Interesting article posted recently in MIT Technology Reviews. What kind of metrics would help detect such tweets? We think the following might be useful:

1. Local time (like late at night)
2. Whether a picture or not is associated with the tweet
3. Whether a link or not is associated with the tweet
4. Number of typos for the tweet in question, compared with average for the user in question 
5. Frequency of tweets (sudden spike) for user in…

This long article with a lot of source code was posted by Suraj V Vidyadaran. Suraj is pursuing a Master in Computer Science at Temple university primarily focused in Data Science specialization. His areas of interests are  in sentiment analysis, data visualization, big data and machine learning.

This data is obtained from UCI Machine learning repository. The purpose of the…