| Course ID: | GEOG 4593/6593. 3 hours. |
| Course Title: | Geospatial Semantics and Geo-Text Mining |
Course
Description: | Different geospatial semantics, text mining, and natural language processing techniques and how they can be applied to different geo-text data. Topics include place name recognition, place name disambiguation, gazetteer and geospatial knowledge graphs, TF-IDF, topic modeling, sentiment analysis, word embedding, and deep learning-based language models. |
| Oasis Title: | Geospatial Semantics |
| Undergraduate Prerequisite: | Permission of department |
| Graduate Prerequisite: | Permission of department |
| Undergraduate Pre or Corequisite: | CSCI 1301-1301L or CSCI 1301E or CSCI 1360 or CSCI 1360E or GEOG 4590/6590-4590L/6590L or GEOG 4590E/6590E or GEOG 4591/6591 |
| Graduate Pre or Corequisite: | CSCI 1301-1301L or CSCI 1301E or CSCI 1360 or CSCI 1360E or GEOG 4590/6590-4590L/6590L or GEOG 4590E/6590E or GEOG 4591/6591 |
| Grading System: | A-F (Traditional) |
|
| Course Objectives: | 1) Students will develop an integrated understanding of various geospatial semantics, natural language processing, and text mining techniques.
2) Students will gain practical experiences by collecting and analyzing geo-text data (e.g., geo-tagged tweets, Yelp Reviews, neighborhood reviews) by using different geospatial text mining methods.
3) Students will be able to integrate these geospatial semantics techniques into real-world GeoAI projects. |
| Topical Outline: | 1) The emergence of geo-text data
2) An overview of geospatial semantics and text mining
3) Place name recognition and disambiguation
4) Gazetteer and geospatial knowledge graph
5) Geospatial clustering and segmentation
6) TF-IDF (term frequency-inverse document frequency)
7) Topic modeling
8) Sentiment analysis
9) Word embedding (e.g., Word2Vec) and large language model (e.g., Transformer, BERT, GPT-3) |