http://www.bayesfor.eu/wiki/ 2010-06-10T06:06:02+02:00 http://www.bayesfor.eu/wiki/ http://www.bayesfor.eu/wiki/lib/images/favicon.ico text/html 2008-09-15T15:55:13+02:00 http://www.bayesfor.eu/wiki/en/bayes-swarm/database Database description Bayes-Swarm is a research project that aims to design and build an engine to extract information from internet sources (news portals, newspapers, news agencies and TV websites). So far once a day it visits 30 sources that means around 70 web pages, mainly homepages and economical and political pages (the full list is reported in appendix A. Every page passes through a working process whose main steps are: text/html 2008-09-15T16:03:11+02:00 http://www.bayesfor.eu/wiki/en/bayes-swarm/dati Data accessibility * Research institutions interested in our data may contact us. * Flash representations of stem time series are available here. * Bayes-Swarm data may not be used for commercial pourpuse without permission. * data used to predict 2008 Italian general elections results are available: * web visibility [R format] * polls and web visibility [R/xls format] text/html 2008-09-15T16:02:44+02:00 http://www.bayesfor.eu/wiki/en/bayes-swarm/documentazione Bayes-Swarm documentation * What's Bayes-Swarm * Database description * Development * Words' flow normalization * Spidered Websources * Examples and applications * Data accessibility text/html 2008-09-15T16:01:48+02:00 http://www.bayesfor.eu/wiki/en/bayes-swarm/esempi Examples and Applications * Italian general election 2008 - [our prediction based on web visibility] * The abstract and references of our article on Italian PD Primary election is availble in english * you can search time series of english words and names here text/html 2008-09-15T16:00:59+02:00 http://www.bayesfor.eu/wiki/en/bayes-swarm/fonti complete source list Name, id, Since * ABC,39,Thu May 01 11:17:43 EDT 2008 * adnkronos,22,Mon Sep 17 16:50:54 EDT 2007 * AGO press,25,Fri Sep 21 09:19:01 EDT 2007 * Al Jazeera,5,Wed Sep 05 09:37:21 EDT 2007 * American reporter,98,Sat May 03 13:08:37 EDT 2008 * Ansa,6,Wed Sep 05 09:37:23 EDT 2007 * Associated Press,72,Sat May 03 13:05:04 EDT 2008 * Atlanta Journal Constitution,87,Sat May 03 13:08:19 EDT 2008 * Avvenire,16,Mon Oct 01 09:38:43 EDT 2007 * BBC - British Broadcasting Corpo… text/html 2008-09-15T15:54:13+02:00 http://www.bayesfor.eu/wiki/en/bayes-swarm/intro Bayes-Swarm Project Bayes-Swarm is a research project aiming at spidering web sources. Web sources' content are then organized in a huge database (the order of magnitude is hundred thusands occurences per day). Finally, the dataset is studied using standard statistical analysis and data mining tecniques. text/html 2008-09-15T16:00:02+02:00 http://www.bayesfor.eu/wiki/en/bayes-swarm/norma Application of geochemical and chemical models to word frequency data from web information flow We have developed a method to normalize words occurence flow and we have presented it in a working paper, this is the abstract: In the present work we applied geochemical concepts and the normalization method from Secondary Ion Mass Spectrometry (SIMS) to analyze word frequency data from web information sources. Bayes-Swarm is a research project that aims to design and build an engine to extr… text/html 2008-09-15T15:57:37+02:00 http://www.bayesfor.eu/wiki/en/bayes-swarm/normalization Application of geochemical and chemical models to word frequency data from web information flow In the present work we applied geochemical concepts and the normalization method from Secondary Ion Mass Spectrometry (SIMS) to analyze word frequency data from web information sources. Bayes-Swarm is a research project that aims to design and build an engine to extract information from internet sources (news portals, newspapers and news agencies websites, blogs, etc.), mainly homepages and econom… text/html 2008-09-15T15:56:14+02:00 http://www.bayesfor.eu/wiki/en/bayes-swarm/sviluppo Bayes-Swarm main development directions * Web content network analysis info/get involved * Normalization How to normalize word occurencies accounting for text volume flow and source popularity info/get involved * News decay What is the decay of attention rate for different news?info/get involved