%0 Journal Article %1 Erramilli2011Explore %A Erramilli, Vijay %A Yang, Xiaoyuan %A Rodriguez, Pablo %D 2011 %K twitter social-networks preprint information-diffusion %T Explore what-if scenarios with SONG: Social Network Write Generator %U http://arxiv.org/abs/1102.0699 %X Online Social Networks (OSNs) have witnessed a tremendous growth the last few years, becoming a platform for online users to communicate, exchange content and even find employment. The emergence of OSNs has attracted researchers and analysts and much data-driven research has been conducted. However, collecting data-sets is non-trivial and sometimes it is difficult for data-sets to be shared between researchers. The main contribution of this paper is a framework called SONG (Social Network Write Generator) to generate synthetic traces of write activity on OSNs. We build our framework based on a characterization study of a large Twitter data-set and identifying the important factors that need to be accounted for. We show how one can generate traces with SONG and validate it by comparing against real data. We discuss how one can extend and use SONG to explore different `what-if' scenarios. We build a Twitter clone using 16 machines and Cassandra. We then show by example the usefulness of SONG by stress-testing our implementation. We hope that SONG is used by researchers and analysts for their own work that involves write activity.

@article{Erramilli2011Explore, abstract = {{Online Social Networks (OSNs) have witnessed a tremendous growth the last few years, becoming a platform for online users to communicate, exchange content and even find employment. The emergence of OSNs has attracted researchers and analysts and much data-driven research has been conducted. However, collecting data-sets is non-trivial and sometimes it is difficult for data-sets to be shared between researchers. The main contribution of this paper is a framework called SONG (Social Network Write Generator) to generate synthetic traces of write activity on OSNs. We build our framework based on a characterization study of a large Twitter data-set and identifying the important factors that need to be accounted for. We show how one can generate traces with SONG and validate it by comparing against real data. We discuss how one can extend and use SONG to explore different `what-if' scenarios. We build a Twitter clone using 16 machines and Cassandra. We then show by example the usefulness of SONG by stress-testing our implementation. We hope that SONG is used by researchers and analysts for their own work that involves write activity.}}, added-at = {2019-06-10T14:53:09.000+0200}, archiveprefix = {arXiv}, author = {Erramilli, Vijay and Yang, Xiaoyuan and Rodriguez, Pablo}, biburl = {https://www.bibsonomy.org/bibtex/2531f3a4e71d4a3e15b88f42c42182dc0/nonancourt}, citeulike-article-id = {8781969}, citeulike-linkout-0 = {http://arxiv.org/abs/1102.0699}, citeulike-linkout-1 = {http://arxiv.org/pdf/1102.0699}, day = 3, eprint = {1102.0699}, interhash = {614ac6f9df376fe065881cf67e0745c9}, intrahash = {531f3a4e71d4a3e15b88f42c42182dc0}, keywords = {twitter social-networks preprint information-diffusion}, month = feb, posted-at = {2011-02-08 09:08:02}, priority = {2}, timestamp = {2019-07-31T12:36:13.000+0200}, title = {{Explore what-if scenarios with SONG: Social Network Write Generator}}, url = {http://arxiv.org/abs/1102.0699}, year = 2011 }