“Tourist” is practically a dirty word these days. Tourists are loud. Tourists are rude. Tourists are ignorant. Tourists are poorly dressed, selfie stick-wielding clichés.
But a traveller… now that’s different. Travellers are curious, adventurous, in-the-know, and eager to immerse themselves in authentic local experiences. Travellers are what every over-edited Instagrammer purports to be. Travellers want deeper, more enriching experiences that leave them feeling physically challenged, mentally refreshed, professionally inspired, and spiritually fulfilled.
It’s a tall and somewhat bullshit order, but experiential travel is big business. There’s just one problem: how can you live like a local when most locals are loathe to spill the secrets of their favourite spots?
Computer scientists at ITMO University in St Petersburg, Russia, have developed a high-tech answer. They found a way to distinguish between Instagram users living in St. Petersburg and visiting tourists based on how they use social media, then developed an algorithm that mines the app’s publicly available data to create a “genuine” locals’ guide.
In order to remove tourists from the analysis, the scientists chose two months of the year with the least number of tourists in St. Petersburg (February and November) and collected all posts taken during that time. They then analysed the profiles of the users who created them, noting that tourists tended to take pictures in the centre of the city, while residents’ geotags were scattered throughout St. Petersburg.
The programmers also cross-referenced with official tourist statistics to further narrow down their local suspects, and excluded the top 15 tourist locations.
“The main idea behind our work is to give tourists insider information from local residents. Therefore Nevsky Prospect, Kazan cathedral, the Hermitage, Pulkovo airport and other well-known areas were excluded from the analysis. Metro stations, geotags for locations that represent the city as a whole, and nearby cities were also not included,” said Ksenia Mukhina, engineer at the eScience Research Institute and assistant at the High Performance Computing Department at ITMO University.
The final dataset consisted of roughly 530,000 posts with geolocation tags in 17,921 places, and 23,596 users classified as St Petersburg residents, reports The Guardian. The algorithm can now automatically sort popular locations into five categories – theatres and museums, restaurants and bars, bridges and streets, parks, and other – revealing the city’s hidden, local-approved gems
“Instagram is a dynamically changing environment. Some places gain popularity while others lose it. Sometimes new restaurants or cafés open. Therefore, the creation of a recommendation service which follows photographs of interesting places in real time is a logical continuation of the current results,” Mukhina added.
Travellers will no doubt be thrilled by the opportunity to circumvent crowded tourist attractions and pricey guidebooks, but will locals be as pleased?
Mukhina hopes the algorithm will improve relations between residents and tourists by redistributing visitors more evenly, easing crowding and traffic in popular hotspots. She also believes the increasing popularity of non-tourist districts could spark business development and inspire the city administration to improve urban infrastructure.
If you’re worried about your favourite locals-only spots blowing up, we see a prime opportunity for trolling by getting a group to tag random locations en masse. While you sip your morning latte in peace at the best cafe in the city, a bunch of confused sightseers will be wondering how they ended up at the waste processing plant.