X-Git-Url: https://projects.mako.cc/source/state_of_wikimedia_research_2015/blobdiff_plain/10463fabeab4400b02b1cfa7bf06aea96214e621..7cd2a85d1c8bc2d5189e0ad63b44756dc3b24b3d:/20150717-wikimania_research.tex?ds=sidebyside

diff --git a/20150717-wikimania_research.tex b/20150717-wikimania_research.tex
index 854624e..8150bad 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}
 
@@ -489,20 +548,97 @@
 
 
 
-% \begin{frame}
-%   \frametitle{Wikipedia Viewership and Flu Prediction: Results}
+\begin{frame}
+   \centertext{6em}{Automation in Wikipedia}
+
+   \note{Tilman
+   
+     Starting to see more practical applications of AI methods to editing.
+
+     Bots have been writing Wikipedia articles ever since back in 2002, 
+     User:Rambot covered US municipalities from US census data.
+     
+     Picked these two related papers for their somewhat unusual approach}
+\end{frame}
+
+
+\begin{frame}
+  \frametitle{Automation in Wikipedia}
+
+  \larger \larger
+  Banerjee et al., \e{Playscript Classification and Automatic Wikipedia 
+  Play Articles Generation}. 
+  2014 22nd International Conference on Pattern Recognition (ICPR). 
+  pp. 3630–3635. 
+  \href{http://dx.doi.org/10.1109/ICPR.2014.624}
+  {DOI:10.1109/ICPR.2014.624}
+  \href{http://www.cse.unt.edu/~ccaragea/papers/icpr14.pdf}{Author's copy}
+
+\end{frame}
+
+
+\begin{frame}
+
+\frametitle{Automation in Wikipedia: Bot-written theatre play articles}
+
+  \begin{itemize}
+   \larger \larger \larger
+   \item Bot searches for playscripts and related documents on the web
+     \bigskip
+   \item Extract key information from them, e.g.
+     \begin{itemize} \larger
+      \item The play's main characters
+      \item Relevant sentences from online synopses of the play
+      \item Mentions in Google Books and Google News (as evidence that 
+      the play satisfies Wikipedia's notability criteria)
+      
+      \end{itemize}
+      
+      \item Some heuristics to exclude non-encyclopedic sentences, e.g. 
+       first person statements
+      
+   \end{itemize}
+
+    \note{Tilman
+    
+	   NB: Most article creation bots work from well-defined databases
+	   (e.g. species, census data, geographical databases). 
+    
+       This bots finds article topics and online references itself, 
+       using an elaborate classifier algorithm to distinguish scripts 
+       from non-scripts.}
+\end{frame}
+
+\begin{frame}
+\frametitle{Automation in Wikipedia: Bot-written theatre play articles}
 
-%   \centering
-%   \includegraphics[width=\textwidth]{figures/flu.png}
+  \includegraphics[width=0.3\textwidth]{figures/Fourteen_submission.png}
+  \begin{itemize}
+   \larger \larger \larger
+   \item 15 articles submitted at Articles for Creation. Two accepted 
+   by Wikipedia editors. One of them without major changes.
+   
+      
+   \end{itemize}
 
-% \note{\begin{itemize}
-%   \larger \larger
+    \note{Tilman
+    
+    Editors were unaware the articles had been automatically generated.
+    
+    
+    Related paper by some of the same authors:
+  
+    Banerjee et al., \e{WikiKreator: Improving Wikipedia Stubs 
+    Automatically}. \href{https://siddbanpsu.github.io/publications/acl2015-banerjee-preprint.pdf}
+    {preprint}, accepted paper at ACL2015
+    
+    Elaborate classifier method to find suitable web resources for 
+    expanding stubs - but copying sentences wholesale from these into
+    articles landed the bot (User:MightyPepper) in a \href{https://en.wikipedia.org/wiki/Wikipedia:Contributor_copyright_investigations/Archive#2015}{contributor copyright investigation}\ldots
+    }
+\end{frame}
 
-%   \item Wikipedia better than Google at predicting peak flu weeks.
-%   \item Wikipedia better at predicting relative influenza rates.
-%   \end{itemize}}
 
-% \end{frame}
 
 
 %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
@@ -578,7 +714,7 @@ 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 +864,12 @@ 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