Add new presentation with vocabulary extraction

master.tex

@@ -187,113 +187,54 @@ Department for Computer-Networks and Communication-Systems}
 	\end{itemize}
 \end{frame}
 
-\begin{frame}
-	\begin{center}
-		\includegraphics[width=0.8\textwidth]{bilder/Overview.png}
-
-		Overview by \cite{SchaeferStede2021}.
-		CA = Corpus Annotation,
-		AD = Argument Detection,
-		SD = Stance Detection,
-		CD = Claim Detection.
-	\end{center}
-\end{frame}
 
 \begin{frame}
 	\begin{center}
-		\includegraphics[width=0.75\textwidth]{bilder/AnnotationSchema.png}
-
-		Overview by \cite{SchaeferStede2021}.
-	\end{center}
-\end{frame}
-
-\begin{frame}
-	\begin{center}
-		\begin{columns}
-			\column{0.5\textwidth}
-				\begin{center}
-					\includegraphics[width=0.8\textwidth]{bilder/Corpus.png}
-	
-					Corpora + IAA reported \cite{SchaeferStede2021}.
-					ADU = Argument Discourse Unit,
-					cx = Cohens Kappa
-				\end{center}
-			\column{0.5\textwidth}
-				\begin{center}
-					\includegraphics[width=0.8\textwidth]{bilder/PrevResults.png}
-		
-					Results reported by \cite{SchaeferStede2021}.
-					ADU = Argument Discourse Unit,
-					cx = Cohens Kappa
-				\end{center}
-			\end{columns}
+		\includegraphics[scale=0.3]{bilder/Pipeline}
 	\end{center}
-
 \end{frame}
 
-
 \section{Current}
 \begin{frame}
 	\begin{center}
-		\includegraphics[scale=0.3]{bilder/Pipeline}
+		\includegraphics[scale=0.3]{bilder/Pipeline_Vocab}
 	\end{center}
 \end{frame}
 
-\begin{frame}{\#abortion}
+\begin{frame}{Kialo}
 	\begin{center}
 		\begin{columns}
 			\column{0.5\textwidth}
-				\begin{center}
-					\includegraphics[scale=0.2]{bilder/Abortion_WordCloud.png}
-				\end{center}
+				\includegraphics[scale=0.1]{bilder/kialo.jpg}
 			\column{0.5\textwidth}
-				\begin{center}
 				\begin{itemize}
-						\item Topic: Abortion
-						\item Time: 2021-08-15 - 2021-10-15
-						\item Root-Tweets: 15.273
-						\begin{itemize}
-							\item Conversation-Starter: 2.250
-						\end{itemize}
-						\item Conversation-Tweets: 14.569
+					\item Labeled Arguments (Pro/Con)
+					\item Strict Guidelines
+					\item Reviewed
 				\end{itemize}
-				\end{center}
 		\end{columns}
 	\end{center}
+	\begin{tcolorbox}[colback=cyan!5!white,colframe=cyan!75!black,title=Kialo Claim]
+		A \textbf{claim} is, in its most basic form, a \textbf{single piece} of an \textbf{argument} made in a discussion. 
+		[...]
+		This \textbf{allows} you to \textbf{inspect} each step of the \textbf{thinking behind} an \textbf{argument}. 
+	\end{tcolorbox}
 \end{frame}
 
-\begin{frame}{\#abortion}
-	\begin{center}
-		\includegraphics[scale=0.3]{bilder/Abortion_Time.png}
-	\end{center}
-\end{frame}
-
-\begin{frame}{\#brexit}
-	\begin{center}
-		\begin{columns}
-			\column{0.5\textwidth}
-				\begin{center}
-					\includegraphics[scale=0.2]{bilder/Brexit_WordCloud.png}
-				\end{center}
-			\column{0.5\textwidth}
+\begin{frame}{Datasets}
 	\begin{center}
 		\begin{itemize}
-						\item Topic: Brexit
-						\item Time: 2020-01-01 - 2020-03-01
-						\item Root-Tweets: 151.090
+			\item [Kialo]:
 			\begin{itemize}
-							\item Conversation-Starter: 24.806
+				\item[abortion]: 3.201 Claims
+				\item[brexit]: 2.554  Claims
+			\end{itemize}
+			\item [Twitter]:
+			\begin{itemize}
+				\item[abortion]: 2.250 Root-Tweets
+				\item[brexit]: 24.806 Root-Tweets
 			\end{itemize} 
-						\item Conversation-Tweets: 275.968
 		\end{itemize}
-				\end{center}
-			\end{columns}
-	\end{center}
-\end{frame}
-
-\begin{frame}{\#brexit}
-	\begin{center}
-		\includegraphics[scale=0.3]{bilder/Brexit_Time.png}
 	\end{center}
 \end{frame}
 
