annotate musicweb.tex @ 32:871ecf98047f

similarity by mood section

\documentclass{llncs}
\usepackage{graphicx}

\usepackage{amsmath,cite}
\usepackage{pifont}
\usepackage{listings}
\usepackage{courier}
\usepackage{adjustbox}
\usepackage{url}
\usepackage{subcaption}
\captionsetup{compatibility=false}
\usepackage[ngerman,english]{babel}
\usepackage[utf8]{inputenc}
\newcommand{\cmark}{\fontsize{14}{14}\textbullet\selectfont}
\usepackage[usenames,dvipsnames]{color}

\lstdefinelanguage{sparql} {
	morekeywords={SELECT, WHERE, a, COUNT, GROUP, ORDER, BY, HAVING, as, DISTINCT, OPTIONAL},
	sensitive=true,
	morecomment=[l][\color{ForestGreen}\bfseries\selectfont]{\#\ },
	moredelim=[s][\color{ForestGreen}\bfseries\selectfont]{?}{\ }, %variable
	moredelim=[s][\color{NavyBlue}\bfseries\selectfont]{@}{\ }, %prefix
	moredelim=[s][\color{OrangeRed}\bfseries\selectfont]{<}{>}, %red URIs
	morestring=[b][\color{ForestGreen}]\", %green strings
	morestring=[b]",
}

\lstdefinestyle{sparql}{
	language=sparql,
	basicstyle=\footnotesize\ttfamily\bfseries,
	% basicstyle=\ttfamily,
	keywordstyle=\color{blue}\bfseries,
	identifierstyle=,
	commentstyle=\color{ForestGreen}\bfseries,
	stringstyle=\color{BlueGreen}\ttfamily,
	showstringspaces=false,
	emph={context},emphstyle=\color{BrickRed}\bfseries,
	frame = lines,
	%aboveskip = 15pt,
	%framexbottommargin = 5pt,
	%framextopmargin = 5pt,
	aboveskip = 10pt,
	framexbottommargin = 2pt,
	framextopmargin = 2pt,
	captionpos=b,
	escapechar=~,
	breaklines=true,
	breakatwhitespace=true,
	breakindent=20pt,
	xleftmargin=5pt,
	xrightmargin=5pt,
	basewidth={0.55em,0.45em},
	%basewidth={0.50em,0.6em},
	fontadjust=true,
	% lineskip={-1.5pt},
	% columns=[c]spaceflexible, %make the long artist URI fit
	%float = h!,
}

\renewcommand{\lstlistingname}{{\bf Listing}}


\lstdefinelanguage{ttl} {
	morekeywords={a},
	sensitive=true,
	% morecomment=[l][\color{ForestGreen}\bfseries\fontsize{10}{2}\selectfont]{\#\ },
	% moredelim=[s][\color{ForestGreen}\bfseries\fontsize{10}{2}\selectfont]{\#\ }{\ },
	% moredelim=[s][\color{NavyBlue}\bfseries\fontsize{10}{2}\selectfont]{@}{\ }, %prefix
	% moredelim=[s][\color{OrangeRed}\bfseries\fontsize{10}{2}\selectfont]{<}{>}, %red URIs
	morecomment=[l][\color{ForestGreen}\ttfamily\bfseries\selectfont]{\#\ },
	moredelim=[s][\color{NavyBlue}\ttfamily\bfseries\selectfont]{@}{\ }, %prefix
	moredelim=[s][\color{OrangeRed}\ttfamily\bfseries\selectfont]{<}{>}, %red URIs
	morestring=[b][\color{ForestGreen}]\", %green strings
	morestring=[b]",
}

\lstdefinestyle{ttl}{
	language=ttl,
	basicstyle=\footnotesize\ttfamily\bfseries,
	keywordstyle=\color{blue}\bfseries,
	identifierstyle=,
	commentstyle=\color{ForestGreen}\bfseries,
	stringstyle=\color{BlueGreen}\bfseries,
	showstringspaces=false,
	emph={context},emphstyle=\color{BrickRed}\bfseries,
	frame = lines,
	framexbottommargin = 5pt,
	framextopmargin = 5pt,
	captionpos=b,
	escapechar=~,
	breaklines=true,
	breakatwhitespace=true,
	breakindent=20pt,
	aboveskip = 15pt,
	xleftmargin=5pt,
	xrightmargin=5pt,
	basewidth={0.55em,0.45em},
	% basewidth={0.50em,0.6em},
	fontadjust=true,
	lineskip={-1.5pt},
	% columns=[c]spaceflexible, %make the long artist URI fit
	% float = h!,
}

