A Computational Approach to Automatic Prediction of Drunk-Texting

8 years 14 days ago

Download www.cse.iitb.ac.in

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.

Aditya Joshi, Abhijit Mishra, Balamurali A. R, Pus

Real-time Traffic

ACL 2015 | Computational Linguistics |

claim paper

» Automatic sense prediction for implicit discourse relations in text

» A matrix alignment approach for link prediction

» A Language for Describing Predictors and Its Application to Automatic Synthesis

» Optimizing Performance of Automatic Training Phase for Application Performance Prediction ...

» Automatic Image Colorization Via Multimodal Predictions

» Gene prediction using the SelfOrganizing Map automatic generation of multiple gene models

» Predictive automatic relevance determination by expectation propagation

» Predictive Reachability Using a SampleBased Approach

» A Mathematical Programming Formulation for Sparse Collaborative Computer Aided Diagnosis

Post Info
More Details (n/a)

Added	13 Apr 2016
Updated	13 Apr 2016
Type	Journal
Year	2015
Where	ACL
Authors	Aditya Joshi, Abhijit Mishra, Balamurali A. R, Pushpak Bhattacharyya, Mark James Carman

Comments (0)

Sciweavers

A Computational Approach to Automatic Prediction of Drunk-Texting

ACL 2015 | Computational Linguistics |

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers