Inferring Networks of Diffusion and Influence. Gomez-Rodriguez, M., Leskovec, J., & Krause, A. In Proceedings of the 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, volume Proceeding, pages 1019--1028, June, 2010. Paper abstract bibtex Information diffusion and virus propagation are fundamental processes talking place in networks. While it is often possible to directly observe when nodes become infected, observing individual transmissions (i.e., who infects whom or who influences whom) is typically very difficult. Furthermore, in many applications, the underlying network over which the diffusions and propagations spread is actually unobserved. We tackle these challenges by developing a method for tracing paths of diffusion and influence through networks and inferring the networks over which contagions propagate. Given the times when nodes adopt pieces of information or become infected, we identify the optimal network that best explains the observed infection times. Since the optimization problem is NP-hard to solve exactly, we develop an efficient approximation algorithm that scales to large datasets and in practice gives provably near-optimal performance. We demonstrate the effectiveness of our approach by tracing information cascades in a set of 170 million blogs and news articles over a one year period to infer how information flows through the online media space. We find that the diffusion network of news tends to have a core-periphery structure with a small set of core media sites that diffuse information to the rest of the Web. These sites tend to have stable circles of influence with more general news media sites acting as connectors between them.
@INPROCEEDINGS{Gomez-Rodriguez2010a,
author = {Gomez-Rodriguez, Manuel and Leskovec, Jure and Krause, Andreas},
title = {{Inferring Networks of Diffusion and Influence}},
booktitle = {Proceedings of the 16th ACM SIGKDD International Conference on Knowledge
Discovery and Data Mining},
year = {2010},
volume = {Proceeding},
pages = {1019--1028},
month = jun,
abstract = {Information diffusion and virus propagation are fundamental processes
talking place in networks. While it is often possible to directly
observe when nodes become infected, observing individual transmissions
(i.e., who infects whom or who influences whom) is typically very
difficult. Furthermore, in many applications, the underlying network
over which the diffusions and propagations spread is actually unobserved.
We tackle these challenges by developing a method for tracing paths
of diffusion and influence through networks and inferring the networks
over which contagions propagate. Given the times when nodes adopt
pieces of information or become infected, we identify the optimal
network that best explains the observed infection times. Since the
optimization problem is NP-hard to solve exactly, we develop an efficient
approximation algorithm that scales to large datasets and in practice
gives provably near-optimal performance. We demonstrate the effectiveness
of our approach by tracing information cascades in a set of 170 million
blogs and news articles over a one year period to infer how information
flows through the online media space. We find that the diffusion
network of news tends to have a core-periphery structure with a small
set of core media sites that diffuse information to the rest of the
Web. These sites tend to have stable circles of influence with more
general news media sites acting as connectors between them.},
arxivid = {1006.0234},
file = {:C$\backslash$:/Users/Dani/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Gomez-Rodriguez, Leskovec, Krause - 2010 - Inferring Networks of Diffusion and Influence.pdf:pdf},
keywords = {\#News\_Aggregator,\#attribution,\#content,\#disease\_outbreak,\#evolution,Data
Structures and Algorithms,Machine Learning,Physics and Society},
mendeley-tags = {\#News\_Aggregator,\#attribution,\#content,\#disease\_outbreak,\#evolution},
url = {http://arxiv.org/abs/1006.0234}
}
Downloads: 0
{"_id":{"_str":"51f6ae0a59ced8df44000f58"},"__v":62,"authorIDs":["5457d58e2abc8e9f370007bb"],"author_short":["Gomez-Rodriguez, M.","Leskovec, J.","Krause, A."],"bibbaseid":"gomezrodriguez-leskovec-krause-inferringnetworksofdiffusionandinfluence-2010","bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"propositions":[],"lastnames":["Gomez-Rodriguez"],"firstnames":["Manuel"],"suffixes":[]},{"propositions":[],"lastnames":["Leskovec"],"firstnames":["Jure"],"suffixes":[]},{"propositions":[],"lastnames":["Krause"],"firstnames":["Andreas"],"suffixes":[]}],"title":"Inferring Networks of Diffusion and Influence","booktitle":"Proceedings of the 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","year":"2010","volume":"Proceeding","pages":"1019--1028","month":"June","abstract":"Information diffusion and virus propagation are fundamental processes talking place in networks. While it is often possible to directly observe when nodes become infected, observing individual transmissions (i.e., who infects whom or who influences whom) is typically very difficult. Furthermore, in many applications, the