\lstdefinelanguage{json} {
	sensitive=true,
	%morecomment=[l]{@},
	moredelim=[s][\color{ForestGreen}]{?}{\ }, %green variables
	moredelim=[s][\color{OrangeRed}\fontsize{7}{2}\selectfont]{<}{>}, %red URIs
	morestring=[b][\color{Gray}]\",
	morestring=[b]",
}

\lstdefinestyle{json}{
	language=json,
	keywords={type,context},
	basicstyle=\fontsize{7}{8}\bfseries\ttfamily,
	keywordstyle=\color{blue}\bfseries,
	identifierstyle=,
	commentstyle=\color{Gray}\bfseries,
	stringstyle=\color{OliveGreen}\ttfamily,
	showstringspaces=false,
	emph={context},emphstyle=\color{BrickRed}\bfseries,
	frame = lines,
	framexbottommargin = 5pt,
	framextopmargin = 5pt,
	tabsize=4,
	captionpos=b,
	escapechar=~,
	breaklines=false,
	xleftmargin=5pt,
	xrightmargin=5pt,
	basewidth={0.50em,0.45em},
	%basewidth={0.50em,0.6em},
	fontadjust=true,
	columns=[c]spaceflexible, %make the long artist URI fit
	float = ht,
}

\renewcommand{\labelitemi}{$\bullet$}

\begin{document}

\mainmatter

\title{MusicWeb: an open linked semantic platform for music metadata}

\author{Mariano Mora-Mcginity \and Alo Allik \and Gy\"orgy Fazekas \and Mark Sandler }
%

\institute{Queen Mary University of London, \\
\email{\{m.mora-mcginity, a.allik, g.fazekas, mark.sandler\}@qmul.ac.uk}}

\maketitle

\begin{abstract}

% MusicWeb is a web site that provides users a browsing, searching and linking platform of music artist and group information by integrating open linked semantic metadata from various Semantic Web, music recommendation and social media data sources, including DBpedia.org, sameas.org, MusicBrainz, the Music Ontology, Last.FM, Youtube, and Echonest. The front portal includes suggested links to selected artists and a search functionality from where users can navigate to individual artists pages. Each artist page contains a biography, links to online audio and a video player with a side menu displaying a selection of Youtube videos. Further it provides lists of YAGO categories linking each artist to other artists by various commonalities such as style, geographical location, instrumentation, record label as well as more obscure categories, for example, artists who have received the same award, have shared the same fate, or belonged to the same organisation or religion. The artist connections are further enhanced by thematic analysis of journal articles and blog posts as well as content-based music information retrieval similarity measures.

This paper presents MusicWeb, a novel platform for linking music artists within a web-based application for discovering connections between them. MusicWeb provides a browsing experience using connections that are either extra-musical or tangential to music, such as the artists' political affiliation or social influence, or intra-musical, such as the artists' main instrument or most favoured musical key. The platform integrates open linked semantic metadata from various Semantic Web, music recommendation and social media data sources including DBpedia.org, sameas.org, MusicBrainz, the Music Ontology, Last.FM and Youtube as well as content-derived information. The front portal includes suggested links to selected artists and a search functionality from where users can navigate to individual artists pages. Each artist page contains a biography and links to online audio and a video resources. Connections are made using YAGO categories linking artist by various commonalities such as style, geographical location, instrumentation, record label as well as more obscure categories, for instance, artists who have received the same award, have shared the same fate, or belonged to the same organisation or religion. These connections are further enhanced by thematic analysis of journal articles and blog posts as well as content-based similarity measures focussing on high level musical categories.

\keywords{Semantic Web, Linked Open Data, music metadata, semantic audio analysis, music information retrieval }
\end{abstract}

