assemble

assemble copied to clipboard

Community detection using pre-implemented algorithms

2

The idea is to list and test classic, pre-implemented algorithms for community detection: - Louvain detection using this implementation https://github.com/taynaud/python-louvain/ - hierarchical clustering https://networkx.github.io/documentation/networkx-1.10/examples/algorithms/blockmodel.html - others? Testing to be done...

henripal

Community detection using spectral matrix analysis and clustering

9

The idea here is to treat the graph matrix as a feature matrix and to use traditional dimension reduction/clustering techniques on these features. An example workflow would be: - build...

henripal

tokenize and analyze 2016 presidential candidate rhetoric for comparison with extremist communities

7

Anyone interested in doing some basic word/n-gram analysis, topic models, etc. on presidential candidate speeches and press releases? Would be really interesting to see which candidates were/weren't plugged in to...

kshaffer

Community detection using non-negative matrix factorization

6

Initially suggested by @hadoopjax in https://github.com/Data4Democracy/discursive/issues/4 - test and implement non-negative matrix factorization using both graph and textual features as described in https://arxiv.org/pdf/1608.01771v1.pdf - testing to be done on the...

henripal

Tweet text data parsing/cleaning for nlp

1

- Look through data available at https://data.world/data4democracy/far-right as data from the discursive project Some of the tasks we might do are: - Stem - Tokenize - Remove stop words -...

wwymak

Word2Vec models

3

Construct word2vec model with tweets for groups of people (e.g. far right) and compare with models trained on the overall twitterverse (e.g. http://fredericgodin.com/papers/Named%20Entity%20Recognition%20for%20Twitter%20Microposts%20using%20Distributed%20Word%20Representations.pdf) Some things to try: clustering tweets with...

wwymak