% THIS IS SIGPROC-SP.TEX - VERSION 3.1
% WORKS WITH V3.2SP OF ACM_PROC_ARTICLE-SP.CLS
% APRIL 2009
%
% It is an example file showing how to use the 'acm_proc_article-sp.cls' V3.2SP
% LaTeX2e document class file for Conference Proceedings submissions.
% ----------------------------------------------------------------------------------------------------------------
% This .tex file (and associated .cls V3.2SP) *DOES NOT* produce:
%       1) The Permission Statement
%       2) The Conference (location) Info information
%       3) The Copyright Line with ACM data
%       4) Page numbering
% ---------------------------------------------------------------------------------------------------------------
% It is an example which *does* use the .bib file (from which the .bbl file
% is produced).
% REMEMBER HOWEVER: After having produced the .bbl file,
% and prior to final submission,
% you need to 'insert'  your .bbl file into your source .tex file so as to provide
% ONE 'self-contained' source file.
%
% Questions regarding SIGS should be sent to
% Adrienne Griscti ---> griscti@acm.org
%
% Questions/suggestions regarding the guidelines, .tex and .cls files, etc. to
% Gerald Murray ---> murray@hq.acm.org
%
% For tracking purposes - this is V3.1SP - APRIL 2009

\documentclass{acm_proc_article-sp}
\usepackage{graphicx}
\usepackage{subcaption}
\usepackage{booktabs}
\usepackage{color, colortbl}
\usepackage[utf8]{inputenc}
\usepackage{multirow}

\usepackage[usenames,dvipsnames]{xcolor}

\begin{document}

\title{Items that Trigger Clicks upon Recommendation}

% You need the command \numberofauthors to handle the 'placement
% and alignment' of the authors beneath the title.
%
% For aesthetic reasons, we recommend 'three authors at a time'
% i.e. three 'name/affiliation blocks' be placed beneath the title.
%
% NOTE: You are NOT restricted in how many 'rows' of
% name/affiliations may appear. We just ask that you restrict
% the number of 'columns' to three.
%
% Because of the available 'opening page real-estate'
% we ask you to refrain from putting more than six authors
% (two rows with three columns) beneath the article title.
% More than six makes the first-page appear very cluttered indeed.
%
% Use the \alignauthor commands to handle the names
% and affiliations for an 'aesthetic maximum' of six authors.
% Add names, affiliations, addresses for
% the seventh etc. author(s) as the argument for the
% \additionalauthors command.
% These 'additional authors' will be output/set for you
% without further effort on your part as the last section in
% the body of your article BEFORE References or any Appendices.

% \numberofauthors{8} %  in this sample file, there are a *total*
% of EIGHT authors. SIX appear on the 'first-page' (for formatting
% reasons) and the remaining two appear in the \additionalauthors section.
%
\author{
% You can go ahead and credit any number of authors here,
% e.g. one 'row of three' or two rows (consisting of one row of three
% and a second row of one, two or three).
%
% The command \alignauthor (no curly braces needed) should
% precede each author name, affiliation/snail-mail address and
% e-mail address. Additionally, tag each line of
% affiliation/address with \affaddr, and tag the
% e-mail address with \email.
%
% 1st. author
% \alignauthor
% Ben Trovato\titlenote{Dr.~Trovato insisted his name be first.}\\
%        \affaddr{Institute for Clarity in Documentation}\\
%        \affaddr{1932 Wallamaloo Lane}\\
%        \affaddr{Wallamaloo, New Zealand}\\
%        \email{trovato@corporation.com}
% % 2nd. author
% \alignauthor
% G.K.M. Tobin\titlenote{The secretary disavows
% any knowledge of this author's actions.}\\
%        \affaddr{Institute for Clarity in Documentation}\\
%        \affaddr{P.O. Box 1212}\\
%        \affaddr{Dublin, Ohio 43017-6221}\\
%        \email{webmaster@marysville-ohio.com}
% % 3rd. author
% \alignauthor Lars Th{\o}rv{\a}ld\titlenote{This author is the
% one who did all the really hard work.}\\
%        \affaddr{The Th{\o}rv{\a}ld Group}\\
%        \affaddr{1 Th{\o}rv{\a}ld Circle}\\
%        \affaddr{Hekla, Iceland}\\
%        \email{larst@affiliation.org}
% \and  % use '\and' if you need 'another row' of author names
% % 4th. author
% \alignauthor Lawrence P. Leipuner\\
%        \affaddr{Brookhaven Laboratories}\\
%        \affaddr{Brookhaven National Lab}\\
%        \affaddr{P.O. Box 5000}\\
%        \email{lleipuner@researchlabs.org}
% % 5th. author
% \alignauthor Sean Fogarty\\
%        \affaddr{NASA Ames Research Center}\\
%        \affaddr{Moffett Field}\\
%        \affaddr{California 94035}\\
%        \email{fogartys@amesres.org}
% % 6th. author
% \alignauthor Charles Palmer\\
%        \affaddr{Palmer Research Laboratories}\\
%        \affaddr{8600 Datapoint Drive}\\
%        \affaddr{San Antonio, Texas 78229}\\
%        \email{cpalmer@prl.com}
}



