Digital Imaginations of National Parks in Different Social Media: A Data Exploration

Vuokko Heikinheimo, Henrikki Tenkanen, Tuomo Hiippala, Tuuli Toivonen

Research output: Chapter in Book/Report/Conference proceedingConference contributionProfessional


Social media contains a wealth of information about human activities in different places. This information can complement data collection efforts in resource-scarce fields such as nature conservation. However, social media platforms differ in popularity, content, and access to data, and the choice of platform may greatly affect the resulting analysis. We explored Flickr, Instagram, and Twitter data from 39 Finnish national parks over a period of two years to assess the fitness-for-purpose of each platform for understanding place-based experiences of national park visitors. From Instagram, we extracted data using two different approaches: coordinate search and keyword search. Furthermore, we identified the languages used in Instagram data using the fastText library, and conducted preliminary content analysis of Flickr and Twitter data using Google Cloud Vision image annotation service. Instagram was the most popular platform in all national parks. Noteworthy, almost 50% of Twitter users had shared their geotagged national park post to Twitter via Instagram. Language identification from text content and content analysis of images provide basis for further exploration of the digital representations of national parks and place-related experiences of visitors.
Original languageEnglish
Title of host publicationOn the Way to Platial Analysis: Can Geosocial Media Provide the Necessary Impetus?
Number of pages8
Publication statusPublished - 27 Oct 2018
MoE publication typeD3 Professional conference proceedings
EventWorkshop on Platial Analysis - Heidelberg, Germany
Duration: 20 Sep 201821 Sep 2018


WorkshopWorkshop on Platial Analysis


Dive into the research topics of 'Digital Imaginations of National Parks in Different Social Media: A Data Exploration'. Together they form a unique fingerprint.

Cite this