Lightening Workshop: Gender mirroring bots & Turing test: Difference between revisions

From Hackers & Designers
No edit summary
No edit summary
Line 34: Line 34:


Technical Details:
The following steps should be used if you would like to run the bots as the Hackers & Designers terminals did during the workshop.
Ensure you have [https://www.python.org/ Python] 2.7.* installed.
Ensure you have Python's package manager [https://pip.pypa.io/en/stable/installing/ pip] installed.
Start by install Gunther Cox's Chatterbot via pip.  This will ensure you get most of the dependencies.
  $ sudo pip install chatterbot
Optionally you can install python Levenshtein if you don't want a warning message while running the bots.
  $ pip install python-levenshtein
The bots do use a bit of Python's natural language package (nltk), so download the following database.
  $ python -m textblob.download_corpora
Ensure you have [https://git-scm.com/ git] installed to grab the code from Github.
Clone the Chatterbot repository from Github.
  $ git clone git@github.com:hackersanddesigners/ChatterBot.git
Run the bot.
  $ cd Chatterbot
  $ python bot.py
After training the bot, we "turned off" learning by commenting out a line of code.  Open the file with your favourite text editor, in the workshop we used nano.
  $ nano chatterbot/chatterbot.py
The line is around line number 207, and looks like this:
  self.learn_response(statement)
In python a comment is "#", so the line should look like:
  #self.learn_response(statement)
Save the file.  In nano Ctrl+O, then Ctrl+X.
Run the bot again:
  $ python bot.py

Revision as of 09:39, 17 November 2016

Template:Events


Lightening workshop and artist talk:


In the context of Rendering Realities (Big Brother Awards exhibition) of the Big Brother Awards Hackers & Designers invites the audience to discuss and experience their gender mirrored by chat bots. The bots will be trained collectively and on the spot. In order to compose new strategies to overcome online discrimination, that go beyond using initials only as female, H&D proposes to collectively comprehend the controversy, while training different bots and analyse them using the Turing test.

The Smell of Data is a scent developed to instinctively alert of data leaks on networked personal devices. The sense of smell helped early humans to survive. But now that our hunting and gathering has moved to the digital environment, our noses can no longer warn us of the lurking dangers in the online wilderness. Leanne will present her work, the series of prototypes it took to get to the final product, and her process and inspiration on giving a scent to data.

Doors open at 19:00 and the event will start at 19:30.

With the Smell of Data by Leanne Wijnsma and curator of the exhibition during the Big Brother Awards Magarita Osipian.


About the exhibition:

Rendering Realities opens on Monday November 14 at 19:30, coinciding with the Big Brother Awards at Stadsschouwburg Amsterdam. It is open on Tuesday November 15 and Wednesday November 16 from 12:00 to 18:00, with a workshop and artist talk on the evening of the 16th from 19:30 to 21:30 in collaboration with Hackers & Designers. Free entrance.

The exhibition is curated by Margarita Osipian

More information here: www.facebook.com/events/1581886842120178/


Technical Details:

The following steps should be used if you would like to run the bots as the Hackers & Designers terminals did during the workshop.

Ensure you have Python 2.7.* installed.

Ensure you have Python's package manager pip installed.

Start by install Gunther Cox's Chatterbot via pip. This will ensure you get most of the dependencies.

  $ sudo pip install chatterbot

Optionally you can install python Levenshtein if you don't want a warning message while running the bots.

  $ pip install python-levenshtein

The bots do use a bit of Python's natural language package (nltk), so download the following database.

  $ python -m textblob.download_corpora

Ensure you have git installed to grab the code from Github.

Clone the Chatterbot repository from Github.

  $ git clone git@github.com:hackersanddesigners/ChatterBot.git

Run the bot.

  $ cd Chatterbot
  $ python bot.py

After training the bot, we "turned off" learning by commenting out a line of code. Open the file with your favourite text editor, in the workshop we used nano.

  $ nano chatterbot/chatterbot.py

The line is around line number 207, and looks like this:

  self.learn_response(statement)

In python a comment is "#", so the line should look like:

  #self.learn_response(statement)

Save the file. In nano Ctrl+O, then Ctrl+X.

Run the bot again:

  $ python bot.py