Comments for Shane's Blog http://sbutler.com/blog data mining and things i find interesting Thu, 22 Mar 2007 00:10:41 +1100 http://wordpress.org/?v=2.8.4 hourly 1 Comment on Smart SPAM & Fighting it by John Aitchison http://sbutler.com/blog/2006/05/smart-spam/comment-page-1/#comment-3905 John Aitchison Thu, 22 Mar 2007 00:10:41 +0000 http://sbutler.com/blog/2006/05/smart-spam/#comment-3905 Interesting ideas. I guess I am not as hopeful as you that a centralized solution like Gmail would be smart enough quickly enough to defeat spammers. For example I get a lot of spam emails with near duplicate but natural enough looking content - the problem is that the content (which has been harvested from the web) is not the real message (which is often male performance enhancing drugs) and swamps the Bayesian filters. I am not sure that "Bayesian like" classification tools will ever be smart enough for this. I think I have a blog entry on this .. no, I just checked, it is not up, so I will put it up now. Here it is http://dsanalytics.com/dsblog/why-bayesian-spam-filters-are-doomed_92 btw, the medium of choice for people under 20 seems to be texting.. email is seen as old hat and when it is used it is usually through eg hotmail who do seem to do a good job of spam suppression. Email is still, however, the medium of business communication although I am intrigued by the gmail idea of conversations (not universally loved though - see http://philwilson.org/blog/2005/06/gmail-conversations.html) Interesting ideas.

I guess I am not as hopeful as you that a centralized solution like Gmail would be smart enough quickly enough to defeat spammers.

For example I get a lot of spam emails with near duplicate but natural enough looking content – the problem is that the content (which has been harvested from the web) is not the real message (which is often male performance enhancing drugs) and swamps the Bayesian filters. I am not sure that “Bayesian like” classification tools will ever be smart enough for this.

I think I have a blog entry on this .. no, I just checked, it is not up, so I will put it up now. Here it is http://dsanalytics.com/dsblog/why-bayesian-spam-filters-are-doomed_92

btw, the medium of choice for people under 20 seems to be texting.. email is seen as old hat and when it is used it is usually through eg hotmail who do seem to do a good job of spam suppression.

Email is still, however, the medium of business communication although I am intrigued by the gmail idea of conversations (not universally loved though – see http://philwilson.org/blog/2005/06/gmail-conversations.html)

]]> Comment on Getting to know R Graphs by » Some inspiration from Statistical Graphics (R, Graphviz etc) [ Data Sciences Analytics ] http://sbutler.com/blog/2006/04/getting-to-know-r-graphs/comment-page-1/#comment-3901 » Some inspiration from Statistical Graphics (R, Graphviz etc) [ Data Sciences Analytics ] Wed, 21 Mar 2007 23:50:21 +0000 http://sbutler.com/blog/2006/04/getting-to-know-r-graphs/#comment-3901 [...] graphics or their ability to convey nuances (sometimes words rule, OK?) I am indebted to Shane’s Blog for a pointer to the R Graph [...] [...] graphics or their ability to convey nuances (sometimes words rule, OK?) I am indebted to Shane’s Blog for a pointer to the R Graph [...]

]]> Comment on Future of Radio by Pierre http://sbutler.com/blog/2006/03/pandora-musicminer/comment-page-1/#comment-2351 Pierre Wed, 03 Jan 2007 13:01:35 +0000 http://sbutler.com/blog/2006/03/pandora-musicminer/#comment-2351 There is also "last.fm" , a music recommader system based on collaborative filtering methods. There is also “last.fm” , a music recommader system based on collaborative filtering methods.

