Computers can be platforms for software agents that “acts for a user or other program in a relationship of agency.” More specifically Chatter Bots are ones that “convincingly simulate how a human would behave as a conversational partner.”

Marrying responses of software agents with greater amounts of artificial intelligence (mining information that is collected from millions of people) does offer potential for helpful convenience, aka Siri, Alexa.

Are bots all bad? good? useful? dangerous? As described by Mark Sample:

Bots are small automated programs that index websites, edit Wikipedia entries, spam users, scrape data from pages, launch denial of service attacks, and other assorted activities, both mundane and nefarious. On Twitter bots are mostly spam, but occasionally, they’re creative endeavors

This week we explore twitter bots – are they mundane or nefarious? how do we know who is a bot and who is not? Are we bots?

This is our first segment into the Electronic Literature segment of netnarr, so we are looking at how the conversational nature of bots might be considered in the scope of narrative.

Opener Activity: Talk to Eliza

Engage in conversation with an online therapist named Eliza:

ELIZA is an early natural language processing computer program created from 1964 to 1966 at the MIT Artificial Intelligence Laboratory by Joseph Weizenbaum.

Created to demonstrate the superficiality of communication between humans and machines, Eliza simulated conversation by using a ‘pattern matching’ and substitution methodology that gave users an illusion of understanding on the part of the program, but had no built in framework for contextualizing events. Directives on how to interact were provided by ‘scripts’, written originally in MAD-Slip, which allowed ELIZA to process user inputs and engage in discourse following the rules and directions of the script.

The most famous script, DOCTOR, simulated a Rogerian psychotherapist and used rules, dictated in the script, to respond with non-directional questions to user inputs. As such, ELIZA was one of the first chatterbots, but was also regarded as one of the first programs capable of passing the Turing Test.

Twitter Bots

From the New Yorker Rise of the Twitter Bots in 2013, twitter bots are described as amusing, creative:

Twitter bots are, essentially, computer programs that tweet of their own accord. While people access Twitter through its Web site and other clients, bots connect directly to the Twitter mainline, parsing the information in real time and posting at will; it’s a code-to-code connection, made possible by Twitter’s wide-open application programming interface, or A.P.I. The bots, whose DNA can be written in nearly any modern programming language, live on cloud servers, which never go dark and grow cheaper by the day. This broad accessibility, magnified by Twitter’s laudably permissive stance on the creation of new accounts, has created fertile ground for such automated shenanigans, like proving our susceptibility to certain typos and making Newt Gingrich seem popular.

If you use Twitter, you’ve probably met your share of one kind of Twitter bot, spambots. They have nonsensical burner handles, and blast messages like “truly $$$ work opportunities” at anyone who so much as mentions an iPad. “Click this link,” they beckon, “so I might seize your identity and use it to hawk Panama’s finest generic Ritalin.” Hardly a compelling sales pitch, but at least it explains why they’re always awake.

Of greater interest—the signal to the spammers’ noise—is the growing population of creative bots that consume, remix, and contribute to the broader culture churn of the Internet.

In 2018 we are now considering that twitter bots might be part of organized efforts to influence public thinking, that they might fool you into thinking they are real people. Just this week a Pew Research Report suggests that more than two thirds of links tweeted are generated by bots; “They’re mostly bland.”

In Nernarr we are not making a conclusive stance (feel free to do so in your own blog!) but more to explore what it means for constructing creative expression in a networked environment.

“I think that Twitterbots are the most important development in contemporary poetry. Twitterbots are combining avant-garde conceptual techniques, ethico-political intervention and high expressive potential, and they’re doing so in a popular social space: they are a popular and populist form of poetry. Twitterbots are published for free, and the culture of making them is an open, sharing culture: Twitterbots push poetic surprise into your social space, and their authors are encouraging and supporting you to join in the making.”
https://harrygiles.org/2016/04/06/some-strategies-of-bot-poetics/

Last year we had a studio visit with Electronic Literature explore Leonard Flores who suggested “Following twitter bots is like hanging art in your twitter stream”. Listen to the way he describes @regrettoegret:

How can we learn more? Follow some twitter bots!

Lists are fine, but why not use bots to find interesting bots? Based on a Kairos interview with Leonard Flores on “Hot Bots” follow @KairosHotBots to get recommendations on hundreds of twitter bots.

But better yet, this bot can offer suggestions:

Send your request to this bot, and follow the accounts it suggests.

Who Are You Calling a Bot?

Can you tell real poetry from bot generated poetry? Test your ability with the five rounds from the Bot or Not test:

Tweet out your results, how many out of five can you determine bot or not?

Can we determine who is a bot or not? Give the Botometer a try:

Is @netnarr a bot?

Run the analysis on your own account first. Take a screenshot of your results (you will need this for your weekly summary). Next test it on people you know, celebrities, the bots you followed from above. Does it seem accurate? Can you trust it’s analysis?

The Netnarr Botversation

Pixabay image by geralt shared into the public domain using Creative Commons CC0

Our activity that starts in class and extends the rest of the week will be to create an ongoing conversation including twitter bots you will create that will tweet out of your own account. Your bot will mention others in netnarr, and you will also augment with your own human authored tweets and replies.

