Emergence of Things Felt: Harnessing the Semantic Space of Facebook Feeling Tags

In 2013 Facebook launched a feature allowing users to add a feeling tag to their posts as part of their daily interactions online. Our research leverages the text accompanying all such volunteered feeling tags in an effort to map the semantic space of ‘Facebook feelings’ as they are catalogued by the crowd. By letting the data speak for itself, a folksonomy of feelings reveal temporal and social patterns in the most commonly shared feelings. Unlike many such studies, however, we do not only focus on examining the patterns emerging from big data, but also put the expressed feelings to work using machine learning towards both the classification and detection of emotions. This paper first demonstrates that feelings expressed online self-organize along the same lines (valence and arousal dimensions) experts in psychology and emotions have organized them for decades. As we enter the debate of classifying human emotions, our analysis directly contrasts Facebook’s manifestation of feelings with prior theoretical proposals to detect both similarities and differences from past assumptions. In line with the ‘exhibitional’ nature of Facebook, we illustrate that ‘extreme’ feelings, such as excitement and anger, are expressed in even more extreme levels of both valence and arousal. Beyond contrasting the folksonomy of feelings with dimensional mappings of emotions proposed by past research, we further utilize artificial intelligence techniques towards building a test version of an automatic ‘Feelings Meter’ able to detect feelings from text.