AMYGDALA

AMYGDALA is an audiovisual installation that captures and interprets the collective emotional state of the Internet. In our ever-connected world, our emotions and perceptions are shaped by a constant stream of external stimuli—from the people we interact with to the digital landscapes we navigate. Every interaction on social media and the web feeds into vast vaults of ‘Big Data,’ transforming personal experiences into a collective digital consciousness. This continuous flow of data represents a global mosaic of shared emotions: happiness, anger, sadness, disgust, amazement or fear. Thus, imagining the Internet as a living organism, we might think that its emotional state may be given by the overall emotions shared by users at any given time.

AMYGDALA listens to this stream of shared thoughts, interpreting and translating into a visual and auditory experience the Internet’s emotional state and its shifts in response to the events that take place around the world. By capturing this ever-shifting emotional landscape, the installation aims to make the invisible data flow visible.

The aim is to stimulate a critical reading of the opportunities and dangers of the digital revolution pervading our lives since the start of the century. Through AMYGDALA, we seek to deepen the understanding of the impact of Big Data on individual and collective freedoms.

Artechouse DC, 2019

Concept

AMYGDALA does just this: it listens to and interprets the contents shared on the net by users in order to generate an audiovisual work.

In humans, the amygdala is central to processing and integrating higher neurological functions, such as the development of emotions and emotional memory systems. It plays a crucial role in comparing new stimuli with past experiences and in processing olfactory inputs. To emulate these processes artificially, AMYGDALA utilises a discipline known as Sentiment Analysis, also known as Opinion Mining. This field merges information retrieval with computational linguistics allowing us to assess the emotional tone of messages shared by users across a network. During the analysis of a written text, the technique focuses not on the topic discussed, but on the opinion and sentiment the document itself expresses.

The rise of Web 2.0 and the explosion of user-generated content have increasingly made Sentiment Analysis a vital tool in various domains, including social research, online reputation management, financial market forecasting, and personalised advertising campaigns. By understanding the collective sentiment of network users, we can gain valuable insights into present conditions and make informed predictions about future social phenomena, from stock market fluctuations and disease outbreaks to public uprisings and entertainment trends. 

AMYGDALA embodies this concept by analysing and interpreting the content shared online, transforming these insights into an immersive audiovisual experience, revealing the current emotional climate of the Internet.

CUBO Unipol, 2016

Artechouse DC, 2019

CUBO Unipol, 2016

CUBO Unipol, 2016

Credits

Commissioned by Unipol
Video Shooting: Gianluca Bertoncelli

For the work, we employed the algorithm of Sentiment Analysis based on the open-source library Synesketch, developed by U. Krcadinac, P. Pasquier, J. Jovanovic & V. Devedzic. (“Synesketch: An Open Source Library for Sentence-Based Emotion Recognition”, IEEE Transactions on Affective Computing 4(3): 312-325, 2013).