|
p@32
|
1 @InProceedings{C2,
|
|
p@32
|
2 author = "Jones, C.D. and Smith, A.B. and Roberts, E.F.",
|
|
p@32
|
3 title = "Article Title",
|
|
p@32
|
4 booktitle = "Proceedings Title",
|
|
p@32
|
5 organization = "IEEE",
|
|
p@32
|
6 year = "2003",
|
|
p@32
|
7 volume = "II",
|
|
p@32
|
8 pages = "803-806"
|
|
p@32
|
9 }
|
|
p@32
|
10
|
|
p@32
|
11
|
|
p@32
|
12 @incollection{melville2010recommender,
|
|
p@32
|
13 title={Recommender systems},
|
|
p@32
|
14 author={Melville, Prem and Sindhwani, Vikas},
|
|
p@32
|
15 booktitle={Encyclopedia of machine learning},
|
|
p@32
|
16 pages={829--838},
|
|
p@32
|
17 year={2010},
|
|
p@32
|
18 publisher={Springer}
|
|
p@32
|
19 }
|
|
p@32
|
20
|
|
p@32
|
21
|
|
p@32
|
22 @incollection{Lops2011,
|
|
p@32
|
23 year={2011},
|
|
p@32
|
24 isbn={978-0-387-85819-7},
|
|
p@32
|
25 booktitle={Recommender Systems Handbook},
|
|
p@32
|
26 editor={Ricci, Francesco and Rokach, Lior and Shapira, Bracha and Kantor, Paul B.},
|
|
p@32
|
27 doi={10.1007/978-0-387-85820-3_3},
|
|
p@32
|
28 title={Content-based Recommender Systems: State of the Art and Trends},
|
|
p@32
|
29 url={http://dx.doi.org/10.1007/978-0-387-85820-3_3},
|
|
p@32
|
30 publisher={Springer US},
|
|
p@32
|
31 author={Lops, Pasquale and de Gemmis, Marco and Semeraro, Giovanni},
|
|
p@32
|
32 pages={73-105},
|
|
p@32
|
33 language={English}
|
|
p@32
|
34 }
|
|
p@32
|
35
|
|
p@32
|
36
|
|
p@32
|
37 @incollection{NIPS2013_5004,
|
|
p@32
|
38 title = {Deep content-based music recommendation},
|
|
p@32
|
39 author = {van den Oord, Aaron and Dieleman, Sander and Schrauwen, Benjamin},
|
|
p@32
|
40 booktitle = {Advances in Neural Information Processing Systems 26},
|
|
p@32
|
41 editor = {C.J.C. Burges and L. Bottou and M. Welling and Z. Ghahramani and K.Q. Weinberger},
|
|
p@32
|
42 pages = {2643--2651},
|
|
p@32
|
43 year = {2013},
|
|
p@32
|
44 publisher = {Curran Associates, Inc.},
|
|
p@32
|
45 url = {http://papers.nips.cc/paper/5004-deep-content-based-music-recommendation.pdf}
|
|
p@32
|
46 }
|
|
p@32
|
47
|
|
p@32
|
48
|
|
p@32
|
49 @incollection{pelikan2015estimation,
|
|
p@32
|
50 title={Estimation of Distribution Algorithms},
|
|
p@32
|
51 author={Pelikan, Martin and Hauschild, Mark W and Lobo, Fernando G},
|
|
p@32
|
52 booktitle={Springer Handbook of Computational Intelligence},
|
|
p@32
|
53 pages={899--928},
|
|
p@32
|
54 year={2015},
|
|
p@32
|
55 publisher={Springer}
|
|
p@32
|
56 }
|
|
p@32
|
57
|
|
p@32
|
58
|
|
p@32
|
59 @ARTICLE{Ding2015451,
|
|
p@32
|
60 author={Ding, C. and Ding, L. and Peng, W.},
|
|
p@32
|
61 title={Comparison of effects of different learning methods on estimation of distribution algorithms},
|
|
p@32
|
62 journal={Journal of Software Engineering},
|
|
p@32
|
63 year={2015},
|
|
p@32
|
64 volume={9},
|
|
p@32
|
65 number={3},
|
|
p@32
|
66 pages={451-468},
|
|
p@32
|
67 doi={10.3923/jse.2015.451.468},
|
|
p@32
|
68 note={},
|
|
p@32
|
69 url={http://www.scopus.com/inward/record.url?eid=2-s2.0-84924609049&partnerID=40&md5=e6419e97e218f8ef1600e3d21e6a9e36},
|
|
p@32
|
70 document_type={Article},
|
|
p@32
|
71 source={Scopus},
|
|
p@32
|
72 }
|
|
p@32
|
73
|
|
p@32
|
74
|
|
p@32
|
75 @unpublished{Bengio-et-al-2015-Book,
|
|
p@32
|
76 title={Deep Learning},
|
|
p@32
|
77 author={Yoshua Bengio and Ian J. Goodfellow and Aaron Courville},
|
|
p@32
|
78 note={Book in preparation for MIT Press},
|
|
p@32
|
79 url={http://www.iro.umontreal.ca/~bengioy/dlbook},
|
|
p@32
|
80 year={2015}
|
|
p@32
|
81 }
|
|
p@32
|
82
|
|
p@32
|
83
|
|
p@32
|
84 @INPROCEEDINGS{Bertin-Mahieux2011,
|
|
p@32
|
85 author = {Thierry Bertin-Mahieux and Daniel P.W. Ellis and Brian Whitman and Paul Lamere},
|
|
p@32
|
86 title = {The Million Song Dataset},
|
|
p@32
