In an online website, some users may create multiple fake users to promote (like/comment) on their own comments/posts. For example, in Instagram to make their comment be seen at the top of the list of comments.
This action is called Sockpuppetry. https://en.wikipedia.org/wiki/Sockpuppet_(Internet)
What are some general algorithms in unsupervised learning to detect these users/behaviors?
In my experience in suggest for this problem to use supervised by using the Artificial Neural Networks, we can you find different architecture have the background or inspiration from comportment of human, or example NN, CNN, RNN... etc.
I hope that be Claire for you. @ Issa Annamoradnejad
Dear Issa Annamoradnejad , you can apply neural networks (NNs) Generative adversarial networks (GANs), Deep belief Nets (DBN), and many more, you can just browse in google scholar and will see a list of available most popular algorithms for unsupervised learning perspectives. However, GANs has a strong capability to perform well when to handle unsupervised problems.
Dear Issa Annamoradnejad ,
Look the link, maybe useful.
https://www.ijitee.org/wp-content/uploads/papers/v9i1/A4437119119.pdf
Article DETECTING FAKE ACCOUNT ON SOCIAL MEDIA USING MACHINE LEARNIN...
Regards,
Shafagat
Dear Issa Annamoradnejad,
I think Gaussian SVM algorithm ( Explain in below paper ) would be a better to predict the fake users. Please have a look on this paper mentioned Article Identifying Fake Accounts on Social Networks Based on Graph ...
Its a nice paper to start with
Thank you Muhammad Nabeel, Shafagat Mahmudova Akash Awasthi
I will follow up on your suggestions.
I suggest you follow https://core.ac.uk/download/pdf/76529027.pdf
Chapter Social Networks Fake Profiles Detection Using Machine Learni...
How do you counter 'faking' turning into 'real' hookers in this context? ... with automated 'switch'? hmmm
Dear Issa Annamoradnejad , I think Deep Belief Net, would be quit good for detecting fake users, also you can use DeepFake Detection CNN. take a look at the following links:
https://en.wikipedia.org/wiki/Unsupervised_learning
https://www.scientificamerican.com/article/detecting-deepfakes1/
Issa Annamoradnejad , this a good question. One colleague from Canada told me there is one list of Twitter users marked as bots/fakes accounts then if you can identify the pattern they follow, it can be useful for your work.
In my experience in suggest for this problem to use supervised by using the Artificial Neural Networks, we can you find different architecture have the background or inspiration from comportment of human, or example NN, CNN, RNN... etc.
I hope that be Claire for you. @ Issa Annamoradnejad
- Badges
- Science topic
- Similar topics
- Computer Science