% There's nothing stopping you putting the seventh, eighth, etc.
% author on the opening page (as the 'third row') but we ask,
% for aesthetic reasons that you place these 'additional authors'
% in the \additional authors block, viz.


% \additionalauthors{Additional authors: John Smith (The Th{\o}rv{\a}ld Group,
% email: {\texttt{jsmith@affiliation.org}}) and Julius P.~Kumquat
% (The Kumquat Consortium, email: {\texttt{jpkumquat@consortium.net}}).}
% \date{30 July 1999}


% Just remember to make sure that the TOTAL number of authors
% is the number that will appear on the first page PLUS the
% number that will appear in the \additionalauthors section.

\maketitle

%opening
\title{Items that trigger clicks on recommendation}
\author{}


\maketitle

\begin{abstract}
In a setting where  recommendations are provided to users when they are viewing a particular item, what factors contribute to the user clicking on some items and not on others?  We examine what triggers users to click on those recommended items in relation to the items the user is currently viewing. More specifically, we examine the items from which clicks happen and what type of items get clicked. Are some items more likely to cause the user to click  on recommendations and are some recommendations more likely to be clicked?  We attempt to explain the factors that trigger clicks on recommendations from different angles. 

\end{abstract}

\section{Introduction}
In a recommendation setting where recommendations are provided to a user on the item that the user is reading,   one might wonder whether some items trigger  clicks  more than others, and if they do, what could  possibly explain that?  In a study on the similar Plista dataset \cite{said2013month}, it was found that traditional news portals providing news and opinions on politics and current events are more likely to generate clicks on recommendation than special interest portals such as sports,  gardening, and automechanic forums. In this study, we focus on one traditional news portal, tagespiegel and examine it to find out factors that trigger recommendations on clicks or lack thereof. %wether some categories are more likely to recieve clicks on recommendations. We also even go further and look at what type of items are more likely to trigger more clicks than others.


In this study we examine this factors that might trigger clicks on recommendations  from several angles. One angle  is from  the categories of items the user is currently reading. More specifically, are some categories of items  more likely to  cause the user to click on recommendations? How are the categories of the base item and the categories of the recommendation items related. Are some categories  more likely to trigger clicks on some categories? For example, is political category more likely to trigger clicks on political categories, or another category such as local category? 

We also go down to the item level and look at what items are more likely to trigger clicks, and what recommendation items are more likely to be clicked. To accomplish this task, we focus on items of categories that trigger more clicks. We identify items that triggered more clicks and items that caused less clicks. We also examine the relationship of the items that triggered clicks and the recommendations that are clicked and not clicked. 

