emotions

In November 2018, Studio Tender Claws launched Tendar, the first long-form, augmented reality game to merge AR technology with human sentiment analysis. Gameplay centers around an artificially-intelligent pet fish that responds to the player’s actions, emotions, and physical surroundings via a combination of generative and hand-scripted dialog. The fish recognizes over 100 user emotions and 200 physical objects as it navigates eight distinct developmental stages. As a small independent game studio, our challenge was to generate and trigger engaging dialog for the vast combinatoric writing surface that the game presented, all while dynamically adjusting tone, affect, and content according to player actions and the fish’s emotional state.

To address this challenge, we adopted Dialogic, an open-source scripting language and toolkit for interactive, generative dialog. Dialogic, authored by panellist Daniel Howe, integrates generative and scripted content, allowing NPCs to respond organically to non-sequential input from human users. Because the system is open-source and under active development, we were able to adapt it to our needs as they emerged throughout the game’s development. The system proved both versatile enough to be used by our mixed-background writing team, and performant enough for runtime execution in our Unity/Android environment.

This panel brings together Samantha Gorman, co-founder of Tender Claws and lead writer for the project; Ian Hatcher, a member of the core writing team; and Daniel Howe, the creator of Dialogic. Together we will discuss how iterative design and close collaboration between the various teams helped us achieve project goals for both Tendar and Dialogic. We will also present the strategies, processes, and tools we found to be most useful in addressing the vast combinatoric space that the project presented.

"StoryFace" is a digital fiction based on the capture and recognition of facial emotions.

The user logs onto a dating website. He/she is asked to display, in front of the webcam, the emotion that seems to characterize him/her the best. After this the website proposes profiles of partners. The user can choose one and exchange with a fictional partner. The user is now expected to focus on the content of messages. However, the user's facial expressions continue to be tracked and analyzed… 

What is highlighted here is the tendency of emotion recognition devices to normalize emotions. Which emotion does the device expect? We go from the measurement of emotions to the standardization of emotions. 

StoryFace was re-published in The New River in 2018.

Poetracking is a work of digital literature created by three students respectively studying graphic design, digital technologies and journalism. It was developed during the Erasmus intensive program “Digital Literature” organised by Philippe Bootz and held in Madrid in 2014. Poetracking's homepage encourages you to draw a tree within the interface by using a simple drawing software, providing built-in tools such as colour and line width. Shortly after your drawing is finished, a poem appears on the screen. Then, after a while, the poem disappears and you are redirected to a database in which all previous drawings and poems are stored, including your newly generated poem. As innocent and simple as it may look, this project draws in fact from the Baum personality test (sometimes called tree test) created by psychoanalyst Charles Koch, which is meant to bring out a patient's main personality traits and emotions by analysing the way he or she represents a tree on a sheet of paper. By closely examining the drawing, its shape, its position on the white blank space, its colours and the thickness of its lines, as well as some characteristic elements of the tree itself, the psychologist is able to get information on the patient's behaviour and his/her relationship with others. For instance, small trunks symbolize introversion and low self-esteem, while large trunks imply strength, higher self-esteem and vitality. In several respects, however, Poetracking misappropriates the original Baum test. By not providing any context or explanation, it twists the actions of the user who unknowingly generates a poem based on the analysis of his/her personality. This result is generated by simultaneously comparing the three tools that have been used (colours, line width and position on the page), all of which are linked to keywords through a combinatory process. But the profiling process no longer is accurate, since the Baum test parameters are reduced to three only. Since the parameters are oversimplified, the Baum test ends up misappropriated and much more minimalistic in the way data is treated, since the drawing is no longer analysed and interpreted extensively. Therefore, the profile given to the patient is reduced to just a few keywords. By highlighting the weaknesses of the Baum test, Poetracking was designed to point out how subjective it can be. By keeping all previously generated profiles in a database and making them available to all users, Poetracking also aims at denouncing tracking systems which analyse our tastes and preferences and try profiling every aspect of our life while we're browsing the internet or using our smartphone. The software is unable to completely track the user's intentions, which gives it another dimension: he or she could decide to ignore the rules and draw anything but a tree, thus being free to experiment with the software and bring out all its poetic potential.

Demo text world in the Oz Project where the player is involved in backstabbing office politics. Emotional and social characters for interactive drama were a key aim.

“Loss of Grasp” is an interactive narrative about the notions of grasp and control. What happens when one has the impression of losing control in life, of losing control of his/her own life? Six scenes tell the story of a man that is losing himself. “Loss of Grasp” plays with the grasp and the loss of grasp and invites the reader to experiment with these feelings in an interactive work.