]]> Comment on DD-WRT, Another Alternative by Jerry http://sbutler.com/blog/2006/01/dd-wrt-another-alternative/comment-page-1/#comment-2216 Jerry Thu, 14 Dec 2006 12:38:19 +0000 http://sbutler.com/blog/2006/01/dd-wrt-another-alternative/#comment-2216 Working online configuration menus for DD-WRT V23 SP2 running on a Buffalo WHR-G54S wireless router: http://www.clearnet.com.au/xcart/Rips/DD-WRT_Buffalo_WHR_G54S/Buffalo_AP/192.168.20.43/index.asp.htm Working online configuration menus for DD-WRT V23 SP2 running on a Buffalo WHR-G54S wireless router:

http://www.clearnet.com.au/xcart/Rips/DD-WRT_Buffalo_WHR_G54S/Buffalo_AP/192.168.20.43/index.asp.htm

]]> Comment on DD-WRT, Another Alternative by Jerry http://sbutler.com/blog/2006/01/dd-wrt-another-alternative/comment-page-1/#comment-2109 Jerry Sat, 25 Nov 2006 19:37:22 +0000 http://sbutler.com/blog/2006/01/dd-wrt-another-alternative/#comment-2109 DD-WRT is now up to V2.3 SP2 - released this September: http://www.dd-wrt.com/dd-wrtv2/down.php?path=downloads%2Fdd-wrt.v23+SP2/ See an online working config menu for DD-WRT V2.3 SP1 here: http://www.clearnet.com.au/ssl/xcart/Rips/DD-WRT/192.168.1.1/index.asp.htm DD-WRT is now up to V2.3 SP2 – released this September:

http://www.dd-wrt.com/dd-wrtv2/down.php?path=downloads%2Fdd-wrt.v23+SP2/

See an online working config menu for DD-WRT V2.3 SP1 here: http://www.clearnet.com.au/ssl/xcart/Rips/DD-WRT/192.168.1.1/index.asp.htm

]]> Comment on Using Gmail for Backups by Haochi http://sbutler.com/blog/2006/05/gmail-for-backups/comment-page-1/#comment-229 Haochi Wed, 03 May 2006 00:46:15 +0000 http://sbutler.com/blog/2006/05/gmail-for-backups/#comment-229 I think you can only backup files that are less than 10MB. I think you can only backup files that are less than 10MB.

]]> Comment on WEKA in Jython or even C# by Dalibor Topic http://sbutler.com/blog/2006/03/weka-jython-csharp/comment-page-1/#comment-226 Dalibor Topic Mon, 03 Apr 2006 01:27:21 +0000 http://sbutler.com/blog/2006/03/weka-jython-csharp/#comment-226 Heya, you may want to check out gcj & how PyLucene does it, if you want to call Java code from Python without having to port your code to a JVM. cheers, dalibor topic Heya, you may want to check out gcj & how PyLucene does it, if you want to call Java code from Python without having to port your code to a JVM.

cheers,
dalibor topic

]]> Comment on Got Zeitgeist? Mining Online Trends by Shane http://sbutler.com/blog/2006/03/mining-online-trends/comment-page-1/#comment-225 Shane Tue, 07 Mar 2006 09:12:36 +0000 http://sbutler.com/blog/2006/03/mining-online-trends/#comment-225 Nice, thanks for the link (and the book :P) Nice, thanks for the link (and the book :P )

]]> Comment on Got Zeitgeist? Mining Online Trends by Swaroop C H http://sbutler.com/blog/2006/03/mining-online-trends/comment-page-1/#comment-224 Swaroop C H Tue, 07 Mar 2006 07:01:57 +0000 http://sbutler.com/blog/2006/03/mining-online-trends/#comment-224 Have you seen http://buzz.yahoo.com ? Have you seen http://buzz.yahoo.com ?

]]> Comment on Online Advertising Gone Mad? by Shane’s Blog » Blog Archive » More on Online Advertising http://sbutler.com/blog/2006/01/online-advertising/comment-page-1/#comment-223 Shane’s Blog » Blog Archive » More on Online Advertising Wed, 22 Feb 2006 00:58:45 +0000 http://sbutler.com/blog/2005/11/adsense/#comment-223 [...] I previously blogged about advertisers going troppo for The Million Dollar Homepage. Well, online advertising is hot all over the net and is gaining on all traditional mediums fast. Australian Internet advert spending was AUD$620 Million last year, and will be AUD$1 Billion by the end of the year. Interestingly Internet advertising only accounts for around 6% of Australian advertising budgets even though Australians are spending 15% of their media contact time online. [...] [...] I previously blogged about advertisers going troppo for The Million Dollar Homepage. Well, online advertising is hot all over the net and is gaining on all traditional mediums fast. Australian Internet advert spending was AUD$620 Million last year, and will be AUD$1 Billion by the end of the year. Interestingly Internet advertising only accounts for around 6% of Australian advertising budgets even though Australians are spending 15% of their media contact time online. [...]