Finally, we zoomed in on some items that show high variance score and look in to the recommendation to find out what type of items got clicked and what other itesm got ignored. We believe this provides us with a lower-level understanding of the factors that trigger clicks or the lack thereof. 

We also examine  the relationship of the contenet of the base items and the items that are clicked to glean any relationship. For this, we employ contenet similarity measures between the base item and those items that are clicked from the base item. %A third angle is to look at the relationship between the  content of the base item and the items that are clicked from it. %This is interesting because sometimes it is not clear whether there i a direct relationship between the content similarity and behavioral factors. 
we can also look at  whether users actually clicked on those items which have some geographical relevance in the sense that the items are about the geographical region that they come from too.


The insights from examining which categories and items generate trigger clicks is important because 1) we understand what makes users click on an item 2) to target those items that generate clicks and to decrease recommendations on those categories that do not trigger recommendations. 

\section{Dataset, Results and Analysis}

We ussed Plista dataset of of one month from Plsia. Plista is a company that provides a recommendation platform where recommendation providers are inked with online publishers in need of recommendation sertvice. From a datset collected over a month,  we extracted the number of times items have been shown and the number of times that items have been clicked from them. It is not easy to get the exact number of times recommendations have been shown on an item. We assume that the number of times an item has been viewed as the number of times recommendations were shown. Although each time an item is viewed, more than one item (usually 5 items) are shown to the user as recommendations, we just count the number of clicks that have happened from those items regardless of which items are clicked. 


Figure \ref{fig:view_click} shows the plot of views and clicks. Because of the big difference between views and clicks, the view and click plots appear to be the same, except at the beginning. However, when we focus on the first 100 items that have been viewed the most, we obtaine the view plot in Figure \ref{fig:view100} and the corresponding clicks that the views triggered produce the click plot in Figure \ref{fig:click100}. The plots were generated by first sorting the scores accroding to views. The rough click plot shows that some items are more likely to trigger clicks on recommendations than others.  
 \begin{figure} [t]
\centering
\includegraphics[scale=0.5]{img/tage_view_click.pdf}

\label{fig:view_click}
\caption{Plots of views and clicks on Tagesspiegel and Ksta.}
\end{figure}



 \begin{figure} [t]
\centering
\includegraphics[scale=0.5]{img/tage_view100.pdf}

\label{fig:view100}
\caption{Plot of the most viewed 100 items}
\end{figure}


 \begin{figure} [t]
\centering
\includegraphics[scale=0.5]{img/tage_click100.pdf}

\label{fig:click100}
\caption{Plot of the clicks triggered from the 100 most viewed items}
\end{figure}

\begin{table}
\caption{A table showing the views, clicks, and ctr of the 12 categories of Tagesspiegel that we considred. }
  \begin{tabular}{|l|l|l|l|l|}
\hline
           category  &  Views & Clicks & CTR (\%)\\
           \hline
      auto&2875&3246&14&0.43\\
berlin&2875&88473&2031&2.3\\
kultur&2875&12218&294&2.41\\
medien&2875&19565&530&2.71\\
meinung&2875&12290&144&1.17\\
politik&2875&52658&1906&3.62\\
sport&2875&22489&479&2.13\\
weltspiegel&2875&16395&435&2.65\\
wirtschaft&2875&17446&476&2.73\\
wissen&2875&5861&71&1.21\\


   \hline
  \end{tabular}
  \label{ctr}
\end{table}




To start to explain the observation that some items trigger more clicks that others, we aggeragated the items (both views and clicks) by 12 categories. These are the main categories that are shown in the tagespiegel website. 
Table \ref{ctr} presents the views. clicks and CTR scores for 12 ctegories of items we considred. The table is sorted by CTR. We observe that political items trigger clicks more than any other category. After political items, the categories of opinion and the the Berlin local categories trigger more clicks on recommendations. Special categories such as culture and and automechanic trigger the least clicks on recommendations. This is consistent with previous findings that reported special interest portals enjoyed less clicks than tradiional and mainstream news and opinion portals. 

