A Python package for spatio-temporal analysis of social media contents
Project description
geoso
A Python package for collecting and spatio-temporal analysis of social media contents
- GitHub repo: https://github.com/MahdiFarnaghi/geoso
- PyPI: https://pypi.org/project/geoso/
- Documentation: https://MahdiFarnaghi.github.io/geoso
- Free software: MIT license
Introduction
geoso is a Python library, being developed to facilitate collection, cleansing, and spatial and spatio-temporal analysis of social media data.
The vision is that the library provided the possibility to download geo-tagged social media content into a database, e.g., PostgreSQL, preprocess the stored data, retrieve, and analyse the data.
Features
- Twitter
- Download tweets from Twitter Streaming API and save them into either a database or JSON Lines text files.
- Import tweets that were from JSON Lines text files into the database.
- Export tweets to CSV file.
- Clean tweets text in the database.
- Retrieve tweets from the database as pandas DataFrame.
Under development features
- Twitter
- Clean tweets text in the database.
- Detect tweets that were published by bots.
Scientific publications
If you are using this library, the following scientific publications could be of your interest.
-
Farnaghi, M., Ghaemi, Z., & Mansourian, A. (2020). Dynamic Spatio-Temporal Tweet Mining for Event Detection: A Case Study of Hurricane Florence. International Journal of Disaster Risk Science, 11, 378-393.
-
Ostermann, F. O. (2021). Linking geosocial sensing with the socio-demographic fabric of smart cities. ISPRS international journal of geo-information, 10(2), 1-22. [52].
-
Zahra, K., Imran, M., Ostermann, F. O. (2020). Automatic identification of eyewitness messages on twitter during disasters. Information processing & management 57 (1), 102107
-
Ghaemi, Z. & Farnaghi, M. 2019. A Varied Density-based Clustering Approach for Event Detection from Heterogeneous Twitter Data. ISPRS International Journal of Geo-Information, 8 (2).
Credits
- spaCy is used for cleaning texts.
- Tweepy is used to develop Twitter data retrieval functionalities.
- This package was created with Cookiecutter and the giswqs/pypackage project template and instructions from Python Packages book.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for geoso-0.0.11-py2.py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 813e0158eb04cd0ee1a93f10c11475fe2f295c947e964363cb892f6c07b31c08 |
|
MD5 | 4b3b903ef7a2066066ed459c9c7d899d |
|
BLAKE2b-256 | 925b4e65d3f231d103573079b9132104b865dbf1b5949840321fb1f0d47f2aa6 |