Sentiment Classification using Images and Label Embeddings
Computation and Language
2017-12-08 v1 Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
Machine Learning
Abstract
In this project we analysed how much semantic information images carry, and how much value image data can add to sentiment analysis of the text associated with the images. To better understand the contribution from images, we compared models which only made use of image data, models which only made use of text data, and models which combined both data types. We also analysed if this approach could help sentiment classifiers generalize to unknown sentiments.
Cite
@article{arxiv.1712.00725,
title = {Sentiment Classification using Images and Label Embeddings},
author = {Laura Graesser and Abhinav Gupta and Lakshay Sharma and Evelina Bakhturina},
journal= {arXiv preprint arXiv:1712.00725},
year = {2017}
}
Comments
13 pages, 3 figures, 9 tables. Technical report for Statistical Natural Language Processing Project (NYU CS - Fall 2016)