1. Deep Learning for Digital Text Analytics: Sentiment Analysis
- Author
-
U, Reshma, B, Barathi Ganesh H, Kale, Mandar, Mankame, Prachi, and Kulkarni, Gouri
- Subjects
Computer Science - Computation and Language ,68T50 - Abstract
In today's scenario, imagining a world without negativity is something very unrealistic, as bad NEWS spreads more virally than good ones. Though it seems impractical in real life, this could be implemented by building a system using Machine Learning and Natural Language Processing techniques in identifying the news datum with negative shade and filter them by taking only the news with positive shade (good news) to the end user. In this work, around two lakhs datum have been trained and tested using a combination of rule-based and data driven approaches. VADER along with a filtration method has been used as an annotating tool followed by statistical Machine Learning approach that have used Document Term Matrix (representation) and Support Vector Machine (classification). Deep Learning algorithms then came into picture to make this system reliable (Doc2Vec) which finally ended up with Convolutional Neural Network(CNN) that yielded better results than the other experimented modules. It showed up a training accuracy of 96%, while a test accuracy of (internal and external news datum) above 85% was obtained., Comment: 8 pages
- Published
- 2018