TTLocVis
TTLocVis: A Twitter Topic Location Visualization Package - Published in JOSS (2020)
Science Score: 95.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
○CITATION.cff file
-
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
✓DOI references
Found 3 DOI reference(s) in README and JOSS metadata -
○Academic publication links
-
✓Committers with academic emails
1 of 4 committers (25.0%) from academic institutions -
○Institutional organization owner
-
✓JOSS paper metadata
Published in Journal of Open Source Software
Scientific Fields
Repository
TTLocVis: Twitter Topic Location Visualization
Basic Info
- Host: GitHub
- Owner: xillig
- License: gpl-3.0
- Language: Python
- Default Branch: master
- Size: 3 MB
Statistics
- Stars: 6
- Watchers: 3
- Forks: 0
- Open Issues: 1
- Releases: 1
Metadata Files
README.md
TTLocVis
A Twitter Topic Location Visualization Python package
Summary
The package TTLocVis provides a broad range of methods to generate, clean, analyze and visualize the contents of Twitter data. TTLocVis enables the user to work with geo-spatial Twitter data and to generate topic distributions from Latent Dirichlet Allocation (LDA) Topic Models for geo-coded Tweets. As such, TTLocVis is an innovative tool to work with geo-coded text on a high geo-spatial resolution to analyse the public discourse on various topics in space and time. The package can be used for a broad range of applications for scientific research to gain insights into topics discussed on Twitter.
In general, Topic Models are generative probabilistic models, that provide an insight into hidden information in large text corpora by estimating the underlying topics of the texts in an unsupervised manner.
Firstly, the package allows the user to collect Tweets using a Twitter developer account for any area in the world. Subsequently, the inherently noisy Twitter data can be cleaned, transformed and exported. In particular, TTLocVis enables the user to apply LDA Topic Models on extremely sparse Twitter data by preparing the Tweets for LDA analysis by the pooling Tweets by hashtags.
TTLocVis provides options for automatized Topic Model parameter optimization. Furthermore, a distribution over topics is generated for each document. The distribution of topics over documents can be visualized with various plotting methods. The average prevalence of topics in the documents at each day can be plotted as a time series, in order to visualize, how topics develop over time.
Above this, the spatial distribution of Tweets can be plotted on a world map, which automatically chooses an appropriate part of the world, in order to visualise the chosen sample of Tweets. As part of the mapping process, each Tweet is classified by its most prevalent topic and colour coded.
How to cite
Kant, G., Weisser, C. and Säfken, B. (2020), TTLocVis: A Twitter Topic Location Visualization Package. Journal of Open Source Software, 5 (54), 2507, https://doi.org/10.21105/joss.02507.
Installation
Attention: Event though TTLocVis should run on Python 3.7 and 3.8, it was not fully tested under these conditions. We do recommend to install a new (conda) environment with Python 3.6.
The package can be installed via pip:
commandline
python pip install TTLocVis
Windows
After successful installation, the user must download the basemap package and install it manually via pip:
commandline
python -m pip install [path-to-the-downloaded-file/your-basemap-wheel]
Note: Do not copy the name of your basemap wheel from the above mentioned website into your python console! Write
it out manually!
The cpXX in the filenames refer to the python version you will use. An example for Python 3.6. would be the file
basemap-1.2.1-cp36-cp36m-win_amd64.whl Remember, TTLocVis is developed to run only on Python 3.6, 3.7 and 3.8.
Linux and iOS
Download basemap package version 1.2.1 and install it accordingly.
Documentation and Usage
You can find the current TTLocVis master branch documentation at our documentation website.
Community guidelines
Contributions to TTLocVis are welcome.
- Just file an Issue to ask questions, report bugs, or request new features.
- Pull requests via GitHub are also welcome.
Potential contributions include ways to further improve the quality of the LDA topics in handling the noisy Twitter data and an improvement of the loc_vis method in a way that it becomes independent form the basemap module.
Authors
- Gillian Kant
- Christoph Weißer
- Benjamin Säfken
License
TTLocVis is published under the GNU GPLv3 license.
Owner
- Name: Gillian Kant
- Login: xillig
- Kind: user
- Repositories: 1
- Profile: https://github.com/xillig
JOSS Publication
TTLocVis: A Twitter Topic Location Visualization Package
Authors
Centre for Statistics, Georg-August-Universität Göttingen, Germany
Centre for Statistics, Georg-August-Universität Göttingen, Germany, Campus-Institut Data Science, Göttingen, Germany
Centre for Statistics, Georg-August-Universität Göttingen, Germany, Campus-Institut Data Science, Göttingen, Germany
Editor
Tania Allard
Tags
Twitter Topic Modelling LDA Latent Dirichlet Allocation Visualization Spatial Modelling Geocoded Text Hashtag-Pooling Algorithm Natural Language Processing Machine LearningGitHub Events
Total
Last Year
Committers
Last synced: 7 months ago
Top Committers
| Name | Commits | |
|---|---|---|
| ChrisW09 | k****t@c****e | 66 |
| Gillian | g****t@g****m | 63 |
| Ben | b****e@u****e | 4 |
| Tania Allard | t****d@g****m | 2 |
Committer Domains (Top 20 + Academic)
Issues and Pull Requests
Last synced: 6 months ago
All Time
- Total issues: 2
- Total pull requests: 2
- Average time to close issues: 15 days
- Average time to close pull requests: about 4 hours
- Total issue authors: 1
- Total pull request authors: 2
- Average comments per issue: 1.0
- Average comments per pull request: 0.0
- Merged pull requests: 1
- Bot issues: 0
- Bot pull requests: 1
Past Year
- Issues: 0
- Pull requests: 0
- Average time to close issues: N/A
- Average time to close pull requests: N/A
- Issue authors: 0
- Pull request authors: 0
- Average comments per issue: 0
- Average comments per pull request: 0
- Merged pull requests: 0
- Bot issues: 0
- Bot pull requests: 0
Top Authors
Issue Authors
- sara-02 (2)
Pull Request Authors
- trallard (1)
- dependabot[bot] (1)
Top Labels
Issue Labels
Pull Request Labels
Packages
- Total packages: 1
-
Total downloads:
- pypi 8 last-month
- Total dependent packages: 0
- Total dependent repositories: 1
- Total versions: 1
- Total maintainers: 1
pypi.org: ttlocvis
TTLocVis: A Twitter Topic Location Visualization package
- Homepage: https://github.com/xillig/TTLocVis
- Documentation: https://ttlocvis.readthedocs.io/
- License: GNU GPLv3
-
Latest release: 0.1.0
published almost 6 years ago