Jonathon Morgan
Jonathon Morgan
Recently @ccarey created a network and pulled down recent tweets for the current alt-right presence on Twitter. This is issue to begin exploring that datasets - topic modeling, network modeling,...
Build a social media hate speech text classifier, maybe using this data from Crowdflower as a starting point (https://data.world/crowdflower/hate-speech-identification). I (Jonathon) am happy to standup the classifier behind a REST...
"Hope speech" is counter-speech - messages posted in response to hate speech on a social platform. This task is to train a classification model that can identify hope speech. One...
Using `collect-social` (https://github.com/data4democracy/collect-social), or a library you're more familiar with (@gati/@jonathon in Slack can help with this), grab the posts, comments, users, etc from far-right/alt-right Facebook pages. A list of...
The D4D community has acquired a few million recent 4chan posts. This issue is to explore that data, using techniques such as topic modeling, network analysis, social media analytics (who...
Which nodes of a given community are most influential? How does information or sentiment spread within communities? When did a given community emerge? Did it emerge from another community? Is...
What are the linguistic characteristics of a given community? How have linguistic characteristics (idioms, hashtags, etc.) emerged and diffused within a given community?
What methods are most accurate for detecting bots within a given community? What are the observed operational characteristics (i.e. objectives) of bots within a given community? Are conversational bots active...
There are a number of crime datasets in the Austin Open Data Portal https://data.austintexas.gov/browse?q=crime. Decide which data to collect, and check with @wwymak for information about a common data format...