\section{Introduction}\label{sec:introduction}
In recent years we have witnessed an explosion of information, a consequence of millions of users producing and consuming web resources. Researchers and industry have recognised the potential of this data, and have endeavoured to develop methods to handle such a vast amount of information: to understand and manage it, to transform into knowledge. Multimedia content providers have devoted a lot of energy to analysing consumer preference, in an effort to offer customised user experiences. Music stream services, for instance, carry out extensive analysis trying to identify patterns in user's listening habits, and researchers are striving to refine multimedia recommendation algorithms. There are two main approaches to music recommendation\cite{Song2012}: the first is known as \emph{collaborative filtering}\cite{Su2009}, which recommends music items based on the choices of similar users.  The second model is based on audio content analysis, or \emph{music information retrieval}. The task here is to extract low to high-level audio features such as tempo, key, metric structure, melodic and harmonic sequences, instrument recognition and song segmentation, which are then used to measure music similarity\cite{Aucoutourier2002}, to carry out genre classification or to identify the mood of the song\cite{Kim2010}. Music discovery websites such as Last.fm\footnote{http://www.last.fm}, Allmusic\footnote{http://www.allmusic.com} or Pandora\footnote{http://www.pandora.com} have successfully developed hybrid systems which combine both approaches.
There are, however, limitations in both approaches to music recommendation. Most users participating in (or whose data is used to analyse) collaborative filtering listen to a very small percentage of the music available, the so called ``short-tail'', whereas the much larger ``long-tail'' remains mainly unknown\cite{Celma2010}. These systems will show a bias towards music that is already consumed by many listeners. Suggesting already popular music will increase the likelihood of it being recommended to new users, thus creating a \emph{rich-club phenomenon}\cite{Zhou2004} or what is known as \emph{cumulative advantage}. Also, content analysis of audio features is mainly applied to songs: systems can recommend similar tracks, but generally know nothing about similar artists. Many music listeners follow artists because of their style and would be interested in music from similar artists. It is very hard to pinpoint what exactly makes two artists ``similar'': very often notions of similarity are based on social and cultural issues, rather than a precise definition of style.
 To many music lovers discovering new music, or music they weren't aware of, is an integral part of enjoying a musical experience, and appreciate expanding their musical taste. Lee and Price\cite{Lee2015} identify seven different \emph{personas} which tipify music service consumption. Two such personas, for instance, the ``active curator'' and the ``music epicurean'' characteristically spend a long time hunting for new music, whereas the ``wanderer'' enjoys the discovery process itself, trying out new things with an open mind.  Automatic musical discovery is a very challenging problem\cite{Jennings2007}. There are many different ways in which people are attracted to new artists: word of mouth, their network of friends, music magazines or blogs, songs heard in a movie or a T.V. commercial, they might be interested in a musician who has played with another artist or been mentioned as an influence,  etc. The route from listening to one artist and discovering a new one would sometimes seem very disconcerting were it to be drawn on paper. A listener is not so much following a map as exploring new territory, with many possible forks and shortcuts. Music discovery systems generally disregard this kind of information, often because it is very nuanced and difficult to parse and interpret. All these sources of information are in fact music metadata, data about the music data itself. Pachet identifies three types of musical metadata \cite{Pachet2005}:
\begin{enumerate}
  \item Editorial metadata: information that is provided manually by authoritative experts. There is a wide range of potential producers of this kind of data, from record labels to collaborative schemes, as well as different kinds of data, from which musician played in which song to tour info, to artists' biography.
  \item Cultural metadata: information which is produced by the environment or culture. This is data that is not explicitly entered into some information system, but rather is contained, and must be extracted from, other information sources, such as user trends, google searches, articles and magazines, word associations in blogs, etc.
  \item Acoustic metadata: data extracted from audio files using music information retrieval methods.
\end{enumerate}
MusicWeb is an application which offers the user the possibility of exploring editorial, cultural and musical links between artists. It gathers, extracts and manages musical metadata from many different sources and connects them in informative ways. This paper deals with the different ways in which musicweb collects these resources and shapes them into high-level information. We will first review various knowledege-based web resources available to musicweb. We will then introduce the application itself and detail the architecture to analyse and extract data. Before the final conclusions and discussion of future work we will analyse the experience of interfacing with the application and how users can explore and discover new musical paths.




\section{Background}\label{sec:background}
\begin{itemize}
\item related work
  \begin{itemize}
  \item http://musikipedia.org/ MUSIKIPEDIA, some paper by the guy who made it, Mohamed Sordo
    \item Pachet's thing on metadata?
  \item Kurt's thesis on the similarity ontology
  \item Phuong Nguyen, Paolo Tomeo, Tommaso Di Noia and Eugenio Di Sciascio: Content-based recommendations via DBpedia and Freebase
    \item music recommendation dbpedia
    \end{itemize}
\item  very brief intro to the role of music related data sources on the web and what they are
\end{itemize}

\section{MusicWeb architecture}

MusicWeb provides a browsing experience using connections that are either extra-musical or tangential to music, such as the artists' political affiliation or social influence, or intra-musical, such as the artists' main instrument or most favoured musical keys. It does this by pulling data from several different web knowledge content resources and presenting them for the user to navigate in a faceted manner\cite{Marchioni2006}. The listener can begin his journey by choosing or searching for an artist (fig. \ref{fig:front_page}). The application offers youtube videos, audio streams, photographs and album covers, as well as the artist's biography (fig. \ref{fig:ella_page}) The page also includes many box widgets with links to artists who are related to the current artist in different, and sometimes unexpected and surprising ways\ref{fig:ella_links}). The user can then click on any of these artists and the search commences again, exploring a web of artists further and further.



