James Allen-Robertson's Projects
The data journalism platform with built in training
Clustered Latent Dirichlet Allocation, a data decomposition approach to topic modeling in parallel
Collect and revisit web pages.
Set of python scripts which parse the Venona.com raw cypherpunks archive files into a structured database of threads.
Supplementary materials for McLevey 2021 Doing Computational Social Science (Sage, UK).
Code related to the project Encrypting Human Rights by A. Stevens and J. Allen-Robertson
Scrapes posts and comments from public Facebook pages.
A small script designed to take either a .csv of Tweet ids, or the export from Gephi's TwitterStreamingImporter Plugin and download related Tweet media.
Cluster images based on image content using a pre-trained deep neural network and hierarchical clustering
A small script to transform an HTML export of highlighted passages from the Amazon Kindle Reader App, into a structured text file.
A basic wrapper to simplify interacting with a local Memgraph instance using Python.
Scripts for the quantiative visual analysis of Twitter Media
Scripts developed for large-scale sampling of visual media for the project "Representing environmental harm and resistance on Twitter: The case of the TAP pipeline in Italy"
OnionScan is a free and open source tool for investigating the Dark Web. This fork has removed the capacity to snapshot image data.
Tools for drawing directed network graphs using plotly
Jupyter Notebooks for the Python Data Science Handbook
Python Implementations of Word Sense Disambiguation (WSD) Technologies.
Large scale graph compression and summarization tool for research and analysis.
Project to classify tweets on @realDonaldTrump as either written by Trump or by his staff
A small project that uses a Neural Network to predict when a tweet was written by Donald Trump, and when it was written by his staff.
Twitter for Python!
A basic python based kit to gather tweets from the live Twitter stream.