A picture is worth many emotions too

A picture is worth many emotions too
x
Highlights

Images on Twitter, Facebook or other social media can convey a lot more than a sentence might and will often provoke emotions in the user, a fascinating research suggests. To prove this, Jiebo Luo, professor of computer science at University of Rochester in Britain, in collaboration with researchers at Adobe Research has come up with a more accurate way to train computers to be able to digest data that comes in the form of images.

London: Images on Twitter, Facebook or other social media can convey a lot more than a sentence might and will often provoke emotions in the user, a fascinating research suggests. To prove this, Jiebo Luo, professor of computer science at University of Rochester in Britain, in collaboration with researchers at Adobe Research has come up with a more accurate way to train computers to be able to digest data that comes in the form of images.

They describe what they refer to as a progressive training deep convolutional neural network (CNN). The trained computer can then be used to determine what sentiments these images are likely to elicit. "This information could be useful for things as diverse as measuring economic indicators or predicting elections," Luo added.

In social media, sentiment analysis is more complicated because many people express themselves using images and videos, which are more difficult for a computer to understand. The researchers treated the task of extracting sentiments from images as an image classification problem.

This means that somehow each picture needs to be analysed and labels applied to it. To begin the training process, Luo and his collaborators used a huge number of Flickr images that have been loosely labeled by a machine algorithm with specific sentiments.

This gave the computer a starting point to begin understanding what some images could convey. The key step of the training process came next, when they discarded any images for which the sentiment or sentiments with which they have been labeled might not be true.

So they use only the "better" labeled images for further training in a progressively improving manner within the framework of the powerful convolutional neural network. The team found that this extra step significantly improved the accuracy of the sentiments with which each picture was labeled. They also adapted this sentiment analysis engine with some images extracted from Twitter.

Show Full Article
Print Article
Next Story
More Stories
ADVERTISEMENT
ADVERTISEMENTS