The science behind Mollom: humans entering CAPTCHAs

Mollom is based on the idea that if we are not 100% confident about the classification of your content in the ham or spam group, we present a CAPTCHA to the user. This improves the classifier's performance and eliminates the need of a moderation queue. And because these CAPTCHAs are only shown in the "gray zone", only a very limited number of real users have to fill in a CAPTCHA, while most of the CAPTCHAs are actually shown to spam-bots.

Here is actual data from the Mollom server showing the number of requests of the different types:

Humans that had to enter a CAPTCHA

This plot shows Mollom's server statistics on any particular day, showing the ham messages in green, the spam messages in orange, and the unsure messages (where a CAPTCHA was shown) in gray. Also notice the thin brown line just on top of the ham region (look close, it is barely visible :), which denotes the human users that had to fill in a CAPTCHA.

In numbers it boils down to this: on average 80% of all content is spam of which about 40% is shown a CAPTCHA and 60% is directly blocked; from all the user generated ham content, which is the remaining 20% of the whole, only 5% (of this 20%) was seen as unsure and had to fill in a CAPTCHA to get accepted. Not too bad... And thanks to both the image and audio CAPTCHAs, there are no accessibility issues.

Mollom t-shirts

Ben and I printed some Mollom t-shirts and we're going to ship some to people that contributed a Mollom plugin or that took advantage of the Mollom API in new or clever ways.

We've just sent some t-shirts to Mattias (WordPress plugin), Tijs (PHP5 class), Markus (Joomla extension), Jan (Ruby library), Andy (Python library), Wim (summer intern) and more. Send us an e-mail if you integrated Mollom in your favorite tool or service!

We also set aside some t-shirts for people that write the best Mollom reviews or otherwise help us spread the word in new, clever or interesting ways ...

Pricing model and payment system in the works

As you might have read, Wim Leers (long term Drupal contributor) is a summer intern at Mollom. After 6 months of public beta testing, and after having blocked more than 5 million spam messages for 2,500 users, we're getting ready to open our doors for business. While Ben and I continue to focus on the spam classifiers and the various Mollom plugins, Wim is helping us to get ready for launch by implementing a payment system and more.

More details about our pricing structure will follow shortly, but as promised, Mollom will remain freely available for both commercial and non-commercial use. The free version of Mollom will be limited in volume and features though. We want as many people to benefit from Mollom as possible so our goal is to make Mollom free for at least 95% of our install base. In other words, the free version of Mollom will go well beyond meeting the needs of the average site owner. Like so, we hope to make a significant contribution to fighting the spam problem online. More details shortly.

Mollom for Joomla

Right on the heals of the WordPress plugin for Mollom, Markus Bopp got his Joomla extension for Mollom accepted into the official Joomla Extension Directory. It is great to see Mollom being adopted by more and more platforms. Thanks Markus!

Mollom for Wordpress