From Trailhead to Summit: Using NLP to Analyze Thru-Hikers’ Wilderness Experiences

We applied Natural Language Processing (NLP) to analyze changes in long-distance hikers' wilderness experiences using 150,000 entries from Trail Journals (2016-2021) on the Appalachian Trail. We used a validated lexicon based on Borrie and Roggenbuck’s (2001) wilderness experience scale to identify key constructs (oneness, timelessness, solitude, care) across entry, immersion, and exit phases. Results revealed dynamic, multiphasic experiences, with heightened oneness at immersion and care during entry and immersion, indicating that users who embark on a thru-hiking journey are more environmentally driven.  While there were limitations to this approach such as the ML's inability to detect linguistic nuances such as sarcasm, the study highlights the NLP's potential to explore psychological constructs in wilderness settings using large datasets. This interdisciplinary approach combines computer science and psychological research to enhance our understanding of person-environment interactions. 

Abdelgawad, N.*, Misra, S., Saaty, M.*, Patel, J.*, Wernstedt, K., & McCrickard, S. (2024). From Trailhead to Summit: Using NLP to Analyze Thru-Hikers’ Wilderness Experiences. American Psychological Association Annual Convention, August 2024, Seattle, WA.