Atlas of Me

A Chrome plugin that presents on-demand personalized maps for unfamiliar distances, areas, and locations.


We encounter measurements like distances and areas often in online text. But many times it is difficult to grasp the magnitude of a distance or area in absolute terms. For example, how long is 100 miles really? How big is 21 acres? How large is the country of Pakistan?

Atlas of Me automatically generates personalized spatial analogy maps that re-express distances, areas, and location references in terms of landmarks that are likely to be more familiar to you. Try it on articles that contain distances, areas, or locations.

Try it out!

Enter a U.S. location that is familiar to you:

Select a measurement type:

Enter a measurement to re-express:


Our algorithm relies on several criteria to generate an analogy:

  • The personal familiarity of the landmark, which we capture using the proximity of the landmark to the user.
  • The general familiarity of the landmark, which we capture using the landmark's popularity of Flickr, a photo sharing website.
  • The multiplicative factor required to re-express the input measurement (e.g., 100 miles, 21 acres) in terms of the user's distance to the landmark or in terms of the area of the landmark.

Landmark Dataset

We developed a database of landmarks and their properties by scraping public datasets containing spatial entities (Yelp, OpenStreetMap). We use a heuristic based on prior work in behavioral geograph to differentiate area landmarks (those for which area is likely to be memorable to people) from other landmarks, which we retain and use for distances. We query the Flickr photo set using variations of each landmark's name to identify how well known a landmark is to the general population.

Download the landmark dataset from our repository.


We describe how we developed an automated approach to generating on-demand personalized spatial analogies for distances, areas, and location references.

Generating Personalized Spatial Analogies for Distances and Areas

Yea-Seul Kim, Jessica Hullman, Maneesh Agrawala

Abstract: Distances and areas frequently appear in text articles. However, people struggle to understand these measurements when they cannot relate them to measurements of locations that they are personally familiar with. We contribute tools for generating personalized spatial analogies: re-expressions that contextualize spatial measurements in terms of locations with similar measurements that are more familiar to the user. Our automated approach takes a user’s location and generates a personalized spatial analogy for a target distance or area using landmarks. We present an interactive application that tags distances, areas, and locations in a text article and presents personalized spatial analogies using interactive maps. We find that users who view a personalized spatial analogy map generated by our system rate the helpfulness of the information for understanding a distance or area 1.9 points higher (on a 7 pt scale) than when they see the article with no spatial analogy and 0.7 points higher than when they see generic spatial analogy.

  Download the paper

Atlas of Me Creators

Yea-Seul Kim

Concept and Developer

Ph.D. student, Information School, University of Washington


Francis Nguyen


Informatics Student, Information School, University of Washington


Jessica Hullman

Concept and Developer

Assistant Professor, Information School, University of Washington


Professor of Computer Science, Stanford University