DeepAI AI Chat
Log In Sign Up

A Computational Approach to Automatic Prediction of Drunk Texting

by   Aditya Joshi, et al.
Monash University
IIT Bombay

Alcohol abuse may lead to unsociable behavior such as crime, drunk driving, or privacy leaks. We introduce automatic drunk-texting prediction as the task of identifying whether a text was written when under the influence of alcohol. We experiment with tweets labeled using hashtags as distant supervision. Our classifiers use a set of N-gram and stylistic features to detect drunk tweets. Our observations present the first quantitative evidence that text contains signals that can be exploited to detect drunk-texting.


page 1

page 2

page 3

page 4


Stance Detection on Tweets: An SVM-based Approach

Stance detection is a subproblem of sentiment analysis where the stance ...

Racial Bias in Hate Speech and Abusive Language Detection Datasets

Technologies for abusive language detection are being developed and appl...

Is This a Joke? Detecting Humor in Spanish Tweets

While humor has been historically studied from a psychological, cognitiv...

MITRE at SemEval-2016 Task 6: Transfer Learning for Stance Detection

We describe MITRE's submission to the SemEval-2016 Task 6, Detecting Sta...

Stance and Sentiment in Tweets

We can often detect from a person's utterances whether he/she is in favo...

Vector Space Model as Cognitive Space for Text Classification

In this era of digitization, knowing the user's sociolect aspects have b...

DialectGram: Automatic Detection of Dialectal Variation at Multiple Geographic Resolutions

We propose DialectGram, a method to detect dialectical variation across ...