Add text for content-based recommender

content-based.tex

+\begin{figure}[htbp!]
+	\centering
+	\includegraphics[scale=0.5]{Bilder/ContendBasedFlow.jpg}
+	\caption{\textit{Content-Based recommender systems} work via \textit{feature vectors}. These \textit{vectors} are learned or created using a variety of methods to model the \textit{user's preferences}. A suggestion is determined by the similarity between the \textit{feature vector} of the \textit{user} and the \textit{items}.}
+	\label{img:content-based}
+\end{figure}
\ No newline at end of file

recommender.tex

@@ -7,4 +7,11 @@ Each of the \textit{users} in $\mathcal{U}$ gives \textit{ratings} from a set $\
 
 In the following, the two main approaches of \textit{collaborative-filtering} and \textit{content-based} \textit{recommender systems} will be discussed. In addition, it is explained how \textit{matrix factorization} can be integrated into the two ways of thinking.
 
+\subsection{Content-Based}
+\textit{Content-based} \textit{recommender systems} work directly with \textit{feature vectors}. Such a \textit{feature vector} can, for example, represent a \textit{user profile}. In this case, this \textit{profile} contains information about the \textit{user's preferences}, such as \textit{genres}, \textit{authors}, \textit{etc}.  This is done by trying to create a \textit{model} of the \textit{user}, which best represents his preferences. The different \textit{learning algorithms} from the field of \textit{machine learning} are used to learn or create the \textit{models}. The most prominent \textit{algorithms} are: \textit{tf-idf}, \textit{bayesian learning}, \textit{Rocchio's algorithm} and \textit{neural networks} \citep{Lops11, Ferrari19}. Altogether the built and learned \textit{feature vectors} are compared with each other. Based on their closeness, similar \textit{features} can be used to generate \textit{missing ratings}.
+
+\input{content-based}
+
 \subsection{Collaborative-Filtering}
+
+\subsection{Matrix-Factorization}
\ No newline at end of file

references.bib

@@ -28,7 +28,8 @@
   bibsource = {dblp computer science bibliography, https://dblp.org}
 }
 @inproceedings{DeKa11,
-author = {Desrosiers, Christian and Karypis, George},
+author = {Christian Desrosiers and
+                George Karypis},
 year = {2011},
 month = {01},
 pages = {107--144},
@@ -38,3 +39,26 @@ editor = {P.B. Kantor and F. Ricci and L. Rokach and B. Shapira},
 publisher={Springer},
 doi = {10.1007/978-0-387-85820-3_4}
 }
+@inproceedings{Lops11,
+author = {Pasquale Lops and 
+			   Marco de Gemmis and
+			   Giovanni Semeraro},
+year = {2011},
+month = {01},
+pages = {74--105},
+title = {Content-based Recommender Systems: State of the Art and Trends},
+booktitle = {Recommender Systems Handbook},
+editor = {P.B. Kantor and F. Ricci and L. Rokach and B. Shapira},
+publisher={Springer},
+doi = {10.1007/978-0-387-85820-3_4}
+}
+
+@inproceedings{Ferrari19,
+author = {Maurizio Ferrari Dacrema and Paolo Cremonesi and Dietmar Jannach},
+year = {2019},
+month = {07},
+pages = {},
+title = {Are We Really Making Much Progress? A Worrying Analysis of Recent Neural Recommendation Approaches},
+isbn = {978-1-4503-6243-6},
+doi = {10.1145/3298689.3347058}
+}
\ No newline at end of file