Emotion | EPFL Graph Search

Emotions are mental states brought on by neurophysiological changes, variously associated with thoughts, feelings, behavioral responses, and a degree of pleasure or displeasure. There is no scientific consensus on a definition. Emotions are often intertwined with mood, temperament, personality, disposition, or creativity. Research on emotion has increased over the past two decades, with many fields contributing, including psychology, medicine, history, sociology of emotions, and computer science. The numerous attempts to explain the origin, function, and other aspects of emotions have fostered intense research on this topic. Theorizing about the evolutionary origin and possible purpose of emotion dates back to Charles Darwin. Current areas of research include the neuroscience of emotion, using tools like PET and fMRI scans to study the affective picture processes in the brain. From a mechanistic perspective, emotions can be defined as "a positive or negative experience that is ass

Towards Recognizing Emotion in the Latent Space

Rayan Elalamy

Emotion recognition is usually achieved by collecting features (physiological signals, events, facial expressions, etc.) to predict an emotional ground truth. This ground truth is arguably unreliable due to its subjective nature. In this paper, we introduce a new approach to measure the magnitude of an emotion in the latent space of a Neural Network without the need for a subjective ground truth. Our data consists of physiological measurements during video gameplay, game events, and subjective rankings of game events for the validation of our model. Our model encodes physiological features into a latent variable which is then decoded into video game events. We show that the events are ranked in the latent space similarly to the participants' subjective ranks. For instance, our model's ranking is correlated (Kendall tau of 0.91) with the predictability rankings.

IEEE2021

Culture et mémoire comme stratégie urbaine. Un monument éphémère (Shanghai, Chine)

Francis Jacquier

En présence de la multitude de chantiers qui éclairent les chimères du développement chinois, nous prenons le temps de marquer une pause dans les lieux représentatifs de cette mutation : « les ruines de Shanghai ». Ces lieux d'une beauté violente et crue caractérisent un instant primordial dans la mégalopole chinoise, ils sont les ultimes témoins d'un passé frais et d'un futur proche. Nous faisons alors le choix d'une investigation sur la mémoire des hommes et les cultures locales comme alternative à l'uniformisation des modes de vie contemporains en proposant «un monument éphémère». Telle une allégorie d'un monument Phénix qui jaillit de la puissance créatrice omniprésente dans les ruines, ce monument éphémère cristallise en un lieu notre croyance idéologique en la puissance de la mémoire des hommes. Telle une lanterne qui éclaire ce décor fragile, le monument s'adresse à tous et offre un lieu d'évasion poétique et sentimentale, le temps de la lanterne est celui d'une expérience librement consentie. Le jour, la lanterne est réceptacle de connaissance, elle absorbe les histoires locales, les souvenirs, les émotions. Elle est un point de rencontre entre artistes, architectes, chercheurs et population, rassemblés ici pour partager leurs connaissances. La nuit venue, la lanterne rayonne sans éblouir, elle attire ceux qui veulent maintenant recevoir, écouter, s'imprégner. Le théâtre rentre en scène, c'est le temps de la représentation. Il s'adresse à tous, comme un passage accessible

2007

Advancing Fine-Grained Emotion Recognition in Short Text

Valentina Sintsova

Advanced emotion recognition in text is essential for developing intelligent affective applications, which can recognize, react upon, and analyze users' emotions. Our particular motivation for solving this problem lies in large-scale analysis of social media data, such as those generated by Twitter users. Summarizing users' emotions can enable better understandings of their reactions, interests, and motivations. We thus narrow the problem to emotion recognition in short text, particularly tweets. Another driving factor of our work is to enable discovering emotional experiences at a detailed, fine-grained level. While many researchers focus on recognizing a small number of basic emotion categories, humans experience a larger variety of distinct emotions. We aim to recognize as many as 20 emotion categories from the Geneva Emotion Wheel. Our goal is to study how to build such fine-grained emotion recognition systems. We start by surveying prior approaches to building emotion classifiers. The main body of this thesis studies two of them in detail: crowdsourcing and distant supervision. Based on them, we design fine-grained domain-specific systems to recognize users' reactions to sporting events captured on Twitter and address multiple challenges that arise in that process. Crowdsourcing allows extracting affective commonsense knowledge by asking hundreds of workers for manual annotation. The challenge is in collecting informative and truthful annotations. To address it, we design a human computation task that elicits both emotion category labels and emotion indicators (i.e. words or phrases indicative of labeled emotions). We also develop a methodology to build an emotion lexicon using such data. Our experiments show that the proposed crowdsourcing method can successfully generate a domain-specific emotion lexicon. Additionally, we suggest how to teach and motivate non-expert annotators. We show that including a tutorial and using carefully formulated reward descriptions can effectively improve annotation quality. Distant supervision consists of building emotion classifiers from data that are automatically labeled using some heuristics. This thesis studies heuristics that apply emotion lexicons of limited quality, for example due to missing or erroneous term-emotion associations. We show the viability of such an approach to obtain domain-specific classifiers having substantially better quality of recognition than the initial lexicon-based ones. Our experiments reveal that treating the emotion imbalance in training data and incorporating pseudo-neutral documents is crucial for such improvement. This method can be applied to building emotion classifiers across different domains using limited input resources and thus requiring minimal effort. Another challenge for lexicon-based emotion recognition is to reduce the error introduced by linguistic modifiers such as negation and modality. We design a data analysis method that allows modeling the specific effects of the studied modifiers, both in terms of shifting emotion categories and changing confidence in emotion presence. We show that the effects of modifiers vary across the emotion categories, which indicates the importance of treating such effects at a more fine-grained level to improve classification quality. Finally, the thesis concludes with our recommendations on how to address the examined general challenges of building a fine-grained textual emotion recognition system.

EPFL2016

Advancing Fine-Grained Emotion Recognition in Short Text

Valentina Sintsova

EPFL2016