|
87 booktitle = {{Proceedings of the 12th International Conference on Music Information
|
|
p@32
|
88 Retrieval ({ISMIR} 2011)}},
|
|
p@32
|
89 year = {2011},
|
|
p@32
|
90 owner = {thierry},
|
|
p@32
|
91 timestamp = {2010.03.07}
|
|
p@32
|
92 }
|
|
p@32
|
93
|
|
p@32
|
94
|
|
p@32
|
95 @phdthesis {1242,
|
|
p@32
|
96 title = {Music Recommendation and Discovery in the Long Tail},
|
|
p@32
|
97 year = {2008},
|
|
p@32
|
98 school = {Universitat Pompeu Fabra},
|
|
p@32
|
99 address = {Barcelona},
|
|
p@32
|
100 abstract = {<p class="small">
|
|
p@32
|
101 Music consumption is biased towards a few popular artists. For instance, in 2007 only 1\% of
|
|
p@32
|
102 all digital tracks accounted for 80\% of all sales. Similarly, 1,000 albums accounted for 50\%
|
|
p@32
|
103 of all album sales, and 80\% of all albums sold were purchased less than 100 times. There is
|
|
p@32
|
104 a need to assist people to filter, discover, personalise and recommend from the huge amount
|
|
p@32
|
105 of music content available along the Long Tail.
|
|
p@32
|
106 </p>
|
|
p@32
|
107 <p class="small">
|
|
p@32
|
108 Current music recommendation algorithms try to
|
|
p@32
|
109 accurately predict what people demand to listen to. However, quite
|
|
p@32
|
110 often these algorithms tend to recommend popular -or well-known to the
|
|
p@32
|
111 user- music, decreasing the effectiveness of the recommendations. These
|
|
p@32
|
112 approaches focus on improving the accuracy of the recommendations. That
|
|
p@32
|
113 is, try to make
|
|
p@32
|
114 accurate predictions about what a user could listen to, or buy next,
|
|
p@32
|
115 independently of how
|
|
p@32
|
116 useful to the user could be the provided recommendations.
|
|
p@32
|
117 </p>
|
|
p@32
|
118 <p class="small">
|
|
p@32
|
119 In this Thesis we stress the importance of the user{\textquoteright}s
|
|
p@32
|
120 perceived quality of the recommendations. We model the Long Tail curve
|
|
p@32
|
121 of artist popularity to predict -potentially-
|
|
p@32
|
122 interesting and unknown music, hidden in the tail of the popularity
|
|
p@32
|
123 curve. Effective recommendation systems should promote novel and
|
|
p@32
|
124 relevant material (non-obvious recommendations), taken primarily from
|
|
p@32
|
125 the tail of a popularity distribution.
|
|
p@32
|
126 </p>
|
|
p@32
|
127 <p class="small">
|
|
p@32
|
128 The main contributions of this Thesis are: <em>(i)</em> a novel network-based approach for
|
|
p@32
|
129 recommender systems, based on the analysis of the item (or user) similarity graph, and the
|
|
p@32
|
130 popularity of the items, <em>(ii)</em> a user-centric evaluation that measures the user{\textquoteright}s relevance
|
|
p@32
|
131 and novelty of the recommendations, and <em>(iii)</em> two prototype systems that implement the
|
|
p@32
|
132 ideas derived from the theoretical work. Our findings have significant implications for
|
|
p@32
|
133 recommender systems that assist users to explore the Long Tail, digging for content they
|
|
p@32
|
134 might like.
|
|
p@32
|
135 </p>
|
|
p@32
|
136 },
|
|
p@32
|
137 url = {http://mtg.upf.edu/static/media/PhD_ocelma.pdf},
|
|
p@32
|
138 author = {Celma, \`{O}.}
|
|
p@32
|
139 }
|
|
p@32
|
140
|
|
p@32
|
141
|
|
p@32
|
142 @inproceedings{gallagher2007bayesian,
|
|
p@32
|
143 title={Bayesian inference in estimation of distribution algorithms},
|
|
p@32
|
144 author={Gallagher, Marcus and Wood, Ian and Keith, Jonathan and Sofronov, George},
|
|
p@32
|
145 booktitle={Evolutionary Computation, 2007. CEC 2007. IEEE Congress on},
|
|
p@32
|
146 pages={127--133},
|
|
p@32
|
147 year={2007},
|
|
p@32
|
148 organization={IEEE}
|
|
p@32
|
149 }
|
|
p@32
|
150
|
|
p@32
|
151
|
