Mining the StockTwits home stream: Part III

bipartite4

Previously we highlighted several ways to mine your StockTwits home stream. Today we wanted to visualize the relationship between StockTwits users and the cashtags they tweet the most about. The graph above is a bipartite graph: the blue nodes represent StockTwits users we follow on our @MKTSTK profile, while the green nodes are different cashtags. The thicker the line joining a user and a cashtag, the more times the user sent a tweet related to the cashtag. The graph uses tweets for the last week. Thus, the graph shows which topics are most important to the users we follow.

For example, the thickest line is drawn between @FinancialJuice and the $MACRO cashtag which is used for referencing macroeconomic events. The $EURUSD tag is another favorite of @FinancialJuice as well as user @Rooster360. We can also see strong links between the cashtag for $AAPL and StockTwits founder @HowardLindzon. Other users also share a strong link with $AAPL, including @BeckyHiu.


Want to learn how to mine social data sources like StockTwits, Twitter, Google Trends, and Estimize? Make sure to download our new book Intro to Social Data for Traders by our very own Thomas Pendergrass


We also wanted to visualize the relationship amongst StockTwits users. To do so, we extracted the users who got mentioned in each tweet, then drew a link between accounts if one account mentioned another user in one of their tweets. The more times an account mentioned another user, the thicker we drew the line connecting the two users. We can see that the @StockTwits and @HowardLindzon accounts do a great job referencing a wide array of other users. A quick scan of our home stream shows that these two accounts are responsible for highlighting the most interesting content on StockTwits. The most connected accounts serve as a valuable bridge for content between user cliques:

whoswho5

Mining the StockTwits Homestream Series

Part I: Minimum Spanning Trees
Part II: Filtered Correlation Network for the S&P 500
Part III: Information Flow

1 reply »

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s