@@ -307,9 +248,9 @@ Department for Computer-Networks and Communication-Systems}
 						\begin{tabular}{@{}lll@{}}
 							\toprule
 							\textbf{Open} & \textbf{Closed} & \textbf{Other} \\ \midrule
-								ADJ & \textbf{AUX} & PUNCT \\
-								ADV & \textbf{CCONJ} & SYM \\
-								INTJ & DET & X \\
+								\textbf{ADJ} & \textbf{AUX} & PUNCT \\
+								\textbf{ADV} & \textbf{CCONJ} & SYM \\
+								INTJ & \textbf{DET} & X \\
 								NOUN & NUM &  \\
 								PROPN & PART &  \\
 								\textbf{VERB} & PRON &  \\
@@ -320,138 +261,141 @@ Department for Computer-Networks and Communication-Systems}
 				\end{center}
 			\column{0.6\textwidth}
 				\begin{itemize}
-					\item Universal POS Tagging
-					\item spaCy: en\_core\_web\_sm
-					\item Open v. Closed $\approx$ Content v. Function
-					\item Selection supposed by \cite{Knott1993}.
+					\item \textbf{ADJ}: \\
+						modify, specify nouns
+					\item \textbf{ADV}: \\
+						modify, specify verbs	
+					\item \textbf{*VERB}: \\
+						typically signal events and actions
+					\item \textbf{*AUX}: \\
+						adds funct. or gramma. meaning
+					\item \textbf{*CCONJ}: \\
+						expresses a semantic relationship
+					\item \textbf{DET}: \\
+						express references in context
+					\item \textbf{*SCONJ}:\\
+						making one construction part of the other
 				\end{itemize}
 			\end{columns}
 	\end{center}
 \end{frame}
 
-\begin{frame}{POS-Tagging}
+\begin{frame}{POS-Tag Distribution by words}
 	\begin{center}
-		\begin{columns}
-			\column{0.4\textwidth}
-				\begin{center}
-					\begin{table}[]
-						\resizebox{0.8\textwidth}{!}{%
-						\begin{tabular}{@{}lll@{}}
-							\toprule
-							\textbf{Open} & \textbf{Closed} & \textbf{Other} \\ \midrule
-								ADJ & \textbf{AUX} & PUNCT \\
-								ADV & \textbf{CCONJ} & SYM \\
-								INTJ & DET & X \\
-								NOUN & NUM &  \\
-								PROPN & PART &  \\
-								\textbf{VERB} & PRON &  \\
-						 		& \textbf{SCONJ} &  \\ \bottomrule
-							\end{tabular}%
-						}
-						\end{table}
+		\includegraphics[width=\textwidth]{bilder/PosDis.png}
 	\end{center}
-			\column{0.6\textwidth}
+\end{frame}
+
+\begin{frame}{Vocabulary Selection}
 	\begin{itemize}
-					\item \textbf{VERB}: \\
-						typically signal events and actions
-					\item \textbf{AUX}: \\
-						adds funct. or gramma. meaning
-					\item \textbf{CCONJ}: \\ 
-						links words or larger constituents,\\
-						expresses a semantic relationship
-					\item \textbf{SCONJ}:\\
-						making one construction part of the other,\\
-						join independent and a dependent clause
+		\item [1] Sorting Word-Lemma per POS-Tag by occurance
+		\item [2] Select Index with best Spearman-Rank-Correlation
+		\item [3] Intersection of all Dataset per POS-Tag till best Index
 	\end{itemize}
-			\end{columns}
-	\end{center}
 \end{frame}
 