\subsection{Clicked and Rejected Items}
We plan to extract a sample of base items with  recommended and clicked items and separate them into clicked and rejected recommendations. We then compare the contenet of the clicked items with the contenet of the base item. We also do the same with the rejected items and see if there is any similarities/differences bertween these two categories.  The sepration of clicked and rejected items and comparing them to the base item is similar to the sepration of recommended moviews into viwed and ignored in \cite{nguyen2014exploring}. 

On the same dataset, there has been a study on the transition probababilities of users on the categories \cite{esiyok2014users}. The finding was that there is a relationship between what the user is reading on and what the user  reads next. They  report that the category local and sports enjoyed the most loyal readers, that is that a user reading on local items will more likely keep reading items of the same categoy. This study was on genral reading. In this study 1) we repeat the same study on a dataset from a different time and 2) we analyze results in terms of similarity of content with the base items. 


Question for myself: Is it maybe possible to compute the category CTR's? Like a hitmap of the CTRs where the recommendations are subsidvided to their categories and a CTR is computed? I think so. We can also go durther and look at the contenet similarities. Further, we can look at what type of items trigger more clicks by selecting some items which generated more clicks and analyzing them. 



\begin{table*}
\caption{A heatmap of the the categories recommendation clicks. }
  \begin{tabular}{|l|l|l|l|l|l|l|l|l|l|l|l|l|}
\hline

berlin&politik&wirtschaft&sport&kultur&weltspiegel&meinung&medien&wissen&auto\\
berlin&2.62&2.08&1.14&2.08&1.69&2.27&1.61&4.32&1.22&0.4\\
politik&3.89&3.16&0.94&3.2&3.75&4.59&3.04&5.88&2.99&0.21\\
wirtschaft&2.53&2.89&0.9&1.74&1.52&1.95&3.48&8.43&2.83&0\\
sport&2.37&2.06&1.47&1.95&2.48&1.68&1.06&4.61&0.29&0.64\\
kultur&2.15&2.84&0.71&1.98&1.55&3.16&1.62&4.77&0.62&0\\
weltspiegel&1.86&3.32&2.15&1.14&6.2&2.22&4.39&4.3&2.22&0\\
meinung&1.66&1.14&0&1.05&1.72&0.64&1.46&0.92&0&1.52\\
medien&1.97&4.32&2.33&1.3&4.46&4.03&1.93&2.42&0.86&0.95\\
wissen&1.3&1.15&1.82&0&0&2.43&2.3&1.13&0&0\\
auto&0.22&0.92&0&0.52&0&0&0&1.22&2&0\\


 \hline
  \end{tabular}
  \label{heatmap}
\end{table*}


The hitmap in Table \ref{heatmap} shows the CTR heatmap of recommendation clicks. For example  if we look at the politk row, we see that the CTR from politics to politics is the highest than from politics to any other category.  We also observe that the CTR from local category Berlin to politics is higher than from the local category Berlin to any other category including to itself. A little surprising result is the high CTR from media to politics. 

The way we extracted our recommendations and clciks is a little uncertan. In the Plista setting, when click results are reported to users, they are not known whose recommendations are being clicked. So while we know our recommendation, we do not know for sure how much of the click notifications that we recieve belong to our recommendations. To extract our clciks, we introduced a time frame of 5 minutes. That is if the click notification happens in with in a range of time, in our case 5 minutes, we consider the clcik is on our recommendations. We consider the click information is a bit inflated for users might not stay for more than 5 minutes. While the actual CTR might be a bit inflated as a result of the inflated number of clicks, we consider the relative scores as indicative of the true difference.

