In this project a team implemented a Twitter bot (MLVbot), generating tweets from a Probabilistic Language Model.

These instructions will get you a copy of the project up and running on your local machine for development and testing purposes.

Start creating a conda enviroment.

$ conda create -n myEnv python=3.6
$ conda activate myEnv

Now within the virtual enviroment, install the following packages:

(myEnv) $ pip install TwitterAPI
(myEnv) $ conda install nltk
(myEnv) $ conda install tqdm

Download the data and the models here.

Extract the .zip file into the root of the project.

Now it should be as follow:

IceSCTB
├── LanguageModel.py
├── Twitter.py
├── TwitterBot.py
├── data
|   └── MIM
|   |    └── ...
|   └── ISL
|        └── ...
├── models
|   ├── LanguageModel3_ISL.pkl
|   └── LanguageModel4_ISLMIM.pkl

Open Twitter.py and specify your uniqe API keys.

class Twitter:
    __consumer_key = ''
    __consumer_secret = ''
    __access_token_key = ''
    __access_token_secret = ''
    __user_id_str = ''

(myEnv) ~/IceSCTB $ python TwitterBot.py

• Ásmundur Guðjónsson - MSc. Language Technology Student
• Egill Anton Hlöðversson - MSc. Language Technology Student

This project is licensed under the MIT License - see the LICENSE.md file for details

• NTLK
• TwitterAPI