%\begin{figure*}
%	\centering
	%%     \begin{minipage}[b]{.48\textwidth}
	%%   \includegraphics[height=8cm]{graphics/front_page.png}
	%%   \caption{Front page}
	%%   \label{fig:front_page}
	%%     \end{minipage}
	%%     \hfill
	%% \begin{minipage}[b]{.48\textwidth}
	%%   \includegraphics[ width=7cm, height=8cm]{graphics/ella_page.png}
	%%   \caption{Ella}
	%%   \label{fig:ella_page}
	%% \end{minipage}
	%% \end{figure}

	%% \begin{subfigure}[t]{0.45\textwidth}
        %%   \centering
	%% 	\hspace{-1.5em}\includegraphics[height=6cm]{graphics/front_page.png}
	%% 	\caption{Front page}
	%% 	\label{fig:front_page}
	%% \end{subfigure}
	%% \hspace{0.4cm}
	%% \begin{subfigure}[t]{0.45\textwidth}
        %%   \centering
	%% 	\hspace{1.5em}\includegraphics[height=6cm]{graphics/ella_page.png}
	%% 	\caption{Ella}
	%% 	\label{fig:ella_page}
	%% \end{subfigure}

	%% \vspace{1.5cm}
	%% \begin{subfigure}{\textwidth}
	%% 	\hspace{0.5em}\includegraphics[width=\textwidth]{graphics/ella_links.png}
	%% 	\caption{Discovered artists}
	%% \end{subfigure}
	%% \caption{MusicWeb interface}
	%% \label{fig:ella_links}
%\end{figure*}                   

	\begin{figure}[!ht]
          \centering
		\hspace{-1.5em}\includegraphics[width=\textwidth, height=6cm]{graphics/front_page.png}
		\caption{Front page}
		\label{fig:front_page}
	\end{figure}
	\hspace{0.4cm}
	\begin{figure}[!ht]
          \centering
		\includegraphics[width=\textwidth, height=6cm]{graphics/ella_page.png}
		\caption{Ella}
		\label{fig:ella_page}
	\end{figure}

	
	\begin{figure}
		\hspace{0.5em}\includegraphics[width=\textwidth, height=6cm]{graphics/ella_links.png}
		\caption{Discovered artists}
	\label{fig:ella_links}
	\end{figure}
 
MusicWeb was originally conceived as a platform for collating metadata about music artists using already available online linked data resources. The core functionality of the platform relies on available SPARQL endpoints sa well as various commercial and community-run APIs. More recently, novel services complement the platform to provide alternative ways to forge connections using natural language processing and machine learning methods. %The front portal includes suggested links to selected artists and a search functionality from where users can navigate to individual artists pages. Each artist page contains a biography, a playlist of online audio and a selection of Youtube videos. Further it provides lists of categories linking each artist to other similar artists by various commonalities such as style, geographical location, instrumentation, record label as well as more obscure categories, for example, artists who have received the same award, have shared the same fate, or belonged to the same organisation or religion. The artist connections are further enhanced by thematic analysis of journal articles and blog posts, content-based music information retrieval similarity metrics and proximity measures in a 2-dimensional mood space.

The MusicWeb API uses a number of LOD resources and Semantic Web ontologies to process and aggregate information about artists: 

\begin{itemize}
	
	\item[] \textbf{Musicbrainz}\footnote{\url{http://musicbrainz.org}} is an online, open, crowd-sourced music encyclopedia, that provides reliable and unambiguous identifiers for entities in music publishing metadata, including artists, releases, recordings, performances, etc. 
	
	\item[] \textbf{DBPedia}\footnote{\url{http://dbpedia.org}} is a crowd-sourced community effort to extract structured information from Wikipedia and make it available on the Web. 
	
	\item[] \textbf{Sameas.org}\footnote{\url{http://sameas.org}} manages URI co-references on Web of Data.
	
	\item[] \textbf{Youtube} API is used to query associated video content for the artist panel.
	
	\item[] \textbf{Echonest}\footnote{\url{http://the.echonest.com}} was a music metadata and information retrieval platform for developers and media companies, which has since been integrated into Spotify.
	