To find out therelationship between base item recommendation pairs that resulted in high CTR scoores, we selected some item-recommendations pairs. To avoid selecting item-recommendation pairs that have very low views and clicks which is usually the type of combination that results in high CTR scores, we first sort our data according to views, and according to clicks. Using  cutt off values, we repeat the intersection until we find the items that have both the highest view and the hight clicks. Using this approach we selected 12 item-recommendation pairs and out of them we selected the 5 pairs that have the highest score. These pairs are presented in Table \ref{}


\begin{table}
\caption{Items and their categories that triggered the highest clicks. }
  \begin{tabular}{|l|l|l|l|l|}
\hline

 138084944&berlin&4528&15&0.33\\
138260114&berlin&364&67&18.41\\
138276052&berlin&352&128&36.36\\
138288428&berlin&295&21&7.12\\
138331188&politik&516&25&4.84\\
138353486&politik&314&15&4.78\\
138657855&berlin&295&27&9.15\\
139760872&politik&387&30&7.75\\
140069310&berlin&307&55&17.92\\
140069310&politik&552&37&6.7\\
140290935&berlin&306&112&36.6\\
140451940&berlin&435&35&8.05\\



 \hline
  \end{tabular}
  \label{top-base}
\end{table}





\begin{table}
\caption{Items and their categories that triggered the lowest clicks. }
   \begin{tabular}{|l|l|l|l|l|}
\hline

110758362&politik&30&0&0\\
113192171&politik&18&0&0\\
115276998&politik&70&0&0\\
118343158&politik&15&0&0\\
121749581&politik&34&0&0\\
45287388&politik&16&0&0\\
45322502&politik&16&0&0\\
62615560&politik&22&0&0\\
63451502&politik&17&0&0\\
68227587&politik&21&0&0\\
88961035&politik&18&0&0\\
95418946&politik&18&0&0\\
96260589&politik&44&0&0\\



 \hline
  \end{tabular}
  \label{bot-base}
\end{table}



\begin{table}
\caption{Items Recommendations and their categories that triggered the highest clicks. }
  \begin{tabular}{|l|l|l|l|l|l|l|}
\hline

base&reco&view.x&click.x&base\_cat.x&reco\_cat.x&ctr.x\\
138614685&138507870&70&23&berlin&berlin&32.86\\
138614685&138657855&69&22&politik&berlin&31.88\\
138622180&138657855&86&19&politik&berlin&22.09\\
138657855&138507870&84&6&berlin&politik&7.14\\
139322452&139370303&62&53&politik&weltspiegel&85.48\\
139385769&139370303&89&14&politik&berlin&15.73\\
139881545&139883694&80&28&politik&medien&35\\
140032342&140069310&91&6&politik&berlin&6.59\\
140141990&140069310&91&7&politik&weltspiegel&7.69\\
140290935&140451940&144&43&medien&politik&29.86\\
140410389&140451940&88&8&medien&berlin&9.09\\
140454828&140451940&69&9&medien&kultur&13.04\\
140462049&140451940&126&11&medien&medien&8.73\\


 \hline
  \end{tabular}
  \label{top-base-reco}
\end{table}





\begin{table}
\caption{Items recommendations and their categories that triggered the lowest clicks. }
   \begin{tabular}{|l|l|l|l|l|l|l|}
\hline

base&reco&view.x&click.x&base\_cat.x&reco\_cat.x&ctr.x\\
107201359&138507870&9&0&berlin&berlin&0\\
45276650&140069310&5&0&politik&berlin&0\\
62615560&139622331&9&0&politik&kultur&0\\
62615560&139648400&8&0&kultur&kultur&0\\
62615560&139667911&5&0&berlin&kultur&0\\
63103846&139648400&8&0&kultur&kultur&0\\
63104505&139648400&5&0&kultur&kultur&0\\
65982081&140451940&10&0&medien&politik&0\\
89607701&140069310&6&0&politik&sport&0\\
96260589&138288428&6&0&berlin&kultur&0\\




 \hline
  \end{tabular}
  \label{bot-base_reco}
\end{table}






\section{discussion and conclusion}

An idea, maybe show the variance of the categories in terms of their CTR? 

\bibliographystyle{abbrv}
\bibliography{ref} 

\end{document}