**Context**

A user is describing a task to be performed by some company:

> I want to move 10 boxes (30x40x50cm) of books and clothes from London
> to Bristol next week. How much would that cost?

The application has find candidate companies that could do the task. In this case it would need to categorize the task as for *removal/transportation* companies.

**Problem**

I tried a number of online services for text categorization but results are discouraging. [uClassify][3] classified my text as "Home", "Games", and "Arts"; [Textimate.me][4] --- as "Science & Environment"; [Textwise][5] returned "Business/Consumer_Goods" and "Services/Clothing Arts/Design/Fashion".

The possible reasons for bad results:

 * task description is very short
 * not evident characteristics in the text to differentiate what is more important for the user: boxes, clothes or maybe moving them.
 * classifiers trained on other types of texts
 * classifiers trained with respect to a different taxonomy

**Potential improvements**

 * focus on verbs rather than nouns
 * harvest real corpus from online service market ("e-bay" for services), where people already categorized that
 * machine-learn based on that

Is this the right direction? What else I could do?

  [3]: http://www.uclassify.com/browse/uClassify/Topics
  [4]: http://textimate.me/try/text-categorization
  [5]: http://www.textwise.com