search

bellecarrell / twitter_brand

In developing a brand on Twitter (and social media in general), how does what you say and how you say it correspond to positive results (more followers, for example)?
0 stars 1 forks source link

Meeting agendas #1

Closed bellecarrell closed 6 years ago

bellecarrell commented 6 years ago

03/23/18 Unigram, bigram, trigram counts in /exp/acarrell/twitter_brand/aggregate_out/.

Questions:

  1. Should I grab users for all or select subset of uni/bi/tri? (I'm thinking both atm, with subset first while other is running)
  2. What is the percentage of users that are still active when pulling IDs from this dataset? (probably not answerable, but just curious)
  3. Based on looking at data, starting to see a few high-level groups that might work (arts, politics, nationalities*, trends [succulents]). Good starting subsets to cultivate?
bellecarrell commented 6 years ago

notes: -anaconda environment with dependencies on grid (@abenton could you point me to setup you have?) -sort by unique users answers:

  1. subset, then all
  2. you'll see
abenton commented 6 years ago

My environments are exported to /home/hltcoe/abenton/py2_environment.yaml and /home/hltcoe/abenton/py3_environment.yaml

You should be able to recreate these environments with:

conda env create -f py2_environment.yml conda env create -f py3_environment.yml