The rapid growth of the number of videos in YouTube provides enormous potential for users to find content of interest to them. Unfortunately, given the difficulty of searching videos, the size of the video repository also makes the discovery of new content a daunting task. In this paper, we present a novel method based upon the analysis of the entire user-video graph to provide personalized video suggestions for users. The resulting algorithm, termed Adsorption, provides a simple method to efficiently propagate preference information through a variety of graphs. We extensively test the results of the recommendations on a three month snapshot of live data from YouTube.
Description
Video suggestion and discovery for Youtube: taking random walks through the view graph
%0 Conference Paper
%1 1367618
%A Baluja, Shumeet
%A Seth, Rohan
%A Sivakumar, D.
%A Jing, Yushi
%A Yagnik, Jay
%A Kumar, Shankar
%A Ravichandran, Deepak
%A Aly, Mohamed
%B WWW '08: Proceeding of the 17th international conference on World Wide Web
%C New York, NY, USA
%D 2008
%I ACM
%K recommendation video youtube
%P 895--904
%R http://doi.acm.org/10.1145/1367497.1367618
%T Video suggestion and discovery for youtube: taking random walks through the view graph
%U http://portal.acm.org/citation.cfm?id=1367618
%X The rapid growth of the number of videos in YouTube provides enormous potential for users to find content of interest to them. Unfortunately, given the difficulty of searching videos, the size of the video repository also makes the discovery of new content a daunting task. In this paper, we present a novel method based upon the analysis of the entire user-video graph to provide personalized video suggestions for users. The resulting algorithm, termed Adsorption, provides a simple method to efficiently propagate preference information through a variety of graphs. We extensively test the results of the recommendations on a three month snapshot of live data from YouTube.
%@ 978-1-60558-085-2
@inproceedings{1367618,
abstract = {The rapid growth of the number of videos in YouTube provides enormous potential for users to find content of interest to them. Unfortunately, given the difficulty of searching videos, the size of the video repository also makes the discovery of new content a daunting task. In this paper, we present a novel method based upon the analysis of the entire user-video graph to provide personalized video suggestions for users. The resulting algorithm, termed Adsorption, provides a simple method to efficiently propagate preference information through a variety of graphs. We extensively test the results of the recommendations on a three month snapshot of live data from YouTube.},
added-at = {2010-02-03T03:46:18.000+0100},
address = {New York, NY, USA},
author = {Baluja, Shumeet and Seth, Rohan and Sivakumar, D. and Jing, Yushi and Yagnik, Jay and Kumar, Shankar and Ravichandran, Deepak and Aly, Mohamed},
biburl = {https://www.bibsonomy.org/bibtex/24132605930e2d2d829065b3b36e6a672/snagpuss},
booktitle = {WWW '08: Proceeding of the 17th international conference on World Wide Web},
description = {Video suggestion and discovery for Youtube: taking random walks through the view graph},
doi = {http://doi.acm.org/10.1145/1367497.1367618},
interhash = {675569c2a2a965b235bc66f05f17f5e8},
intrahash = {4132605930e2d2d829065b3b36e6a672},
isbn = {978-1-60558-085-2},
keywords = {recommendation video youtube},
location = {Beijing, China},
pages = {895--904},
publisher = {ACM},
timestamp = {2010-02-03T03:46:51.000+0100},
title = {Video suggestion and discovery for youtube: taking random walks through the view graph},
url = {http://portal.acm.org/citation.cfm?id=1367618},
year = 2008
}