	\item[] \textbf{Last.fm}\footnote{\url{http://last.fm}} is an online music social network and recommender system that collects information about users listeing habits and makes available crowd-sourced tagging data through an API. 
	
	\item[] \textbf{YAGO}\cite{Suchanek:WWW:2007} is a semantic knowledge base that collates information and structure from Wikipedia, WordNet and GeoNames with high accuracy. The ontology makes use of the categories defined in Wikipedia as a principle for semantic linking of entities, while exploiting the clean taxonomy of concepts from WordNet. 
	
	\item[] \textbf{the Music Ontology}\cite{DBLP:conf/ismir/RaimondASG07} provides main concepts and properties for describing musical entities, including artists, albums, tracks, performances, compositions, etc., on the Semantic Web
	
\end{itemize}

\begin{figure}[!ht]
	\centering
	\includegraphics[scale=0.5]{graphics/architecture.pdf}%\vspace{-5pt}
	\caption{MusicWeb architecture}\vspace{-10pt}
	\label{fig:layers}
\end{figure}

The global MusicBrainz identifiers enable convenient and concise means to disambiguate between potential duplicates or irregularities in metadata across resources, a problem which is all too common in systems relying on named entities. Besides identifiers, the MusicBrainz infrastructure is also used for the search functionality of MusicWeb. However, in order to query any information in DBpedia, the MusicBrainz identifiers need to be associated with a DBpedia resource, which is a different kind of identifier. This mapping is achieved by querying the Sameas.org co-reference service to retrieve the corresponding DBpedia URIs. The caveat in this process is that Sameas does not actually keep track of MusicBrainz artist URIs, however, by substituting the domain for the same artist's URI in the BBC domain\footnote{\url{http://www.bbc.co.uk/music/artists/}}, the service can get around this obstacle. Once the DBpedia artist identity is determined, the service proceeds to construct the majority of the profile, including the biography and most of the linking categories to other artists. The standard categories available include associated artists and artists from the same hometown, while music group membership and artist collaboration links are queried from MusicBrainz. The core of the Semantic Web linking functionality is provided by categories from YAGO. The Spotify\footnote{historically the Echonest} and Last.fm APIs are used for recommendations that are based on different similarity calculations, thus providing recommendations that do not necessarily overlap. 
%% - Brief description of what it is and what it does
%% - Architecture (with a nice diagram) [Alo, can you make this in Omnigraffle? I can then adjust/refine]
%% - More details about individual components we use (Yago, musicbrainz, sameas, dbpedia etc.)
%% - Brief intro to components we developed for artist similarity (just to bridge to Section 4)

\section{Artist similarity}
%% 4. Artist similarity 
%% 4.1 Socio-cultiral linkage (using linked data)
%% 4.2 Artist similarity by NLP [needs a better subtitle]
%% 4.3 Artist similarity by features [i can write this part]
Music does not lend itself easily to categorisation. There are many ways in which artist can be, and in fact are, considered to be related. Similarity may refer to whether artists' songs sound similar, or are perceived to be in the same style or genre. But it may also mean that they are followed by people from similar social backgrounds or political inclinations, or similar ages; or perhaps they are similar because they have played together, or participated in the same event, or their songs touch on similar themes. Linked data facilitates faceted searching and displaying of information\cite{Oren2006}: an artist may be similar to many other artists in one of the ways just mentioned, and to a completely different plethora of artists in other senses, all of which might contribute to music discovery. Semantic web technologies can help us gather different facets of data and shape them into representations of knowledge. MusicWeb does this by searching similarities in three different domains: socio-cultural, research and journalistic literature and content-based linkage.
\subsection{Socio-cultural linkage}
NOTE: not sure about this. Do we consider the dbpedia queries to be socio-cultural? or the collaborates-with in musicbrainz? Or do you (George) mean something like the introduction just above?

