Spatial Footprints of Human Perceptual Experience in Geo-Social Media

Abstract

Analyses of social media have increased in importance for understanding human behaviors, interests, and opinions. Business intelligence based on social media can reduce the costs of managing customer trend complexities. This paper focuses on analyzing sensation information representing human perceptual experiences in social media through the five senses: sight, hearing, touch, smell, and taste. First a measurement is defined to estimate social sensation intensities, and subsequently sensation characteristics on geo-social media are identified using geo-spatial footprints. Finally, we evaluate the accuracy and F-measure of our approach by comparing with baselines.

Discovering underlying sensations of human emotions based on social media

“…It can be considered as a crucial feature to discriminate a text in terms of human sensation. In the recent work (Lee, Ogawa, Kwon, & Kim, 2018), a dedicated measure was proposed for estimating the sensation intensity. In particular, the authors identified meaningful regional differences of sensation intensity depending on a native language and temperature.…”

“…(Lee, Thabsuwan, Pongpaichet, & Kim, 2018) improved that method taking into account a lexical semantic relation of words based on Wordnet (Miller, 1995) graph structure. Accordingly, we adopt those measures of sensation intensity as a feature for the sensation classification: Sensation Intensity (Lee, Ogawa, et al, 2018) …”