Carlita is a Twitter bot capable of chat with people via direct messages or mentions.
Carlita is developed using Python and the libraries python-twitter and halpy.
The “conversation simulator” algorithm that MegaHAL uses was created by Jason Hutchens. MegaHAL is able to construct a model of lenguage based on the evidence it encounters while conversing with the user. The input received from the user is parsed into an alternating sequence of words and non-words, where a word is a series of alphanumeric characters and a non-word is a series of other characters. If the user has a habit of putting a double space after a full stop, for instance, MegaHAL will do just the same.
In order to reply it utilizes a Markov model.
Things that carlita is doing:
- Receive and reply to direct messages. Also, learn about them.
- Receive and reply to tweet mentions. Also, learn about them.
- Follow new people that is following it.
- Once in a while, reply back to a random tweet from one of its teachers.
- Once in a while follow new people mentioned on its TL.
- Learn from people on this list.
The source code is available on Github!