\subsection{Similarity in the literature}
Often artist share a connection through literature topics. For example: a psychologist interested in self-image during adolescence might want to research the impact of artists like Miley Cyrus or Rihanna on young teenagers\cite{Lamb2013}. Or a historian researching class politics in the UK might write about The Sex Pistols and John Lennon\cite{Moliterno2012}. In order to extract these relations one must mine the data from texts using natural language processing. Our starting point is a large database of 100,000 artists. MusicWeb searches several sources and collects texts that mention each artist. It then carries out semantic analysis to identify connections between artists and higher-level topics. There are two main sources of texts:
\begin{enumerate}
\item Research articles. There are various web resources that allow querying their research literature databases. MusicWeb uses mendeley\footnote{\url{http://dev.mendeley.com/}} and elsevier\footnote{\url{http://dev.elsevier.com/}}. Both resources offer managed and largely curated data and search possibilities include keywords, authors and disciplines. Data comprehension varies, but most often it features an array of keywords, an abstract, readership categorised according to discipline and sometimes the article itself.
  \item Online publications, such as newspapers, music magazines and blogs focused on music. This is non-managed, non-curated data, it must be extracted from the body of the text. The data is accessed after having crawled websites searching for keywords or tags in the title, and then scraped. External links contained in the page are also followed. 
\end{enumerate}
Many texts contain references to an artist name without actually being relevant to MusicWeb. A search for Madonna, for example, can yield many results from the fields of sculpture, art history or religion studies. The first step is to model the relevance of the text, and discard texts which are of no interest to music discovery. This is done through a two stage process:
\begin{enumerate}
\item Managed articles contain information about the number of readers per discipline. This data is analysed and texts are discarded if the readers belong mainly to disciplines not related to humanities.
\item The text is projected onto a tfd/idf vector space model\cite{Manning1999} constructed from words appearing in a relatively small collection of already accepted articles. Cosine similarity between this corpus and the text of every potential is computed, and texts which exceed a threshold are rejected.
\end{enumerate}
All items that pass these tests are stored as potential articles in the shape of the graph depicted in figure \ref{fig:article_graph}. Potential articles can always be reviewed and discarded as the corpus of articles grows and the similarity is recomputed.

\begin{figure}[!ht]
  \centering
  \includegraphics[scale=0.4]{graphics/article_graph.pdf}
  \caption{Article graph}
  \label{fig:article_graph}

\end{figure}
Texts (or abstracts, in the case of research publications where the body is not available) are subjected to semantic analysis. It is first tokenised and a bag of words is extracted from it. This bag of words is used to query the alchemy\footnote{AlchemyAPI is used under license from IBM Watson.} language analysis service for:
\begin{itemize}
\item Named entity recognition. The entity recogniser provides a list of names that appear mentioned in the text together with a measure of relevance. They can include toponyms, institutions, publications and persons. MusicWeb is interested in identifying artists, so every person mentioned is checked against the database. If the person is not included in MusicWeb's database then three resources are checked: dbpedia, musicbrainz and freebase. All three resources identify musicians using the yago ontology. It is important to align the artist properly, since the modeling process is largely unsupervised, and wrong identifications can skew the model. Musicians identified in texts are stored and linked to the artist that originated the query. MusicWeb then offers a link to either of them as ``appearing together in article''.
\item Keyword extraction. Non-managed texts and research that don't include tags or keywords. Keywords are checked against wordnet for hypernyms and stored. Artists that share keywords or hypernyms are considered to be relevant to the same topic in the literature.
\end{itemize}
MusicWeb also offers links between artists who appear in different articles by the same author, as well as in the same journal.



\subsection{Content-based linking}\label{sec:mir}

Content-based Music Information Retrieval (MIR) [Casey et.al. 2008] facilitates applications that rely on perceptual, statistical, semantic or musical features derived from audio using digital signal processing and machine learning methods. These features may include statistical aggregates computed from time-frequency representations extracted over short time windows. For instance, spectral centroid is said to correlate with the perceived brightness of a sound [Schubert et.al., 2006], therefore it may be used in the characterisation in timbral similarity between music pieces. More complex representations include features that are extracted using a perceptually motivated algorithm. Mel-Frequency Cepstral Coefficients for instance are often used in speech recognition as well as in estimating music similarity. Higher-level musical features include keys, chords, tempo, rhythm, as well as semantic features like genre or mood, with specific algorithms to extract this information from audio. 
%
Content-based features are increasingly used in music recommendation systems to overcome issues such as infrequent access of lesser known pieces in large music catalogues (the ``long-tail'' problem) or the difficulty of recommending new pieces without user ratings in systems that employ collaborative filtering (``cold-start'' problem) [Celma, 2008].

In this work, we are interested in supporting music discovery by facilitating a user to engage in interesting journeys through the ``space of music artists''. Although similar to recommendation, this is in contrast with most recommender systems which operate on the level of individual music items. We aim at creating links between artists based on stylistic elements of their music derived from a collection of recordings and complement the social and cultural links discussed in the previous sections.