underlying network over which the diffusions and propagations spread is actually unobserved. We tackle these challenges by developing a method for tracing paths of diffusion and influence through networks and inferring the networks over which contagions propagate. Given the times when nodes adopt pieces of information or become infected, we identify the optimal network that best explains the observed infection times. Since the optimization problem is NP-hard to solve exactly, we develop an efficient approximation algorithm that scales to large datasets and in practice gives provably near-optimal performance. We demonstrate the effectiveness of our approach by tracing information cascades in a set of 170 million blogs and news articles over a one year period to infer how information flows through the online media space. We find that the diffusion network of news tends to have a core-periphery structure with a small set of core media sites that diffuse information to the rest of the Web. These sites tend to have stable circles of influence with more general news media sites acting as connectors between them.","arxivid":"1006.0234","file":":C$\\backslash$:/Users/Dani/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Gomez-Rodriguez, Leskovec, Krause - 2010 - Inferring Networks of Diffusion and Influence.pdf:pdf","keywords":"#News_Aggregator,#attribution,#content,#disease_outbreak,#evolution,Data Structures and Algorithms,Machine Learning,Physics and Society","mendeley-tags":"#News_Aggregator,#attribution,#content,#disease_outbreak,#evolution","url":"http://arxiv.org/abs/1006.0234","bibtex":"@INPROCEEDINGS{Gomez-Rodriguez2010a,\r\n author = {Gomez-Rodriguez, Manuel and Leskovec, Jure and Krause, Andreas},\r\n title = {{Inferring Networks of Diffusion and Influence}},\r\n booktitle = {Proceedings of the 16th ACM SIGKDD International Conference on Knowledge\r\n\tDiscovery and Data Mining},\r\n year = {2010},\r\n volume = {Proceeding},\r\n pages = {1019--1028},\r\n month = jun,\r\n abstract = {Information diffusion and virus propagation are fundamental processes\r\n\ttalking place in networks. While it is often possible to directly\r\n\tobserve when nodes become infected, observing individual transmissions\r\n\t(i.e., who infects whom or who influences whom) is typically very\r\n\tdifficult. Furthermore, in many applications, the underlying network\r\n\tover which the diffusions and propagations spread is actually unobserved.\r\n\tWe tackle these challenges by developing a method for tracing paths\r\n\tof diffusion and influence through networks and inferring the networks\r\n\tover which contagions propagate. Given the times when nodes adopt\r\n\tpieces of information or become infected, we identify the optimal\r\n\tnetwork that best explains the observed infection times. Since the\r\n\toptimization problem is NP-hard to solve exactly, we develop an efficient\r\n\tapproximation algorithm that scales to large datasets and in practice\r\n\tgives provably near-optimal performance. We demonstrate the effectiveness\r\n\tof our approach by tracing information cascades in a set of 170 million\r\n\tblogs and news articles over a one year period to infer how information\r\n\tflows through the online media space. We find that the diffusion\r\n\tnetwork of news tends to have a core-periphery structure with a small\r\n\tset of core media sites that diffuse information to the rest of the\r\n\tWeb. These sites tend to have stable circles of influence with more\r\n\tgeneral news media sites acting as connectors between them.},\r\n arxivid = {1006.0234},\r\n file = {:C$\\backslash$:/Users/Dani/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Gomez-Rodriguez, Leskovec, Krause - 2010 - Inferring Networks of Diffusion and Influence.pdf:pdf},\r\n keywords = {\\#News\\_Aggregator,\\#attribution,\\#content,\\#disease\\_outbreak,\\#evolution,Data\r\n\tStructures and Algorithms,Machine Learning,Physics and Society},\r\n mendeley-tags = {\\#News\\_Aggregator,\\#attribution,\\#content,\\#disease\\_outbreak,\\#evolution},\r\n url = {http://arxiv.org/abs/1006.0234}\r\n}\r\n\r\n","author_short":["Gomez-Rodriguez, M.","Leskovec, J.","Krause, A."],"key":"Gomez-Rodriguez2010a","id":"Gomez-Rodriguez2010a","bibbaseid":"gomezrodriguez-leskovec-krause-inferringnetworksofdiffusionandinfluence-2010","role":"author","urls":{"Paper":"http://arxiv.org/abs/1006.0234"},"keyword":["#News_Aggregator","#attribution","#content","#disease_outbreak","#evolution","Data Structures and Algorithms","Machine Learning","Physics and Society"],"downloads":0,"html":""},"bibtype":"inproceedings","biburl":"http://delicias.dia.fi.upm.es/prov-xgCURATED.bib","downloads":0,"keywords":["#news_aggregator","#attribution","#content","#disease_outbreak","#evolution","data structures and algorithms","machine learning","physics and society"],"search_terms":["inferring","networks","diffusion","influence","gomez-rodriguez","leskovec","krause"],"title":"Inferring Networks of Diffusion and Influence","title_words":["inferring","networks","diffusion","influence"],"year":2010,"dataSources":["drTBSwRdnSo2Wujnd"]}