
This is DGR Model3 Serial number 002.
The bot posts from this account:
http://twitter.com/DGR_m3_02
DGR m3 s2 is a public test bot.
The DGR parameters are:
# All fields are compulsory
# The twitter user name and password
twitter_username: DGR m3_02
twitter_password:
# Doesn't change. make sure it has imageid and feeling an a limit of >= 20
wff_search: http://api.wefeelfine.org:8080/ShowFeelings?display=xml&returnfields=imageid,feeling&limit=50&gender=1&born=1984&city=london
# Emotional states
emotion_keywords: {
happy: [beer, girls, bike, winning],
sad: [broken, crash, fallen, smashed, bent],
silly: [lads, chasing, running, tricks],
alone: [practice, cleaning, cooking, dreaming]
}
# Times of day (after given times), 24hour clock, 00..23
time_keywords: {
07: [breakfast, eggs, tea, The Sun],
11: [practice, biking, bmx, wheels],
19: [dinner, beer, mates, pub, peas],
23: [sleep, tv, movie]
}
# Times of day for Saturday & Sunday (after given times), 24hour clock, 00..23
weekend_time_keywords: {
09: [practice, biking, bmx, wheels],
19: [dinner, beer, mates, pub, peas],
23: [sleep, tv, movie]
}
# Words to fall back on if nothing else matches, or to add randomly
character_keywords: [crazy, brave, champion, dreamer, bmx]
Hello.
ReplyDeleteI was retweeted by DGR_m3_02 which chose a half-edited tweet I'd posted in error and later deleted.
I RTweet the Tweets that statisically make sense to me.
If it statistically makes sense to your bot but verbally makes no sense to humans, you need to work on the bot.
The characters relate themselves to other users of the internet, and try to reveal themselves through other users related posts.
I understand the words but have no idea what that sentence means.
As such, the characters you design evolve into a personality.
Surely the algorithms YOU design evolve into more consistent retweeters - the point of which remains a mystery to me?
Hi Andrew, thanks for taking the time to leave a comment.
ReplyDeleteIt's not a conforming character design that interests the project, quite the opposite for now. The objective is to see narratives develop, not predefine what they should be.
By watching what a sibling picks up on Twitter - and when - starts to tell a story about that sibling. The algorithm, as such, is based upon filtering what is happening on the web, rather than calculating an answer. Thus the sibling is telling it's story through the conversations of others.
Let me know if you get RT'ed again. Unlikely, but I'm keen to know if it does happen.