\subsection{Similarity by mood}

While automatic feature extraction has significantly enhanced organisation and categorisation of large music collections, it is still rather challenging to derive high level semantic information relating to mood or genre. Complementing signal processing and machine learning methods with crowd-sourced social tagging data from platforms like Last.fm can enrich and inform understanding of general listening habits and connections between artists. 
Mood-based similarity is another experimental enhancement to MusicWeb. This method involves using the Semantic Web version of ILM10K music mood dataset that consists of over 4000 unique artists. The dataset is based on crowd-sourced mood tag statistics from Last.fm users, which have been transformed to numerical coordinates in a Cartesian space. Every track in the collection is associated to 2-dimensional coordinates reflecting energy and pleasantness respectively. The similarity between artists in this case is measured by first calculating the location of the target artist in the mood space by averaging the coordinates of all the associated tracks. The same procedure is repeated for all other artists which then enables computing Manhattan distances between the target from the rest and using the ranking as similarity metric. This process is illustrated by the example SPARQL query in Listing \ref{lst:sparql1}. 
\vspace{-10pt}
\noindent\begin{minipage}{\textwidth}
	\begin{lstlisting}[ style = sparql, label=lst:sparql1, tabsize=4,  caption={example SPARQL query to retrieve similar artists from the ILM10K mood dataset by Manhattan distance of valence-arousal coordinates.} ]
SELECT ?artist ?mbid
WHERE
{
	SELECT ?artist ?mbid (AVG(?valence) as ?avg_valence) (AVG(?arousal) as ?avg_arousal) ((ABS(AVG(?target_valence)-AVG(?valence)) + ABS(AVG(?target_arousal)-AVG(?arousal))) as ?diff)
	WHERE {
		{
			SELECT ?target_valence ?target_arousal
			WHERE {
				?target_coords mood:valence ?target_valence ;
					mood:arousal ?target_arousal ;
					mood:configuration mood:actfold4 .
				?target_lfmid mood:coordinates ?target_coords ;
					mood:artist_name ?target_artist .
				FILTER(?target_artist = "Roots Manuva")
			}
		}
		?coords mood:valence ?valence ;
			mood:arousal ?arousal ;
			mood:configuration mood:actfold4 .
		?lfmid mood:coordinates ?coords ;
			foaf:maker ?maker ;
			mood:artist_name ?artist .
		?maker mo:musicbrainz_guid ?mbid .
		FILTER(?artist != "Roots Manuva")
	} GROUP BY ?artist ?mbid ORDER BY ?diff
} LIMIT 20
	\end{lstlisting} 
\end{minipage}


\section{Discussion}\label{sec:discussion}

\section{Conclusions}\label{sec:conclusions}

	%
	% ---- Bibliography ----
	%
	%% \vspace{-1em}\begin{thebibliography}{5}
	%% 	%


        %%        \bibitem{Song2012}
        %%         Y.~Song, S.~Dixon and M.~Pearce.
        %%         \newblock A survey of music recommendation systems and future perspectives
        %%         \newblock In {\em Proceedings of the 9th International Symposium on Computer Music Modelling and Retrieval}, 2012.

        %%         \bibitem{Su2009}
        %%           X.~Su and T. M. ~Khoshgoftaar.
        %%         \newblock A Survey of Collaborative Filtering Techniques.
        %%         \newblock In {\em Advances in Artificial Intelligence,(Section 3):1–19}, 2009.

        %%       \bibitem{Aucoutourier2002}
        %%           J. J.~Aucouturier and F~Pachet.
        %%           \newblock Music Similarity Measures: What is the Use.
        %%           \newblock In {\em Proceedings of the ISMIR, pages 157–163}, 2002.

        %%         \bibitem{Kim2010}
        %%           Y.E.~Kim, E.M.~Schmidt, R.~Migneco, B.G.~Morton, P.~Richardson, J.~Scott, J.A.~Speck and D.~Turnbull.
        %%           \newblock Music Emotion Recognition: A State of the Art Review.
        %%           \newblock In {\em Proc. of the 11th Intl. Society for Music Information Retrieval (ISMIR) Conf}, 2010.

        %%       \bibitem{Celma2010}
        %%          \`O.~Celma
        %%          \newblock Music Recommendation and Discovery:The Long Tail, Long Fail, and Long Play in the Digital Music Space.
        %%          \newblock Springer Verlag, Heidelberg, 2010.

