Analysis updated 2026-08-03 · repo last pushed 2020-03-22
Trace common locations and transportation routes among confirmed COVID-19 cases in a specific city.
Map patient movement patterns to identify transmission hotspots for data journalism.
Search and analyze structured patient trajectory data to understand how the virus was spreading across China.
| hiyouga/covid-19-tracker | 0xallam/posthog | 0xallam/search-engine | |
|---|---|---|---|
| Stars | 1 | 1 | 1 |
| Language | — | Python | C++ |
| Last pushed | 2020-03-22 | 2026-03-26 | 2023-08-23 |
| Maintenance | Dormant | Maintained | Dormant |
| Setup difficulty | hard | moderate | hard |
| Complexity | 2/5 | 3/5 | 3/5 |
| Audience | researcher | pm founder | developer |
Figures from each repo's GitHub metadata at analysis time.
The project has no setup instructions or documentation on data format and distribution, so users must figure out how to access and use the data on their own.
The repository behind the Beihang University big data research team's COVID-19 tracker is a project that organizes information about confirmed COVID-19 patients in China. The team collected publicly available travel and activity histories for 4,626 diagnosed patients and turned that unstructured text into a clean, organized dataset. The goal is to help researchers, public health officials, and the public understand how the virus was spreading by making patient movement data easy to search and analyze. The project works by taking raw descriptions of where patients went and what they did, then using natural language processing, a type of artificial intelligence that can read and extract meaning from text, to pull out key details. For each patient, it captures basic information like gender, age, home location, occupation, and whether they had contact with Wuhan or Hubei province. It also records their movements, including timestamps, locations, modes of transportation, and events they attended, along with any known relationships between patients. Public health researchers, epidemiologists, and data analysts would be the primary users of this kind of dataset. For example, an epidemiologist studying how COVID-19 spread through a specific city could use the structured trajectory data to trace which locations or transportation routes were common among confirmed cases. A data journalist could also use it to map out transmission patterns or identify hotspots. By having all of this information in a structured format rather than scattered across news reports and government notices, it becomes far easier to spot trends and draw meaningful conclusions. The project page itself does not include any documentation beyond the description of the dataset. There are no setup instructions or usage guidelines provided, so it is unclear how the data is formatted or distributed. What is notable is that it represents a serious effort to apply AI-powered text extraction to a real-world public health crisis, transforming messy, scattered patient reports into something that could support meaningful analysis.
A dataset of travel and activity histories for 4,626 COVID-19 patients in China, built using AI to extract structured details from raw text reports for researchers and analysts.
Dormant — no commits in 2+ years (last push 2020-03-22).
No license information is provided, so the default copyright terms apply and usage rights are unclear.
Setup difficulty is rated hard, with roughly 1h+ to a first successful run.
Mainly researcher.
This repo across BitVibe Labs
Verify against the repo before relying on details.