2

Can somebody tell me where I can find small Higgs twitter dataset.The Large one is present on the Stanford website but because of its large size, I am unable to create and display graph using matplotlib and NetworkX as it is taking very much time.

Basically, I need follower/followee dataset plus retweet dataset.The purpose is for modelling spread of the scientific rumour.Any type of help would be appreciated.

1
  • 1
    What is the Higgs twitter dataset? Please add a link.
    – user4293
    Commented Nov 9, 2017 at 8:33

1 Answer 1

2

If you already downloaded the big dataset, I recommend you sample the data (reduce the dataset) yourself. There are different approaches that you can use:

  1. Randomly sample edges (node1, node2, attributes..). This will destroy the characteristics of the network, so I don't recommend it.
  2. Randomly sample nodes and then keep all the transaction that include those nodes. Again this will change some characteristics of your network, but the result is already much better and you probably keep the sufficient characteristic for rumor spread.
  3. Slice by timestamp. You do not consider all the data from eg. 2010 to 2017, but only slice e.g. May 2015 to Nov 2015. This is the best approach, since it keeps all the characteristics of the network with regard to some point in time.

Hope this helps.

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.