        %%        \bibitem{Zhou2004}
        %%         S.~Zhou and R. J.~Mondrag\'on
        %%         \newblock The rich-club phenomenon in the Internet topology
        %%         \newblock In {\em Communications Letters, IEEE}, 2004

        %%       \bibitem{Lee2015}
        %%         J. H.~Lee and R.~Price
        %%         \newblock Understanding users of commercial music services through personas: design implications.
        %%         \newblock In {\em Proceedings of the 16th ISMIR Conference}, M\'alaga, Spain, 2015

        %%       \bibitem{Jennings2007}
        %%           D.~Jennings.
        %%           \newblock Net, Blogs and Rock ’n’ Rolls: How Digital Discovery Works and What It Means for Consumers.
        %%           \newblock Nicholas Brealey Pub., 2007


        %%         \bibitem{Pachet2005}
        %%           F.~Pachet
        %%           \newblock Knowledge management and musical metadata.
        %%           \newblock In {\em Encyclopedia of Knowledge Management}, Schwartz, D. Ed. Idea Group, 2005


        %%          \bibitem{Marchioni2006}
        %%             G.~Marchionini
        %%             \newblock Exploratory search: from finding to understanding.
        %%             \newblock In {\em COMMUNICATIONS OF THE ACM}, 49(9), 2006

        %%         \bibitem{FazekasRJS10_OMRAS2}
	%%          G.~Fazekas, Y.~Raimond, K.~Jakobson, and M.~Sandler.
	%%          \newblock An overview of semantic web activities in the {OMRAS2} project.
	%%          \newblock {\em Journal of New Music Research (JNMR)}, 39(4), 2010.

	%%        \bibitem{Porter:ISMIR:15}
	%%          A.~Porter, D.~Bogdanov, R.~Kaye, R.~Tsukanov, and X.~Serra.
	%%          \newblock Acousticbrainz: a community platform for gathering music information
	%% 	 obtained from audio.
        %%          \newblock In {\em 16th International Society for Music Information Retrieval
	%% 		(ISMIR) Conference}, 2015.

	%% 	\bibitem{DBLP:conf/ismir/RaimondASG07}
	%% 	Y~Raimond, S.~Abdallah, M.~Sandler, and F.~Giasson.
	%% 	\newblock The music ontology.
	%% 	\newblock In {\em Proceedings of the 8th International Conference on Music
	%% 		Information Retrieval, ISMIR 2007, Vienna, Austria, September 23-27}, 2007.

	%% 	\bibitem{Suchanek:WWW:2007}
	%% 	F.~Suchanek, G.~Kasneci, and G.~Weikum
	%% 	\newblock YAGO: A Core of Semantic Knowledge Unifying WordNet and Wikipedia.
	%% 	\newblock In {\em Proceedings of the 16th international World Wide Web conference, May 8–12, 2007, Banff, Alberta, Canada.}, 2007.

        %%       \bibitem{Oren2006}
        %%         E.~Oren, R.~ Delbru, and S.~Decker
        %%         \newblock Extending faceted navigation for rdf data.
        %%         \newblock In {\em ISWC, 559–572}, 2006

        %%       \bibitem{Lamb2013}
        %%         S.~Lamb, K.~Graling and E. E. Wheeler
        %%         \newblock ‘Pole-arized’ discourse: An analysis of responses to Miley Cyrus’s Teen Choice Awards pole dance.
        %%         \newblock In {\em Feminism Psychology vol. 23}, May 2013

        %%       \bibitem{Moliterno2012}
        %%         A. G.~Moliterno
        %%         \newblock What Riot? Punk Rock Politics, Fascism, and Rock Against Racism.
        %%         \newblock Published online: \url{http://www.studentpulse.com/articles/612/what-riot-punk-rock-politics-fascism-and-rock-against-racism}, 2012

        %%       \bibitem{Manning1999}
        %%         C.~Manning and H.~Sch\"utze
        %%         \newblock Foundations of Statistical Natural Language Processing.
        %%         \newblock MIT Press, Cambridge, MA., 1999


        %%       \bibitem{Wong2012}
        %%         W.~Wong, W.~Liu and M.~Bennamoun
        %%        \newblock Ontology Learning from Text: A Look Back and into the Future
        %%        \newblock In {\em ACM Comput. Surv. 44, 4}, 2012

               
        %%       \bibitem{Landauer1998}
        %%           T.~Landauer, P.~Folt, and D.~Laham.
        %%          \newblock An introduction to latent semantic analysis
        %%          \newblock In {\em Discourse processes, 25}, 1998

        %%        \bibitem{Blei2012}
        %%          D.~Blei, A.~ Ng, and M.I.~Jordan.
        %%          \newblock Latent Dirichlet Allocation.
        %%          \newblock In {\em Journal of Machine Learning Research, 3(4-5), 993–1022}, 2012
			

	%% \end{thebibliography}
       
        \bibliographystyle{plain} 
        \bibliography{musicweb}

\end{document}