charles Murray) as a function of their language’s eigenvector
+      centrality.
+    \end{itemize}}
+\end{frame}
+
+
 \subsection{Community and Organization}
 
 \begin{frame}
@@ -366,13 +409,29 @@
 
 \begin{frame}
   \frametitle{Community and organization: Warncke-Wang et al.}
+  
+  \larger \larger
+  \e{Perfect Alignment Hypothesis (PAH)}: There is an exact match
+  between the supply of high-quality content and the demand for it.
+
+  \bigskip
 
   \includegraphics[width=\textwidth]{figures/warncke-english_confusion.pdf}
+
+  \note{\e{Quality}: Stub, Start, C, B, Good Article, A, Featured Article
+  
+    \e{Popularity}: equivalently sized buckets}
 \end{frame}
 
 \begin{frame}
   \frametitle{Community and organization: Warncke-Wang et al.}
 
+  Measure of the degree of misalignment can be used to build lists of
+  categories that are relatively \e{``overproduced''} and
+  \e{``underproduced''}:
+
+  \bigskip
+
   \includegraphics[width=\textwidth]{figures/warncke-english_overunder.pdf}
 \end{frame}
 
@@ -578,7 +637,7 @@ AAAI Conference on Web and Social Media (ICWSM).
  \item 2: Articles about women tend to be less centrally connected in
    the network of articles than articles about men (Smurfette!)
  \item 3: (\e{viz}) Content of articles about women uses different words
-   than those about men. Much igher incidence of language related to
+   than those about men. Much higher incidence of language related to
    family, gender, and relationships.
    \end{itemize}
 }
@@ -728,3 +787,12 @@ AAAI Conference on Web and Social Media (ICWSM).
 
 \end{document}
 
+
+%  LocalWords:  xshift yshift makopurple Tilman wikipedia Scopus Hu
+%  LocalWords:  Ronen Gonçalves Vespignani Hidalgo al Galician Ranjan
+%  LocalWords:  eigenvector Warncke Terveen Hecht underproduced NEJM
+%  LocalWords:  Hwang Engl doi Kräenbring WebMD WikiProject Mohsen
+%  LocalWords:  Jadidi Markus Strohmaier Wikipedias WPs Smurfette
+%  LocalWords:  Barnhisel Rapchak WikiEd Mesgari Mostafa Okoli Chitu
+%  LocalWords:  Mehdi Mohamad Årup Lanamäki Arto Miquel Ribé OpenSym
+%  LocalWords:  WikiPapers