]]> Comment on Online Advertising Gone Mad? by Michael Frans http://sbutler.com/blog/2006/01/online-advertising/comment-page-1/#comment-200 Michael Frans Wed, 04 Jan 2006 04:55:43 +0000 http://sbutler.com/blog/2005/11/adsense/#comment-200 My hat goes off to Alex Tew, he certainly found a unique idea to sell ad space. I actually took his idea one step further... selling ad space by the BYTE! There are so many "pixel pushers" out there now that I needed to put a spin on the pixel advertising concept. Check out http://www.buckabyte.com My hat goes off to Alex Tew, he certainly found a unique idea to sell ad space. I actually took his idea one step further… selling ad space by the BYTE! There are so many “pixel pushers” out there now that I needed to put a spin on the pixel advertising concept. Check out http://www.buckabyte.com

]]> Comment on OpenWRT on a Linksys WRT54G by Shane’s Blog » Blog Archive » DD-WRT, Another Alternative http://sbutler.com/blog/2005/12/openwrt-on-wrt54g/comment-page-1/#comment-199 Shane’s Blog » Blog Archive » DD-WRT, Another Alternative Mon, 02 Jan 2006 12:30:49 +0000 http://sbutler.com/blog/?p=75#comment-199 [...] sbutler.com Blog - Research - CV - Photos - Contact « OpenWRT on a Linksys WRT54G [...] [...] sbutler.com Blog – Research – CV – Photos – Contact « OpenWRT on a Linksys WRT54G [...]

]]> Comment on TV for Geeks by Shane http://sbutler.com/blog/2005/09/tv-for-geeks/comment-page-1/#comment-29 Shane Wed, 28 Sep 2005 03:39:55 +0000 http://sbutler.com/blog/?p=57#comment-29 Also http://www.filefarmer.com/techshows/ has links to lots of other shows. Also http://www.filefarmer.com/techshows/ has links to lots of other shows.

]]> Comment on TV for Geeks by jB: no - that's definitely not good enough http://sbutler.com/blog/2005/09/tv-for-geeks/comment-page-1/#comment-13 jB: no - that's definitely not good enough Fri, 09 Sep 2005 10:48:38 +0000 http://sbutler.com/blog/?p=57#comment-13 <strong>It's interview time</strong> Mark Stephens a.k.a. Robert X. Cringely started his weekly series of interviews named NerdTV over at http://www.pbs.org/cringely/nerdtv/ which includes talks with 'celebrities' like Sun Microsystem's Bill Joy (Sept. 20th), Apple's co-founder Steve ... It’s interview time

Mark Stephens a.k.a. Robert X. Cringely started his weekly series of interviews named NerdTV over at http://www.pbs.org/cringely/nerdtv/ which includes talks with ‘celebrities’ like Sun Microsystem’s Bill Joy (Sept. 20th), Apple’s co-founder Steve …

]]> Comment on The Joys of Gentoo by Shane http://sbutler.com/blog/2005/08/the-joys-of-gentoo/comment-page-1/#comment-12 Shane Wed, 07 Sep 2005 23:10:21 +0000 http://sbutler.com/blog/?p=50#comment-12 Yes I'd agree generally but in practice I have not always found it to be the case. My system was not working properly as a result of udev rules not being updated (because i wasn't using etc-update). Also, I have noticed some software, such as OpenVPN for example, seems to constantly move around their config files! Yes I’d agree generally but in practice I have not always found it to be the case. My system was not working properly as a result of udev rules not being updated (because i wasn’t using etc-update). Also, I have noticed some software, such as OpenVPN for example, seems to constantly move around their config files!

]]>