Modern tourists travel in new ways. The rising class of so-called "Creative tourists" prefer to explore everyday life instead of simply ticking off a list of sights to see. However, travel guides all currently represent places as simply a collection of sights.

At the same time, public geotagged social media data is opening a new world of ways to investigate another place. In this thesis, I describe efforts to bring these trends together, by developing neighborhood guides for travelers, based on social media. I first investigate why people geotag and where this public geotagged data comes from. Then, after developing a model of what tourists want through a series of interviews and surveys, I develop a prototype social-media-based neighborhood guide for travelers. By an iterative user study and quantitative investigation into photo sources, I find that this data can give users an ideal glimpse into a new city.

Implications are widespread: I show not only how social media can be used to help people travel, but also develop a perspective on what social media tells, and does not tell, about cities and neighborhoods. I show that social media provides an idealized qualitative image into a city, while perhaps not reflecting the objective, quantitative reality. This matches tourists' needs ideally, providing an exciting new opportunity for a new generation of tourism tools.

105 pages

Thesis Committee:
Jason Hong (Chair)
Jodi Forlizzi
Aniket Kittur
Judd Antin (Airbnb)

Anind K. Dey, Head, Human-Computer Interaction Institute
Andrew W. Moore, Dean, School of Computer Science

Return to: SCS Technical Report Collection
School of Computer Science homepage

This page maintained by reports@cs.cmu.edu