Predicting Human Preferences Using the Block Structure of Complex Social Networks. Guimerà, R., Llorente, A., Moro, E., & Sales-Pardo, M. PLoS One, 7(9):e44620, September, 2012. ![Predicting Human Preferences Using the Block Structure of Complex Social Networks [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex With ever-increasing available data, predicting individuals' preferences and helping them locate the most relevant information has become a pressing need. Understanding and predicting preferences is also important from a fundamental point of view, as part of what has been called a “new” computational social science. Here, we propose a novel approach based on stochastic block models, which have been developed by sociologists as plausible models of complex networks of social interactions. Our model is in the spirit of predicting individuals' preferences based on the preferences of others but, rather than fitting a particular model, we rely on a Bayesian approach that samples over the ensemble of all possible models. We show that our approach is considerably more accurate than leading recommender algorithms, with major relative improvements between 38% and 99% over industry-level algorithms. Besides, our approach sheds light on decision-making processes by identifying groups of individuals that have consistently similar preferences, and enabling the analysis of the characteristics of those groups.
@article{guimera_predicting_2012,
title = {Predicting {Human} {Preferences} {Using} the {Block} {Structure} of {Complex} {Social} {Networks}},
volume = {7},
url = {http://dx.doi.org/10.1371/journal.pone.0044620},
doi = {10.1371/journal.pone.0044620},
abstract = {With ever-increasing available data, predicting individuals' preferences
and helping them locate the most relevant information has become a
pressing need. Understanding and predicting preferences is also important
from a fundamental point of view, as part of what has been called a “new”
computational social science. Here, we propose a novel approach based on
stochastic block models, which have been developed by sociologists as
plausible models of complex networks of social interactions. Our model is
in the spirit of predicting individuals' preferences based on the
preferences of others but, rather than fitting a particular model, we rely
on a Bayesian approach that samples over the ensemble of all possible
models. We show that our approach is considerably more accurate than
leading recommender algorithms, with major relative improvements between
38\% and 99\% over industry-level algorithms. Besides, our approach sheds
light on decision-making processes by identifying groups of individuals
that have consistently similar preferences, and enabling the analysis of
the characteristics of those groups.},
number = {9},
urldate = {2014-10-04},
journal = {PLoS One},
author = {Guimerà, Roger and Llorente, Alejandro and Moro, Esteban and Sales-Pardo, Marta},
month = sep,
year = {2012},
pages = {e44620},
}
Downloads: 0
{"_id":"TgvduStb6XHHfTbJa","bibbaseid":"guimer-llorente-moro-salespardo-predictinghumanpreferencesusingtheblockstructureofcomplexsocialnetworks-2012","authorIDs":[],"author_short":["Guimerà, R.","Llorente, A.","Moro, E.","Sales-Pardo, M."],"bibdata":{"bibtype":"article","type":"article","title":"Predicting Human Preferences Using the Block Structure of Complex Social Networks","volume":"7","url":"http://dx.doi.org/10.1371/journal.pone.0044620","doi":"10.1371/journal.pone.0044620","abstract":"With ever-increasing available data, predicting individuals' preferences and helping them locate the most relevant information has become a pressing need. Understanding and predicting preferences is also important from a fundamental point of view, as part of what has been called a “new” computational social science. Here, we propose a novel approach based on stochastic block models, which have been developed by sociologists as plausible models of complex networks of social interactions. Our model is in the spirit of predicting individuals' preferences based on the preferences of others but, rather than fitting a particular model, we rely on a Bayesian approach that samples over the ensemble of all possible models. We show that our approach is considerably more accurate than leading recommender algorithms, with major relative improvements between 38% and 99% over industry-level algorithms. Besides, our approach sheds light on decision-making processes by identifying groups of individuals that have consistently similar preferences, and enabling the analysis of the characteristics of those groups.","number":"9","urldate":"2014-10-04","journal":"PLoS One","author":[{"propositions":[],"lastnames":["Guimerà"],"firstnames":["Roger"],"suffixes":[]},{"propositions":[],"lastnames":["Llorente"],"firstnames":["Alejandro"],"suffixes":[]},{"propositions":[],"lastnames":["Moro"],"firstnames":["Esteban"],"suffixes":[]},{"propositions":[],"lastnames":["Sales-Pardo"],"firstnames":["Marta"],"suffixes":[]}],"month":"September","year":"2012","pages":"e44620","bibtex":"@article{guimera_predicting_2012,\n\ttitle = {Predicting {Human} {Preferences} {Using} the {Block} {Structure} of {Complex} {Social} {Networks}},\n\tvolume = {7},\n\turl = {http://dx.doi.org/10.1371/journal.pone.0044620},\n\tdoi = {10.1371/journal.pone.0044620},\n\tabstract = {With ever-increasing available data, predicting individuals' preferences\nand helping them locate the most relevant information has become a\npressing need. Understanding and predicting preferences is also important\nfrom a fundamental point of view, as part of what has been called a “new”\ncomputational social science. Here, we propose a novel approach based on\nstochastic block models, which have been developed by sociologists as\nplausible models of complex networks of social interactions. Our model is\nin the spirit of predicting individuals' preferences based on the\npreferences of others but, rather than fitting a particular model, we rely\non a Bayesian approach that samples over the ensemble of all possible\nmodels. We show that our approach is considerably more accurate than\nleading recommender algorithms, with major relative improvements between\n38\\% and 99\\% over industry-level algorithms. Besides, our approach sheds\nlight on decision-making processes by identifying groups of individuals\nthat have consistently similar preferences, and enabling the analysis of\nthe characteristics of those groups.},\n\tnumber = {9},\n\turldate = {2014-10-04},\n\tjournal = {PLoS One},\n\tauthor = {Guimerà, Roger and Llorente, Alejandro and Moro, Esteban and Sales-Pardo, Marta},\n\tmonth = sep,\n\tyear = {2012},\n\tpages = {e44620},\n}\n\n","author_short":["Guimerà, R.","Llorente, A.","Moro, E.","Sales-Pardo, M."],"key":"guimera_predicting_2012","id":"guimera_predicting_2012","bibbaseid":"guimer-llorente-moro-salespardo-predictinghumanpreferencesusingtheblockstructureofcomplexsocialnetworks-2012","role":"author","urls":{"Paper":"http://dx.doi.org/10.1371/journal.pone.0044620"},"metadata":{"authorlinks":{}},"downloads":0},"bibtype":"article","biburl":"https://api.zotero.org/users/6655/collections/TJPPJ92X/items?key=VFvZhZXIoHNBbzoLZ1IM2zgf&format=bibtex&limit=100","creationDate":"2020-03-27T02:34:35.364Z","downloads":0,"keywords":[],"search_terms":["predicting","human","preferences","using","block","structure","complex","social","networks","guimerà","llorente","moro","sales-pardo"],"title":"Predicting Human Preferences Using the Block Structure of Complex Social Networks","year":2012,"dataSources":["5Dp4QphkvpvNA33zi","jfoasiDDpStqkkoZB","BiuuFc45aHCgJqDLY"]}