Mr.Zhou finally turns into Dr.Zhou (hooray!). For those curious minds, a draft of the dissertation can be found at PhD Dissertation. The official copy, like all other dissertation work, is archived with the Library of Congress.
I'm lucky to get invited together with 9 students to have lunch with Dick Costolo, Twitter CEO. He's quite friendly, maybe it's from his other career being a comedian. Some points:
I use Qualtrics to do advanced surveys that requires "drag and drop", "flow logic", etc. And then I use Amazon Mechanical Turk to recruit subjects for really cheap (I usually do $0.15/subject). This post is about how to make the two services work together.
It seems that all other existing approaches require subjects to copy a "confirmation code" here and there. But what I'll show you here is a very smooth process: Mturk workers would see the survey inside of Mturk, they work on it, submit, and get paid (see below):
I've been working on RecommenderAPI, a general purpose recommendation engine for Drupal, for a few years now. In the meantime, I'm doing my graduate work in recommender system, social computing, and machine learning. In this article, I'd like to discuss what to look forward to in the next major release of RecommenderAPI.
This is the notes/resources for the guest lecture I presented in SI 583, Feb. 16, 2012.
- A research project: “conversation co-mentions recommender”
- An open source project: Recommender API Drupal module
- A startup: DrupalAI.com
- Final thoughts on having a successful career in recommender system
Also see sample code of Apache Mahout programming in attachment.
The concluding remark of the the start-up class, ENGR 490, was quite thoughtful: A student's educational objective is to "learn to have a fun and satisfying life".
Things like "starting a successful company", "getting a degree", "becoming rich and famous", etc. are all possible, but not indispensable, means to that end -- "a fun and satisfying life". Never lose your direction on that!
I've always wanted to build a cutting edge recommender system for Drupal as good as what Amazon offers. Google Summer of Code 2009 gave me the first chance to attack this task, and I developed the Recommender API module and helper modules that provides recommendation service based on users browsing history, fivestar ratings, product purchasing history, etc. After 2 years of application in the real world, I received many users feedback concerning performance/scalability issue of the modules, which cannot be fixed under the current PHP implementation -see why here-.
To solve the performance issue, I think the best option is to outsource the complex recommendation computation to Apache Mahout instead of using my own PHP implementation. I have submitted another GSoC application for 2011 to work on this. Hope it will get accepted so that I can get this done.
The second part of my GSoC 2011 application is to build a framework so that 3rd party programs, such as Apache Mahout, can easily exchange data with Drupal for data-intensive computing, such as computing recommendations. More details is discussed in my GSoC 2011 application. I hope this would facilitate more innovations on data-intensive computation with Drupal using 3rd party script/programs.
If you like these ideas, please support my application at http://groups.drupal.org/node/137054.
Drupal rocks, and let's make it rock more :D
The Recommender API module and a few helper modules were released in 2009 as a result of my Google Summer of Code 2009 project for Drupal. Thanks to users of the modules, I have received many useful feedback and suggestions over the past 1+ year of application.
Below is the roadmap for the next release of Recommender API module, which will be completely re-written.
Add Views support so that there are more customized ways to show the recommendations. See more details at Issue #673786.
Support Drupal 7. See more details at Issue #910258.
Our research group at the University of Michigan has been working on the "related modules" block for Drupal.org for more than 2 years now. We have published 2 papers on this project so far:
1) Assessment of Conversation Co-mentions as a Resource for Software Module Recommendation. Will be presented at ACM Recommender System Conference'09
2) Conversation Pivots and Double Pivots. Presented at ACM Computer Human Interaction Conference'08