Data Buzzword Trash Bot

 

The Data Profession BuzzWord Trash Bot takes all the most popular data profession buzzwords and smashes them together multiple times a day to create tweets that could be written by anyone not initiated into the fold of the profession to appear as though they know what they’re talking about. It is meant to be satyrical and to shine a light on the meaninglessness of so many of the words used to describe data and what data scientists do.

This bot was written in R, and the code can be found below.

Be sure to keep up on the bots activities daily by heading over to the Data Couture Twitter page.

 

Check out the troubled waters you’ve got to cross to get the most of your transaction data on Episode 22: Transaction Data Difficulties https://youtu.be/IxGP_6a_P0Y

#vlog #transactions #machinelearning

Check out why transaction data is so tricky to wrangle on today’s episode of the Data Couture Podcast! #podcast #data #wrangling

Transaction data is key to unlocking vast troves of information about customer habits. Check out the latest Data Driven vlog at https://youtu.be/Hg0kvyepjlY to find out more!

#transaction #data #cx #customerexperience #vlog

Autoregressed Automated Data Models #DataBuzzWordBot #DataCouture #Bot #BuzzWordTrash #Buzzy #DataProfessionBuzzwords

Lab grown diamonds are coming to a ring, necklace, or earrings near you. Find out why they are the solution to deeply unethical and ecologically problematic natural stones! #data #diamonds #podcast

Load More...

 

 

R Code (feel free to update whichever aspect(s) and launch it on your own Twitter page):

library(ROAuth)
library(twitteR)

# text strings for random nouns, adjectives, and hashtags for the twitter bot

adjectives1 <- c("Accurate","Organized","Optimized","Autoregressed","Backpropogating","Bagging","Bayesian","Binary","Binomial","Boosting","Bootstrapping","Categorical","Classifying","Clustering","Confident","Converging","Correlated","Similar","Covariant","Validated","Mined","Transformed","Automated","Supervised","Unsupervised","Deep","Descriptive","Dummy","Early","Evaluated","Analyzed","Reduced","Selected","Gated","Go","Graded","Hidden","Hierarchical","Holdout","Inferential","Iterated","Labeled","Lassoed","Logistic","Mapped","Mixed","Simulated","Multi-","Normalized","Encoded","Overfit","Quartile","Regularized","Residual","Semi-","Standardized","Tokenized","Underfit","Zookeeping")

adjectives2<- c("Accurate","Organized","Optimized","Autoregressed","Backpropogating","Bagging","Bayesian","Binary","Binomial","Boosting","Bootstrapping","Categorical","Classifying","Clustering","Confident","Converging","Correlated","Similar","Covariant","Validated","Mined","Transformed","Automated","Supervised","Unsupervised","Deep","Descriptive","Dummy","Early","Evaluated","Analyzed","Reduced","Selected","Gated","Go","Graded","Hidden","Hierarchical","Holdout","Inferential","Iterated","Labeled","Lassoed","Logistic","Mapped","Mixed","Simulated","Multi-","Normalized","Encoded","Overfit","Quartile","Regularized","Residual","Semi-","Standardized","Tokenized","Underfit","Zookeeping")

nouns <- c("Business Intelligence","Data Engineering","Decisions Sciences","Artificial Intelligence","Machine Learning","Predictive Analytics","Supervised Learning","Classification","Cross Validation","Clustering","Deep Learning","Linear Regression","A/B Testing","Hypothesis Testing","Statistical Power","Standard Error","Causal Interference","Exploratory Data Analysis","Data Visualization","R","Python","MatLab","SQL","SAS","ETL","GitHub","Data Models","Data Warehouse","ML","AI","PA","Regression","BI","PowerBI","Tableau","Bot","Pie Chart","Big Data","Computer Vision","Dataset","Dataframe","Dashboard","Variable")

hashtags <- c("#Buzzy","#DataProfessionBuzzwords","#DataBuzzWordBot","#BuzzWordTrash","#Bot","#Annoying")


# setting up twitter authentication

api_key <- "Insert_yours_here"
api_secret <- "Insert_yours_here"
access_token <- "Insert_yours_here"
access_token_secret <- "Insert_yours_here"

setup_twitter_oauth(api_key,api_secret,access_token,access_token_secret)


# generating the tweets

numb_adjectives1 <- sample(seq(0,2,1),size=1)
numb_adjectives2 <- sample(seq(0,1,1),size=1)
numb_nouns <- sample(seq(1,2,1),size=1)


# sampling the numbers for the tweets

# randomly choose your first adjectives 
random_adjectives1 <- NULL 
for(i in 1:numb_adjectives1){
random_adjectives1 <- c(random_adjectives1,sample(adjectives1,size=1))
}

# randomly choose your second adjectives 
random_adjectives2 <- NULL 
for(i in 1:numb_adjectives2){
random_adjectives2 <- c(random_adjectives2,sample(adjectives2,size=1))
}

# randomly choose your nouns
random_nouns <- NULL 
for(i in 1:numb_nouns){
random_nouns <- c(random_nouns,sample(nouns,size=1))
}

# randomly choose a hashtag
random_hashtag <- sample(hashtags,size=6)


# removing duplicates from nouns
if(length(random_nouns)==2){
if(random_nouns[1]==random_nouns[2]){
random_nouns <- random_nouns[1]
}
}

# removing duplicates from adjectives
if(length(random_adjectives2)==2){
if(random_adjectives1[1]==random_adjectives2[2]){
random_adjectives1 <- random_adjectives2[1]
}
}


# Combining all elements into a single string
temp <- c(random_adjectives1,random_adjectives2,random_nouns,random_hashtag)
tweettxt <- paste(temp,collapse=" ")
tweettxt


# SEND THE TWEET
tweet(tweettxt)