Synesketch Serves as Bridge Between Words, Emotions, and Images
September 4th | 2009 By
Synesketch is an artistic software library with synesthetic abilities, created by Uroš Krčadinac. It is a Web’s first free open-source textual emotion recognition and visualization engine – code that feels the words visually! For example, the six images above visualize a response to Ekman’s six basic emotions – happiness, anger, fear, surprise, sadness, and disgust (left to right, top to bottom).
According to the projects official Wiki, Synesketch “is a software library (Java API) for sensing and creative visualization of textual emotions! Code is serving as a medium between words, emotions, and images; between poetry and painting. Gluing computers with our emotions and aesthetic experiences, it is both a software innovation and an interactive art experiment.
The Visualization system is based on the Jared Tarbell’s work. “It is a generative painting system of imaginary colliding particles, inspired by graphics created by particle colliders, such as the famous one in CERN. After the interpretation of a new fragment of text, new particle collision happens, which produces a discrete universe of new particles. While moving, particles form various visual patterns. Colors and shapes of these patterns depend on the type and intensity of interpreted textual emotions (as seen on the images above).”
The project names four different potential goals for this software:
1.) End User Applications: Such as a visual chat program – while we talk, colors and shapes are being generated.
2.) Tool for Visual Artists and Designers: To create visualizations based on textual emotions
3.) Affect Sensing and Emotion Recognition Engine: They have developed a Synesketch Lexicon – WordNet-based lexicon of words with their general and specific emotional weights (for Ekman’s emotion types: happiness, sadness, fear, anger, disgust, surprise).
4.) Experimental Polygon for Synesthesia and Real-Time Text Visualization: The Synesketch API allows you to create your own synesthetia-like algorithms.
I personally think this application is fascinating. In particular, I am drawn to the affect sensing and emotion recognition engine application. Systems like this may play an important role in helping marketers understand the voice of their customers in a more meaningful way. Imagine a CMO with a Synesketch widget on his marketing dashboard that compiles all of the written statements associated with his/her brand online and provides them a real-time view of either positive or negative sentiment.
Check out Synesketch Gallery and Demo page for more examples of the tool in action.