University of Vienna · 2026W

Geographic Information Retrieval

How can a search system retrieve information when geographic meaning matters?

Format9 lectures + labs
EnvironmentPython + Jupyter
PlatformMoodle

About the Course

Search is not only about words. Queries may refer to places, regions, distances, directions, and spatial relationships. Geographic Information Retrieval (GIR) studies how search systems interpret this geographic meaning to retrieve and rank useful information.

Situated at the intersection of Information Retrieval, GIScience, and foundational NLP, this course focuses on text-based GIR. Through lectures and guided labs, students move from place references in text to geographic entities, efficient indexes, and explainable rankings.

Learning Outcomes

After completing the course, students should be able to:

  1. Explain how geographic meaning changes information retrieval.
  2. Identify, represent, and evaluate place references in text.
  3. Interpret geocoding candidates using context, scope, and evidence.
  4. Distinguish common geometries, bounding boxes, and document geographic scope.
  5. Use inverted indexes and Boolean operations for basic retrieval.
  6. Explain spatial indexes, spatial queries, and coordinate reference systems.
  7. Produce textual rankings using TF-IDF and cosine similarity.
  8. Combine textual and spatial relevance and trace uncertainty through a GIR workflow.

Teaching Team

Yingjing Huang

Yingjing Huang

Department of Geography and Regional Research
University of Vienna
yingjing.huang@univie.ac.at

Zilong Liu

Zilong Liu

Department of Geography and Regional Research
University of Vienna
zilong.liu@univie.ac.at

Teaching & Learning

Each teaching week follows a consistent rhythm: concept → worked example → core method → code walkthrough → lab task → checkpoint. Students work with provided notebooks, make small changes to inputs or parameters, inspect outputs, and explain what they observe.

Scope and expectations. The emphasis is on understanding and connecting the components of a GIR system. Advanced Python programming, desktop GIS training, deep learning, and production-scale search-engine development are outside the core scope.

Lecture

Core concepts, inspectable examples, methods, formulas, and data structures.

Lab

Guided notebook work focused on inputs, outputs, validation, and errors.

Readings

The following core GIR reference will be used throughout the course.

  1. Purves, R. S., Clough, P., Jones, C. B., Hall, M. H., & Murdock, V. (2018). Geographic information retrieval: Progress and challenges in spatial search of text. Foundations and Trends in Information Retrieval, 12(2–3), 164–318. https://doi.org/10.1561/1500000034

Weekly Schedule

WeekGroup TueGroup FriTopicLecturer

No make-up exam!

Grading

Participation10%

Submit a lab checkpoint for each class by 23:59 on the day of the class.

Quiz15%

Held in Week 4.

Midterm exam30%

Held in Week 6.

Project proposal15%

Details released in Week 8 · team proposal due in Week 9.

Final project30%

Team presentation in Week 11.

Further details and submission instructions will be announced in class and on Moodle.

Tools & Data

PythonCore programming environment
JupyterLectures, examples, and labs

Course Platforms

This website

Public syllabus, weekly topics, slides, notebooks, and readings.

Moodle

Announcements, submissions, deadlines, and communication.