Wednesday, February 18, 2009

Old Thesis Ideas

At one point, I was going to do my thesis computer support for what I called "The Lunch Problem." The Lunch Problem consists of three questions that all must be answered at roughly the same time, because the answer to any one of them impacts the answers to the other two:

1. When are we going to lunch?
2. Where are we going for lunch?
3. Who is coming to lunch?

It's not as easy as it seems. Because if Janine is coming to lunch, I don't want to go. If we leave at 10:45, Brad can't make it. John had sushi last night. And so forth. It seemed like a hard groupware problem to me.

I'm reminded of this because I'm trying to schedule a dinner. I think we're on our third, and hopefully final date. We've also run into a few dietary restrictions on the way (and one date made it even worse.)

Wednesday, February 11, 2009

Valentine's Day Cards

I used to do Valentine's Day cards. I stopped doing them for a few years, a combination of inertia and lack of creativity. This year, I'm happy to say I did one, and I think it's one of the best ones yet. It's a short (7 page) comic book, about what happens when terrorists attack. There is a paper version available, but you can also get the PDF now, rather than waiting.

Friday, February 06, 2009

Naive Bayesian Classification

I was naive. I thought Naive Bayesian Classification would help. I coded up a rough-and-ready version of it. I gave it 30% of my data as training, then see what it did with the remaining 70%. I have 7 categories. So, if I used a really naive classifier (say, something like this), I'd get 14% correct answers. My classifier got 4%.

I think the classifier is failing because it's a really small vocabulary: about 400 words are used total, and there is pretty big overlap. I'm not sure if more data would help. The context has a highly regularized vocabulary (think air traffic control, or emergency dispatch).

But I really enjoyed the exercise.

Wednesday, February 04, 2009

Emphasis Quotes

I'm not a big fan of emphasis quotes. Most of the time it is just sad, but sometimes it reaches funny. This time, it was actively painful. It's not just the casual abuse of quotes, but the fact that they don't even match!