Reducing Emotion to Mere ‘Information’A Phenomenological Critique of a Partial Understandingof Emotion in Affective ComputingNithin Monteiro SJAbstract —Affective computing, a growing field in human-computer interaction aims to create computers that have the ability to sense, recognize, express and in some cases ‘have’ emotions/affect. Affective computing manipulates the physiological modulations felt during emotional experiences to infer the supposed corresponding ‘affective states’ in human beings. The empirical approach to affective computing emphasizes the physical and cognitive aspects of affective experiences. However, it lacks a discrimination in the treatment of affectivity. Furthermore, affective computational models consider emotion as ‘information’ that can be extracted from the human ‘body’ in isolation to the complex relations that human beings share with others and the world against a backdrop of an overall network of interpersonal emotions and moods. I argue that an empirical approach to affective computing misses the existential significance of emotions because it considers ‘emotion’ derivative rather than constitutive of human existence. In this essay, I shall offer a phenomenological account of ‘emotion’ inspired by the accounts of Martin Heidegger, Jean-Paul Sartre and Edward Casey. I contend that a dialogue with phenomenology and philosophy in general, can help computational scientists to define specific affective experiences that they are investigating. A cross-disciplinary dialogue offers insights into the ethical design of affective computing technologies.Index Terms : Interaction; Affectivity; Emotion; Phenomenology; Interembodiment—————————— ——————————