-\begin{frame}{POS-Tagging Conversation Starter}
+\begin{frame}{Step 1: Example SCONJ}
 	\begin{center}
-		\includegraphics[scale=0.3]{bilder/Abortion_POS.png}
+	\begin{tabular}{lllll}
+			\toprule
+				{} & \textbf{abortion\_kialo} & \textbf{brexit\_kialo} & \textbf{abortion} &   \textbf{brexit} \\
+			\midrule
+				0  &           that &         that &     that &     that \\
+				1  &             if &           if &       if &       if \\
+				2  & \textbf{because} &           \textbf{as} &      how &      how \\
+				3  &           when &      \textbf{because} &     when &       \textbf{as} \\
+				4  &             \textbf{as} &         when &      why &     when \\
+				5  &          where &        since &  \textbf{because} &      why \\
+				6  &        whether &          for &       \textbf{as} &  \textbf{because} \\
+				7  &            for &          how &    where &    where \\
+				8  &          while &        while &    while &      for \\
+				9  &          since &         than &    since &    since \\
+				10 &            how &        where &      for &    after \\
+				11 &            why &      whether &    until &    while \\
+				12 &           than &          why &   before &       so \\
+				13 &           upon &       before &    after &     like \\
+				14 &          after &        after &  whether &     than \\
+			\bottomrule
+		\end{tabular}
 	\end{center}
 \end{frame}
 
-\begin{frame}{POS-Tagging Conversation Starter}
+\begin{frame}{Step 2: Best Indices}
 	\begin{center}
-		\includegraphics[scale=0.3]{bilder/Brexit_POS.png}
+		\begin{tabular}{lll}
+			\toprule
+				\textbf{Tag} & \textbf{Spearman} & \textbf{Index} \\
+			\midrule
+				SCONJ & 0.93 & 26 \\
+				CCONJ & 0.83 & 10 \\
+				AUX & 0.91 & 26 \\
+				VERB & 1.0 & 10 \\
+				DET & 0.97 & 27 \\
+				ADJ & 1.0 & 10 \\
+				ADV & 0.89 & 30 \\
+			\bottomrule
+		\end{tabular}
 	\end{center}
 \end{frame}
 
