Free Open-Source Textual Emotion Recognition and Visualization



Synesketch is the Web’s first free open-source software for textual emotion recognition and artistic visualization, designed and developed by Uroš Krčadinac.

Synesketch algorithms analyse the emotional content of text sentences in terms of emotional types (happiness, sadness, anger, fear, disgust, and surprise), weights (how intense the emotion is), and a valence (is it positive or negative). The recognition technique is grounded on a refined keyword spotting method which employs a set of heuristic rules, a WordNet-based word lexicon, and a lexicon of emoticons and common abbreviations. The real-time generative animationis partially based on Jared Tarbel’s algorithms, itself inspired by the physics graphics of colliding particles.

Research papers about Synesketch were published in the IEEE Transactions on Human-Machine Systems and the IEEE Transactions on Affective Computing. Synesketch was awarded by the International Digital Media and Arts Association, Canada, and the Belgrade Chamber of Commerce, Serbia. It was reviewed by the Creative Review magazine and many data art and visualization blogs, shown on festivals and conferences in Canada, Austria, China, Serbia, and Finland, and used by designers, artists, engineers, and researchers world-wide.

Synesketch is part of the research and design efforts of the GOOD OLD AI Lab and the studio.

At the moment we are not planning to work on a new version of Synesketch. The softwere is free and open for further development by Java and Processing communities.


Synesketch is open and free to download.

It is published under GNU General Public License (version 2 or later).

It is written in Java and well documented.

We suggest that you use it with Eclipse.

Please use one of the following citations when referencing Synesketch in your work:

Research Publications

Krcadinac U., Jovanovic J., Devedzic V. & Pasquier P. Textual affect communication and evocation using abstract generative visuals, IEEE Transactions on Human-Machine Systems, doi:10.1109/THMS.2015.2504081 [Preprint PDF]

Krcadinac U., Pasquier P., Jovanovic J. & Devedzic V. Synesketch: An Open Source Library for Sentence-Based Emotion Recognition, IEEE Transactions on Affective Computing 4(3): 312-325, 2013, doi:10.1109/T-AFFC.2013.18 [Preprint PDF]

Top to bottom: happiness, fear, surprise, disgust, anger, sadness. Left to right: low-high intensity of emotion.



Best Graduation Thesis Award, Belgrade Chamber of Commerce, Serbia, 2009

Graduate Student Showcase Award, International Digital Media and Arts Association (iDMAa), Canada, 2010


Creative Review magazine, 2008


SHARE Conference, Serbia, 2012

Digital Narrative, International Digital Media Arts Association Conference, Canada, 2010

School of Interactive Art and Technology, Simon Fraser University, Canada, 2010

Media Interaction Lab, Austria, 2008

Alternative Party Art Exhibition, Finland, 2008

Synesketch-Based Projects


SyneSkype is the software extension of the Skype software. SyneSkype adds one new feature to the standard Skype chat: a window for Synesketch visualizations of emotions detected in the exchanged chat messages (take a look at the screenshot). You can download it and use it with Eclipse. (You might need this file too.)

Third-Party Software

Kaleidok (2015): a new kind of interactive media tool and take part in an emerging experience which explores speech recognition, media retrieval and visuals generating in a collaborative context (between people, and between people and machines). By sharing data in new and creative ways, we can interact with world events, emotional experiences and social exchanges. Technology has made a kaleidoscope of diverse cultural expressions accessible, and KaleidOk offers a platform for people to explore the connections between their internal dialogue and the outside world.

EmoTweet: sources live tweets, senses emotions and creatively visualizes them. A combination of six basic emotions- happiness, anger, fear, surprise, sadness, and disgust at various scales make up a final visualization of the tweet.

Twitter Emotion Graphs: shows you the emotional state of Twitter in real-time.

Generative Art Karaoke Player: a visualizer of the emotions in lyrics. The player takes a song, plays it, and with each line of text that plays in the lyrics, the strongest emotion of that line is visualized. Examples include Thriller by Michael Jackson and Shiny Happy People by REM.

Graphic Design

Diversity and Complexity, Scott E. Page, Princeton University Press (Book Cover Art by Synesketch)

Data Visualization

What do Programmers Feel About their Software?, Nat Pryce

News Visualized, Amy Martin