Looping predictive method to improve accuracy of a machine learning model

The topic of this project is an analysis of drug-related tweets. The goal is to build a Machine Learning Model that can distinguish between tweets that indicate drug abuse and other tweets that also contain the name of a drug but do not describe abuse. Drugs can be illegal, such as heroin, or legal drugs with a potential of abuse, such as painkillers. However, building a good Machine Learning Model requires a large amount of training data. For each training tweet, a human expert has determined whether it indicates drug abuse or not. This is difficult work for humans. In this project a new “Looping Predictive Method” was developed that allows generating large training datasets from a small seed set of tweets by repeatedly adding machine-labeled tweets to the human-labeled tweets. With this method, an accuracy improvement of 15.4% was achieved from an initial set of 1,075 tweets, by expanding the training set to 29,908 tweets.

Name thesis:degree_name

Master of Science in Computer Science - (M.S.)

Discipline thesis:degree_discipline

Computer Science

Year

2017

Author dc:creator

• Pogili, Subramanyam Reddy

Contributors dc:contributor

• James Geller
• Soon Ae Chun
• Hai Nhat Phan

• Machine learning
• Looping predictive method
• Computer Sciences

Repository record dc:identifier

https://digitalcommons.njit.edu/theses/45

OAI identifier oai:identifier

oai:digitalcommons.njit.edu:theses-1044