-\begin{frame}{POS-Tagging Words (PWords)}
-	\begin{table}[]
-		\centering
-		\resizebox{\textwidth}{!}{%
-			\begin{tabular}{@{}llllllll@{}}
+\begin{frame}{Step 3: Vocabulary Selection}
+	\begin{center}
+	\resizebox{0.75\textwidth}{!}{
+		\begin{tabular}{llllllll}
 			\toprule
-				\multicolumn{2}{c}{\textbf{SCONJ}} & \multicolumn{2}{c}{\textbf{CONJ}} & \multicolumn{2}{c}{\textbf{AUX}} & \multicolumn{2}{c}{\textbf{VERB}} \\ \midrule
-				\textit{\textbf{Brexit}} & \multicolumn{1}{l|}{\textit{\textbf{Abortion}}} & \textit{\textbf{Brexit}} & \multicolumn{1}{l|}{\textit{\textbf{Abortion}}} & \textit{\textbf{Brexit}} & \multicolumn{1}{l|}{\textit{\textbf{Abortion}}} & \textit{\textbf{Brexit}} & \textit{\textbf{Abortion}} \\ \midrule
-				that & \multicolumn{1}{l|}{that} & and & \multicolumn{1}{l|}{and} & is & \multicolumn{1}{l|}{is} & have & have \\
-				if & \multicolumn{1}{l|}{if} & but & \multicolumn{1}{l|}{but} & will & \multicolumn{1}{l|}{are} & get & get \\
-				how & \multicolumn{1}{l|}{how} & or & \multicolumn{1}{l|}{or} & be & \multicolumn{1}{l|}{be} & going & do \\
-				as & \multicolumn{1}{l|}{when} & + & \multicolumn{1}{l|}{+} & are & \multicolumn{1}{l|}{will} & know & want \\
-				when & \multicolumn{1}{l|}{why} & plus & \multicolumn{1}{l|}{yet} & have & \multicolumn{1}{l|}{can} & \textbf{leave} & know \\
-				why & \multicolumn{1}{l|}{because} & so & \multicolumn{1}{l|}{nor} & can & \multicolumn{1}{l|}{do} & \textbf{voted} & make \\
-				because & \multicolumn{1}{l|}{as} & both & \multicolumn{1}{l|}{both} & has & \multicolumn{1}{l|}{should} & want & \textbf{need} \\
-				where & \multicolumn{1}{l|}{where} & yet & \multicolumn{1}{l|}{neither} & was & \multicolumn{1}{l|}{was} & \textbf{see} & think \\
-				since & \multicolumn{1}{l|}{while} & either & \multicolumn{1}{l|}{so} & do & \multicolumn{1}{l|}{have} & think & let \\
-				for & \multicolumn{1}{l|}{since} & nor & \multicolumn{1}{l|}{either} & am & \multicolumn{1}{l|}{would} & let & \textbf{has} \\
-				after & \multicolumn{1}{l|}{after} & n & \multicolumn{1}{l|}{n} & would & \multicolumn{1}{l|}{has} & \textbf{done} & \textbf{say} \\
-				while & \multicolumn{1}{l|}{\textbf{until}} & • & \multicolumn{1}{l|}{plus} & \textbf{been} & \multicolumn{1}{l|}{am} & do & going \\
-				\textbf{so} & \multicolumn{1}{l|}{for} & neither & \multicolumn{1}{l|}{•} & were & \multicolumn{1}{l|}{\textbf{does}} & \textbf{go} & \textbf{had} \\
-				\textbf{like} & \multicolumn{1}{l|}{\textbf{before}} & \textbf{minus} & \multicolumn{1}{l|}{} & \textbf{could} & \multicolumn{1}{l|}{\textbf{being}} & \textbf{leaving} & \textbf{support} \\
-				\textbf{despite} & \multicolumn{1}{l|}{\textbf{whether}} & \textbf{daythe} & \multicolumn{1}{l|}{} & should & \multicolumn{1}{l|}{were} & make & \textbf{said} \\ \bottomrule
-				\end{tabular}%
+				{} &    \textbf{SCONJ} &   \textbf{CCONJ} &     \textbf{AUX} &  \textbf{*VERB} &       \textbf{DET} &    \textbf{*ADJ} &     \textbf{*ADV} \\
+			\midrule
+				0  &    after &     and &      \textbf{be} &    \textbf{be} &         a &   more &    also \\
+				1  &       as &    both &     can &    \textbf{do} &       all &  other &  always \\
+				2  &  because &     but &   could &  \textbf{have} &        an &        &      as \\
+				3  &   before &  either &      \textbf{do} &  make &   another &        &    even \\
+				4  &  despite &     nor &     get &       &       any &        &    just \\
+				5  &      for &      or &    \textbf{have} &       &      both &        &    long \\
+				6  &      how &      so &  having &       &      each &        &    more \\
+				7  &       if &     yet &     may &       &    either &        &    most \\
+				8  &     once &         &   might &       &     every &        &   never \\
+				9  &    since &         &    must &       &      half &        &    only \\
+				10 &       so &         &    need &       &        no &        &      so \\
+				11 &     than &         &   shall &       &     quite &        &   still \\
+				12 &     that &         &  should &       &      some &        &    then \\
+				13 &   though &         &      to &       &      such &        &     too \\
+				14 &   unless &         &    will &       &      that &        &    very \\
+				15 &    until &         &   would &       &       the &        &    well \\
+				16 &     upon &         &         &       &     these &        &         \\
+				17 &     when &         &         &       &      this &        &         \\
+				18 &    where &         &         &       &     those &        &         \\
+				19 &  whether &         &         &       &      what &        &         \\
+				20 &    while &         &         &       &  whatever &        &         \\
+				21 &      why &         &         &       &     which &        &         \\
+				22 &     with &         &         &       &     whose &        &         \\
+			\bottomrule
+		\end{tabular}
 	}
-	\end{table}
+	\end{center}
 \end{frame}
 
-\begin{frame}{Pre-Selection}
+\begin{frame}{First Impression}
+	Using vocab. with SCONJ, CCONJ, AUX, DET:
 	\begin{itemize}
-		\item Conditions:
-		\begin{itemize}
-			\item [1] At least one word in PWords
-			\item [2] At least 200 characters long
-		\end{itemize}
-		\item \#Abortion: $\Rightarrow$ 1.400 Candidates
-		\item \#Brexit: $\Rightarrow$ 11.842 Candidates
+		\item [$\Rightarrow$] 0.069\% dropoff in abortion
+		\item [$\Rightarrow$] 0.066\% dropoff in brexit
+		\item [$\Rightarrow$] Dropoff = Adds, Allegations, Comments, Links etc.
+		\item [$\Rightarrow$] Root-Tweets $\geq$200 chars) could be better
 	\end{itemize}
 \end{frame}
 
-\begin{frame}
-	\begin{tcolorbox}[colback=cyan!5!white,colframe=cyan!75!black,title=Example 1: \#Brexit]
-		\textbf{How} ironic \textbf{is} this? \textbf{For} 4 years, \textcolor{orange}{\#Remainers} predicted \textbf{that} \textcolor{orange}{\#Brexit} \textbf{would} cause a catastrophic national crisis. Now \textbf{that} Brexit \textbf{has} happened at long last, we \textbf{are} indeed facing a catastrophic national crisis, \textbf{but} it \textbf{has} absolutely nothing to \textbf{do} with Brexit. Go figure \textbf{that} one out.
-		%\textcolor{red}{RT} \textcolor{magenta}{@SaysSheToday}: The $[$Dixie Chicks$]_{c}$ were attacked just for $[$using 1A right$]_{p_1}$ to say they were ashamed of GWB. They $[$didn’t commit treason$]_{c}$ $[$like the \textcolor{orange}{\#47Senators}$]_{p_2}$
-	\end{tcolorbox}
-\end{frame}
-\begin{frame}
-	\begin{tcolorbox}[colback=cyan!5!white,colframe=cyan!75!black,title=Example 2: \#Brexit]
-		Labour cannot win the next general election with \textcolor{magenta}{@Keir\_Starmer} \textbf{because} voters \textbf{do}n’t trust him. Starmer \textbf{is} a proven liar \textbf{and} fraud who tried to cheat 17.4m voters out of their \textcolor{orange}{\#Brexit} referendum victory. Starmer \textbf{is} unelectable. \textcolor{orange}{\#LabourDebate} \textcolor{orange}{\#labourhustings}
-		%\textcolor{red}{RT} \textcolor{magenta}{@SaysSheToday}: The $[$Dixie Chicks$]_{c}$ were attacked just for $[$using 1A right$]_{p_1}$ to say they were ashamed of GWB. They $[$didn’t commit treason$]_{c}$ $[$like the \textcolor{orange}{\#47Senators}$]_{p_2}$
-	\end{tcolorbox}
-\end{frame}
-\begin{frame}
-	\begin{tcolorbox}[colback=cyan!5!white,colframe=cyan!75!black,title=Example 3: \#Brexit]
-		\textcolor{orange}{\#SaturdayThought} \textbf{If} \textcolor{orange}{\#PMs} "oven-ready Brexit deal" \textbf{is so} "oven-ready," \textbf{why has} he not got full agreement of the EU \textbf{yet}? \textbf{After} all, \textcolor{magenta}{@Conservatives} keep telling us \textbf{that} \textcolor{orange}{\#Brexit} \textbf{is} over now.\textcolor{orange}{\#JustAsking}
-		%\textcolor{red}{RT} \textcolor{magenta}{@SaysSheToday}: The $[$Dixie Chicks$]_{c}$ were attacked just for $[$using 1A right$]_{p_1}$ to say they were ashamed of GWB. They $[$didn’t commit treason$]_{c}$ $[$like the \textcolor{orange}{\#47Senators}$]_{p_2}$
-	\end{tcolorbox}
-\end{frame}
-\begin{frame}
-	\begin{tcolorbox}[colback=cyan!5!white,colframe=cyan!75!black,title=Example 4: \#Abortion]
-		POV: Stop saying NOBODY \textbf{is} “pro-abortion."  It\textbf{'s} \textcolor{orange}{\#stigmatising}. \textbf{Its} simply inaccurate, Plenty of folk \textbf{are} unapologetically \textcolor{orange}{\#proabortion}; \textbf{because} there\textbf{'s} nothing wrong with \textcolor{orange}{\#Abortion} -it\textbf{`s} a necessary health care procedure \textbf{that} saves lives.
-		%\textcolor{red}{RT} \textcolor{magenta}{@SaysSheToday}: The $[$Dixie Chicks$]_{c}$ were attacked just for $[$using 1A right$]_{p_1}$ to say they were ashamed of GWB. They $[$didn’t commit treason$]_{c}$ $[$like the \textcolor{orange}{\#47Senators}$]_{p_2}$
-	\end{tcolorbox}
-\end{frame}
-
-
 \section{Next}
 \begin{frame}
 	\begin{itemize}
-		\item [1] More controverse topics
-		\item [2] Cleaning of PWords
-		\item [3] PWords and POS-Distribution for Kialo
-		\item [4] Annotation / Quality-Check on Candidate-Subset
+		\item [1] Selection on SCONJ, CCONJ, AUX
+		\item [2] Selection sampling:
+		\begin{itemize}
+			\item [] \textbf{Sample 1}: Dropoff
+			\item [] \textbf{Sample 2}: Root-Tweets with length $<$ 200
+			\item [] \textbf{Sample 3}: Root-Tweets with length $\geq$200
+		\end{itemize}
+		\item [3] Annotation of samples
+		\item [4] Fine-Tuning of argumentive vocabulary
 	\end{itemize}
 \end{frame}