October 2017
Vector Space Models are currently the most popular machine-learning technology for natural language processing. While current vector space models are far from being able to capture all nuances of a language or culture, their geometry could represent early attempts to grasp a universal pattern in the human mind. Read the rest Do Our Minds All Share a Unique Structure?
October 2017
Vector Space Models are currently the most popular machine-learning technology for natural language processing. While current vector space models are far from being able to capture all nuances of a language or culture, their geometry could represent early attempts to grasp a universal pattern in the human mind. Read the rest 
La publicité fait partie du quotidien, ses modalités sont rarement remises en question. Et pourtant, la publicité joue un rôle important dans bien des maux qui préoccupent les sociétés contemporaines: la surconsommation et ses conséquences sur l’environnement, la manipulation des opinions politiques ou encore l’homogénéisation des identités culturelles. 
Gestes politiques scrutés, postures médiatiques décortiquées, soulignées, détournées ou ridiculisées (2017, Toronto).
Videos and collages created on mobile phone using Nintendo Miitomo application.
2016-2018
Presented at the 
Political “footprints” are vector-based representations of political discourse, where each vector corresponds to a word. These representations are computed using machine learning and pre-trained word embeddings, allowing for a more structurally independent form of political analysis. 
Picture collages based on Elephant & Castle street advertising and stock images.
May 2016 
Jessa Lingel is assistant Professor at the Annenberg School for Communication, University of Pennsylvania. She is the author of 
In this interview, the futurist and science fiction author