An open‐source image classifier for characterizing recreational activities across landscapes

Winder, Samantha G.; Lee, Heera; Seo, Byong Seol; Lia, Emilia H.; Wood, Spencer A.

doi:10.1002/pan3.10382

Cited by 10 publications

(9 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Social media images and short‐form texts (e.g. image captions and tweets) have been analysed quantitatively to understand many aspects of outdoor experiences, including landscape values, subjective well‐being, activity participation and experiences of tranquillity and aesthetic appreciation (Calcagni et al., 2019; Egarter Vigl et al., 2021; Lin et al., 2022; Oteros‐Rozas et al., 2018; Schirpke et al., 2018; Song et al., 2020; Wartmann et al., 2021; Winder et al., 2022). Longer form texts such as blog posts and trip reports provide information about the qualities of people's experiences in more developed, narrative formats and have been analysed qualitatively to understand visitors' recreation experiences (Armstrong et al., 2021; Champ et al., 2013; Williams & Champ, 2015).…”

Section: Introductionmentioning

confidence: 99%

“…Large data sets, such as those generated by social media users, often require automated methods such as machine learning to analyse content that cannot be reviewed and coded using typical methods (Egarter Vigl et al., 2021; Lee et al., 2019; Winder et al., 2022). Studies using natural language processing (NLP) and natural language understanding have examined the spatial variation in the content of real‐time, geolocated images and short‐form texts such as tweets.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Where wilderness is found: Evidence from 70,000 trip reports

Derrien,

Winder,

Wood

et al. 2023

People and Nature

Self Cite

View full text Add to dashboard Cite

Outdoor recreation is an essential way many people engage with nature. The provision of public spaces for recreation intersects with conservation practices motivated by intertwined social and ecological values, such as strict practices associated with the concept of ‘wilderness’. Debates persist about how such concepts and management practices influence people's recreation experiences. Many US public land management agencies facilitate opportunities for outdoor recreation, relying on management frameworks and tools intended to foster specific experiential qualities. But these frameworks and tools assume simplistic relationships between settings and people's experiences, and managers rarely assess these relationships. This study uses a data set of nearly 70,000 crowdsourced trip reports from a hiking website to understand the qualities of visitors' experiences on trails. We study the geographic distribution of experiential qualities commonly associated with US wilderness areas: aesthetics, awe, challenge, pristineness, quietness, solitude and timelessness. Using analytical methods that rely on machine learning and natural language processing, we identify these experiential qualities in trip reports from hundreds of routes, and use generalized linear models to analyse relationships between the frequency of each experiential quality and the route's administrative, built, biophysical, geographic and social settings. We find that four of the seven experiential qualities (aesthetics, awe, challenge and solitude) are commonly described in trip reports, each appearing in 15%–55% of manually coded reports. The extent to which setting characteristics explained variability in experiences differed, ranging from 34% of the variability in the proportion of trip reports describing aesthetics to 55% for awe. The setting characteristics associated with each experiential quality also differed, with characteristics such as trail mileage and summit destinations having stronger influences on experiential qualities than characteristics such as wilderness designation. Synthesis and applications. Our findings suggest the need to consider more diverse variables in experience–setting relationships, develop more robust models to characterize those relationships and create new data sources to represent understudied variables. These advances would help empirically inform and improve frameworks and tools used for recreation and wilderness planning and monitoring, and potentially promote more responsive management to evolving social–ecological values. Read the free Plain Language Summary for this article on the Journal blog.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Where wilderness is found: Evidence from 70,000 trip reports

Derrien,

Winder,

Wood

et al. 2023

People and Nature

Self Cite

View full text Add to dashboard Cite

show abstract

“…Most present applications of deep learning in a CES context have used objects or scene classifications of images on social media as proxies for CES (Lee et al, 2019;Richards and Tunçer, 2018). Applications also rely on a limited groups of experts or researchers to categorise CES according to the objects or scenes found in the images (Gosal et al, 2019;Winder et al, 2022). On the other hand, despite their availability, models trained to predict complete semantic representations of CES are lacking.…”

Section: Knowledge Gapsmentioning

confidence: 99%

“…Not only sentiment could be used to weight humanspecies interactions as indicators of CES; species rarity could also imply an interaction of greater cultural importance. Recently, some studies have begun to explore this research challenge with promising results, using the text and content of the images to produce more advanced indicators (Fox et al, 2021a;Winder et al, 2022).…”

Section: Moving To Full Measures Of Cesmentioning

confidence: 99%

“…"Big data" and "AI" have become familiar buzzwords, finding themselves into the vocabulary of engineers, medical practitioners, business people and policy-makers as well as scientists. Their application to CES assessment, especially the use of deep learning, is only just emerging and therefore many of the challenges are still yet to be explored (Ghermandi et al, 2022;Winder et al, 2022).…”

Section: Crowdsourced Data Machine Learning and Societymentioning

confidence: 99%

See 1 more Smart Citation

Crowdsourced data and machine learning to measure cultural ecosystem services

Havinga

View full text Add to dashboard Cite

Cultural ecosystem services (CES) are some of the most valuable contributions of ecosystems to human well-being. Nevertheless, these services are often underrepresented in ecosystem service assessments. Defining CES for the purposes of spatial quantification has been challenging because it has been difficult to spatially model CES. However, rapid increases in mobile network connectivity and the use of social media have generated huge amounts of crowdsourced data. This offers an opportunity to define and spatially quantify CES. We inventoried established CES conceptualisations and sources of crowdsourced data to propose a CES definition and typology for spatial quantification. Furthermore, we present the results of three spatial models employing crowdsourced data to measure CES on Texel, a coastal island in the Netherlands. Defining CES as information-flows best enables service quantification. A general typology of eight services is proposed. The spatial models produced distributions consistent with known areas of cultural importance on Texel. However, user representativeness and measurement uncertainties affect our results.Ethical considerations must also be taken into account. Still, crowdsourced data is a valuable source of information to define and model CES due to the level of detail available. This can encourage the representation of CES in ecosystem service assessments.

show abstract