Benchmark Custom Text

Choose a dataset

For training the models, the dataset provides 7920 labeled tweets. The dataset is provided in the form of a csv file with each line storing a tweet id, its label and the tweet.

Overview
Training dataset
Labels
Docs
positive#fingerprint #Pregnancy Test https://goo.gl/h1MfQV #android #apps #beautiful #cute #health #igers #iphoneonly #iphonesia #iphone
positiveFinally a transparant silicon case ^^ Thanks to my uncle :) #yay #Sony #Xperia #S #sonyexperias… http://instagram.com/p/YGEt5JC6JM/
positiveWe love this! Would you go? #talk #makememories #unplug #relax #iphone #smartphone #wifi #connect... http://fb.me/6N3LsUpCu
positiveI'm wired I know I'm George I was made that way ;) #iphone #cute #daventry #home http://instagr.am/p/Li_5_ujS4k/
negativeWhat amazing service! Apple won't even talk to me about a question I have unless I pay them $19.95 for their stupid support!
negativeiPhone software update fucked up my phone big time Stupid iPhones
positiveHappy for us .. #instapic #instadaily #us #sony #xperia #xperiaZ https://instagram.com/p/z9qGfWlvj7/
positiveNew Type C charger cable #UK http://www.ebay.co.uk/itm/-/112598674021 … #bay #Amazon #etsy New Year #Rob Cross #Toby Young #EVEMUN #McMafia #Taylor #SPECTRE 2018 #NewYear #Starting 2018 #recipes #technology #SamsungGalaxyS9 #iPhoneX pic.twitter.com/PjIwq59WtC
Prediction dataset
Metrics
Google Cloud
AWS
Accuracy0.62737260.8671329
Precision0.27476040.6853933
Recall0.37068970.7887931
Confusion matrix
AWS
PositiveNegative
Positive68584
Negative49183
Google Cloud
PositiveNegative
Positive542227
Negative14686