Hi Alex,
thanks for your interest :-)
You can ignore the comments boxes, those are only there if someone wants
to provide a better answer for the users (when the final version will
launch).
For my evaluation I only consider the ratings and some comments about
the approach in general users gave in forums / mailing lists.
Considering the rating you can give as many stars as you think the Q/A
is valuable to the reader. If it's a irrelevant question, low rating. If
the answer is not helpful, especially low rating :-)
Best regards,
Stefan
Am 08.03.2011 22:03, schrieb Alexander Klimetschek:
Interesting :-)
But from a first glance, I am not sure how to evaluate the answers. Should
I rate? Write a comment? Are comments only for correcting the answer (and
thus not directly useful for your quality statistics)? What if an answer
is wrong or a non-answering email from the mailing list thread was used -
rate it with 1 star?
Regards,
Alex
On 08.03.11 21:54, "Stefan Henß"<[email protected]> wrote:
Hi everybody,
I'm currently doing research for my bachelor thesis on how to
automatically extract FAQs from unstructured data.
For this I've built a system automatically performing the following:
- Load thousands of conversations from forums and mailing lists (don't
mind the categories there, don't discriminate between sources).
- Build new categorization solely based on the conversation's texts (by
clustering).
- Pick the best modelled categories as basis for one FAQ each.
- For each question (first entry in a thread) find the best reply from
its answers.
- Select the most relevant and well formatted question/answer-pairs for
each FAQ.
For the evaluation I'm interested in expert's perceptions of the
results, e.g. if the questions are relevant, correctly answered, etc.
Also as I'll release a paper about the approach I'd be happy if you
could rate one or two questions (stars on the details pages) so I'd have
some statistics to present.
Here's the direct link to the Jackrabbit FAQs:
http://faqcluster.com/jackrabbit-node-jcr-repository-apache
(There are some other interesting FAQs as well at http://faqcluster.com/)
Thanks for your help
Stefan
