Social Media is a powerful presence in the world today and has been used for many positive reasons. Yet it has a darker side. Cyber-bullying and inappropriate tweets that go viral can have devastating effects on individuals and brands.
A 140-character tweet is easily taken out of context. This data visualization shows connections between Twitter users during a 'Twitter Storm'. This phenomenon can be thought of as the 21st Century equivalent of playground bullying but on a global scale where the 'playground' is the entire social media space.
An individual puts out a message that is either intentionally or un-intentionally provocative. One group of users responds negatively and attacks the individual. Others see what is happening and attempt to protect the original user. At some point the message goes viral as each users followers see and respond to either the original message or the comments made about it. The reach can quickly become truly global.
The Justine Sacco 'Twitter Storm' inspired Eye Of The Storm. She sent a racist and insensitive tweet to a few friends before boarding a plane to Africa. By the time she landed, she had become globally infamous, as her tweet went viral and caused a massive 'Twitter Storm' that ruined her life. This visualization is tracking a 'Twitter Storm' following the death of Margaret Thatcher, former Prime Minister of the UK. Pro Thatcher and anti Thatcher supporters are reacting to a negative tweet. Two distinct groups can be seen. In the center of the eye is the subject of the storm and their followers attempting to protect and support them. The larger group around the outside of the eye contains the attackers that are reacting negatively and even in a threatening manner. The dots (or nodes) are twitter user Idâ€™s and the lines (or edges) connect tweets using either Retweet (RT) or mentions.
This visualization shows a representation of a graph, although the layout parameters have been used to create a format that is unlike those typical used to display graphs. The data was downloaded using the twitteR package in R and collected over a period of around a week. From here the data was loaded into Teradata Aster and a small amount of cleansing and reformatting was carried out, for instance populating the 'To' field using text mining techniques if this information was contained in the text. Similar techniques were used to remove irrelevant tweets.
Aster Lens was then used to create the graph and parameters such as gravity and edge influence adjusted to create the final visual.
Christopher Hillman is based in London UK with his wife and two kids and is a Principal Data Scientist in the Advanced Analytics team at Teradata travelling extensively in the International Region.
His passion for analytics spans 20 years of experience working in the business intelligence and advanced analytics industries. Prior to Teradata Chris specialized in the Retail and CPGN vertical, working as Solution Architect, Principal Consultant and Technology Director. Chris currently works together with the Teradata Aster Centre of Expertise and is involved in start-up analytics for Big Data projects helping customers to unlock insights from their data including understanding where MapReduce or SQL is an appropriate technique to use.
As well as working for Teradata, Christopher is currently studying part-time for a PhD in Data Science at the University of Dundee applying Big Data analytics to the data produced from experimentation into the Human Proteome. His research area involves real-time analysis of Mass Spectrometer data using Parallel algorithms. Part of his duties at the University include lecturing on Hadoop and MapReduce coding.
You must be a registered user to add a comment. If you've already registered, sign in. Otherwise, register and sign in.