Like Partying? Your Face Says It All. Predicting the Ambiance of Places with Profile Pictures
This work is incremental, improving upon prior research by analyzing visual cues and algorithm performance for ambiance prediction in social-networking contexts.
The study tackled the problem of predicting a place's ambiance from visitor profile pictures, showing that a state-of-the-art algorithm could sometimes outperform humans in accuracy.
To choose restaurants and coffee shops, people are increasingly relying on social-networking sites. In a popular site such as Foursquare or Yelp, a place comes with descriptions and reviews, and with profile pictures of people who frequent them. Descriptions and reviews have been widely explored in the research area of data mining. By contrast, profile pictures have received little attention. Previous work showed that people are able to partly guess a place's ambiance, clientele, and activities not only by observing the place itself but also by observing the profile pictures of its visitors. Here we further that work by determining which visual cues people may have relied upon to make their guesses; showing that a state-of-the-art algorithm could make predictions more accurately than humans at times; and demonstrating that the visual cues people relied upon partly differ from those of the algorithm.