Researchers use Instagram to Help Tourists See Cities from a Local's Perspective
Programmers from ITMO University have created a list of places in St. Petersburg which could help locals indirectly give advice to tourists. The scientists created a computer algorithm that allows users to find the most popular museums, cafes, streets and parks based on photographs taken by locals. Results of the research were presented at The International Conference on Computational Science and published in the peer-reviewed journal Procedia Computer Science.
People tend to photograph significant moments or places. Therefore, social networks such as Instagram are constantly becoming more and more popular. At this time, there are more than 700 million monthly active users around the world with 14.4 million of them in Russia. In most cases, people post photos either because it’s the first time they visited a place or, on the contrary, because they go there often.
Staff at ITMO University’s eScience Research Institute found a way to distinguish between Instagram users living in St. Petersburg and visiting tourists based on how they use social media. As such, the programmers discovered which locations were most loved by St. Petersburg locals.
The most popular place in the “Theaters and Museums” category was the Ice Palace arena, which was more popular than even Mariinsky Theater in terms of number of photographs taken there. In the category “Streets and Bridges”, the locals most liked the Alexander column and the Fontanka river embankment. Amongst cafes and restaurants, the most photogenic was “Schastye” on Rubinstein Street, the creative space “Golitsyn Loft” and Mickey & Monkeys. In the “Other” category, Loft Project ETAGI took the lead.
“Of course, popular locations for locals and for tourists differ, but it was important for us to know just how they differ. Guides usually offer tourists a list of 10-15 attractions. However, locals usually know more. By identifying their favorite places, we can significantly diversify such guide books”, explains Alexander Visheratin, engineer and Head of Research at eScience Institute at ITMO University.
In order to remove tourists from the analysis, the scientists chose two months of the year with the least number of tourists, that is, February and November, and collected all the posts from Instagram taken during that time in St. Petersburg. Programmers used the photos to identify the users who posted them and analyzed their profiles.
First, tourists usually posted pictures in the center of the city, along Nevsky Prospekt, the main street, while the residents’ geotags were scattered throughout St. Petersburg.
In order to more effectively detect city residents, the scientists used official tourist statistics. According to information from the administration of St. Petersburg, the largest number of tourists comes from the European Union (32%) and their holidays rarely exceed 2 weeks. Thus, a user was identified as a tourist if their posts in St. Petersburg during a calendar year were contained within two 15-day or less-long windows with a gap of at least 30 days between each time period.
Furthermore, the programmers 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”, – shared Ksenia Mukhina, the main author of the article, engineer at the eScience Research Institute, and assistant at the High Performance Computing Department at ITMO University.
Ksenia Mukhina also noted that the algorithm that was created now automatically sorts popular locations into five categories: theaters and museums, restaurants and bars, bridges and streets, parks and other.
“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. This is what we are currently working on”, summarizes Ms. Mukhina.
Article: Detection of tourists attraction points using Instagram profiles (2017), Ksenia D. Mukhina, Stepan V. Rakitin, Alexander A. Visheratin, Procedia Computer Science,
You can read the article in Russian here.