The intent of this activity is to explore the influence we can have in social media by both human and automated means, plus what can happen when we are communicating online, but perhaps not sure if we are responding to a person or a software agent.

Each Kean students will receive from @cogdog a direct message containing a position on an issue of Digital Life we have already discussed in class. Your mission is to engage as many as others in a conversation and see how you can influence them. Do not reveal your mission to anyone.

Note: Open participants are welcome to design their own secret mission to promote; it woks better if you pick a position you may not full buy into!

We will use Zach Whalen’s Google Spreadhseet Twitter bot method — those who were in NetNarr in 2017 recall we created bots for different twitter accounts; for this year we are setting one up to tweet out of our regular account (thus it gets mixed in with our hand written ones).

  1. Follow Zach’s steps starting at General Setup Instructions by clicking the link to make a copy of his spreadsheet in your own Google Drive
  2. Skip his step 1 since you already have a twitter account (make sure you are logged into it). To create the bot you will need to make sure you have a mobile phone number associated with your account
  3. Follow the directions in Zach’s Step 2 to set up a new Twitter app at http://apps.twitter.com/ (this creates an ability for the spreadsheet to tweet out under your account). When the form asks for a Website, you can enter your blog URL.
  4. Go back to the new spreadsheet you created and follow the steps there to set up the API keys and app settings.
  5. For Step 6 in the spreadsheet, use the menu option for Select From Columns

Now let’s pause here. That’s the setup. What we want to think about is a structure for the tweets that our sheet will send that has a pattern to allow use of multiple words randomly chosen for parts of the tweet. we also want to make sure one of those random things is the twitter names of everyone in our class, so we mention people or invite them to respond.

The minimum requirement is that your tweets should mentioned everyone in class:

@nessacastrii
@JasmineDA18
@BlaqueBeauty_30
@tiffsanto
@mrsjayj
@rissacandiloro
@stryii
@Justinsightfuls
@helterskelliter
@Kmarzinsky
@eniasebiomo
@cogdog

You may choose to include some of our active open participants:

@dogtrax
@wentale
@MiaZamoraPhD
@grammasheri
@NomadWarMachine
@MCorbettWilson
@AwoJolt
@netarr

And all your tweets sent by this bot should include the #netnarr hashtag.

Let’s say my mission is to advocate for the pure artistic value of bots. My sentence structure might be something like:

[opening conjecture] that twitter bots are [adjective] for [some kind of action]. I [verb] [twitter handle] to [some kind of response] for #netnarr

Try to come up with a pattern that sounds conversational.

Everything in brackets will have multiple word our spreadsheet will use. We return there, and delete everything in the Select From Columns sheet to place our own content. If there is just one line, then that is the text that is used. The more options you have in a column, the more random it will seem.

I might set up my sheets to look like this:

setting up the select from columns data

We can run some tests before we send our bot tweeting. Go to the Preview tab. Select Generate Preview from the Bot menu to see how your tweets will look. Check to make sure there are no odd syntaxes or awkward grammar.

If it looks okay, select Send a Test Tweet from the Bot menu. Check your own tweet to ensure your bot is posting.

Return to the Setup tab of the spreadsheet and under Step 8 select an interval for your tweets to be sent– we suggest 4, 6 or 8 hours so you are not annoying.

Finally set it in motion, by select Start posting tweets from the Bot menu. Note that you can update, edit the columns at any time.

Now your bot is tweeting as you. For the rest of the week engage in the Botversation:

  • Respond to all tweets that mention you.
  • Follow up your own tweets, or include in between the bot tweeted messages, your own manually authored tweets to add links, media, commentary to further support for position.
  • Be nice. Do not insult or berate others. You assert your position by posytive tweets, not negative.
  • Stop at any time. If for any reason you do not want to engage, just turn off your bot, and say “I’m done”.

Our goal here is not to win, but explore a space where some of the conversations are generated by bots and some are not. Your goal is to get people to respond and contribute to your position.

We all have opinions about the world. And we want to be able to assert them for the things we care strongly about — can twitter do this? Can bots help? Or do they make things less clear?

Another bot will reveal everyone’s mission by 6:00 pm Sunday EST- see how much conversation you can create and contribute to, and see if you can determine which tweets by others are bots and which are not.

Give this Checklist to your bot

Pixabay image by TheDigitalArtist shared into the public domain using Creative Commons CC0

Week 12 Checklist


Featured Image: Schylling – Replica Atomic Robot Man – Four Mechanic Angels of Destruction Wikimedia Commons image by D.J. Shin licensed under a Creative Commons CC BY-SA license

Alan Levine
Alan Levine feels weird writing about himself in the third person. A 1990s pioneer on the web and early proponent of blogging, he shares his ideas at CogDogBlog.com. His interests include web storytelling (#ds106 #4life), mocking MOOCs, daily photography, bending WordPress, and randomly dipping into the infinite river of the internet. He and his dog enjoy the peace of a little home in Strawberry, Arizona.

Leave a Reply

Your email address will not be published. Required fields are marked *