Towards trust-aware recommendations in social networks
Alberto Lumbreras Carrasco · 2012
for inspiring the first ideas for this thesis after wondering, upset, why last.fm hadn’t recommend him that upcoming concert of his favorite and most listened band, Los Planetas; for pointing me to Trust-aware Recommender Systems when I was lost, and for introducing me the Recommender Systems Handbook. Thanks to the authors of the handbook for writing and compiling such a comprehensive introduction to the state of the art of recommender systems. This book has been specially helpful when writing Chapter 2 of this Master Thesis and has served as a starting point to find further references. Thanks to Elisa for her laughs, the strength and the motivation, and for having taken too much care of our reproductive labour. Thanks to my parents for their dedication. This Thesis wouldn’t have been possible without of all the efforts they invested on me. Thanks to my Master Thesis Advisor, Ricard Gavaldà, for opening the doors of research to me, and allowing me to pursue that old human dream of combining work and pleasure. Thanks to all the men and women that struggled to get a public education system, and to those who are still struggling to defend it today. 1 2 Recommender systems have been strongly researched within the last decade. With the emergence and popularization of social networks a new field has been opened for social recommendations. Introducing new concepts such as trust and considering the network topology are some of the new strategies that recommender systems have to take into account in order to adapt their techniques to these new scenarios. In this thesis a simple model for recommendations on twitter is developed to apply some of the known techniques and explore how well the state of the art does in a real scenario. The thesis can serve as a basis for further social recommender system research. Contents 1