Reading Emotions

The goal of this project is to better understand the emotional complexity of literary characters and make this data openly available to the public. Characters are the scaffolding of great storytelling. This Zooniverse project will allow us to crowdsource data to train AI models to better understand the emotions of characters at significantly larger scales than researchers have ever been able to in the past. Our guiding research question is: why are imaginary stories so important to us?

In the nineteenth-century heyday of the novel, there were over 1.5 million literary characters invented just in English alone. Today, with the continued growth of literary markets around the world and the explosion of creative writing on the internet through fan communities, that number is orders of magnitude higher.

How on earth can we possibly understand all of this creativity?

This is where you, the reader, come in. We need your help to build better, more transparent AI models to understand human storytelling. To be clear: our goal is not to build AI to generate stories or create smarter chatbots. Our aim is fundamentally academic: we want to develop models to help us understand stories and thus learn more about this essential human activity. Most AI development is happening inside of black boxes and behind closed doors. Our models will be open to the public as will all of the annotations made by readers like you. You are a key participant in how we will understand the future of stories.

How does it work?

As we all know, emotions are complicated. Figuring out what you are feeling at any given moment is of course difficult. This is also true of literary characters. They experience a complex range of emotions that will sometimes be more or less explicit. It's that range and subtlety that propels us as readers through a story as we connect with someone else's intimate inner life.

Debates about how to classify emotions are legion in academic research. In our project, we want to surface the full range of readers' potential responses. For this reason we are using an open-text response approach. You will read a single sentence and then have the ability to write in all of the emotions that you feel the character is experiencing in that moment. We provide a list of possible emotions to help you decide, but it is really up to you. You don't have to follow any schema just trust your gut.

Sometimes the task will be easy. Consider the following sentence:

Sometimes the task will be far more ambiguous. Consider the following sentence:

Now that Xander’s not here --I-- don’t feel the need to be as polite.

What is the narrator feeling? Relief? Probably. Some bitterness? Possibly. It's really up to you to decide. Try to put yourself in that person's body and intuit what they are feeling in that situation with the limited amount of information you have.

In this project you will have the chance to read thousands of sentences where characters are likely feeling some kind of emotion. We hope you have fun figuring out what they may be feeling!