sensing sentiments
Monday, March 29th, 2010
Social media, location-based services, anywhere-anytime internet access etc. offer major opportunities for mass-sampling people’s moods, sentiments and emotions.
In October of last year, Facebook started correlating status updates of their (US) users with the Gross National Happiness Index. Later, results from the UK, Canada and Australia were added to the mix. According to a recent article in Fastcompany:
“Facebook demonstrated that the vast historic record of status updates is a potential goldmine of information that could easily be raked through by sociology analysts keen to work out when it’s best to deliver an advert for particular products, or perhaps even to promote a particular political message.”
Indeed, sentiment analysis as the game is called (see also here), is not only interesting for artists and gadgeteers, but also for businesses and public institutions.
The concept is not new, in 2001, webdesign meeting point k10k.net launched Moodstats, a webbased effort to enable people to share their moods. Yet, now that our physical and virtual action patterns are becoming increasingly intertwined, applications like iPhone app Glow enable anywhere, anytime, sentiment sampling.
In most current applications, people are still required to express their mood, emotional state etc. Language processing algorithms can help to analyze this data. The next step is obviously to have emotion sensing technologies (e.g. Philips Design’s VIBE) reading, interpreting and allowing us to communicate our emotions directly. Imagine your t-shirt changing color depending on how you feel, for example.
Image by Glow
