Analyzing Co-Occurrences

A common question we hear at Texifter is, “How can one derive co-occurrences in a slice of data?” DiscoverText makes this process relatively easy – when starting with one known variable. For instance, one might like to see which hashtags or links or keyword co-occur with other hashtags, links, and keywords in a given archive. In this case below, it is done with an archive of Romney tweets.

To derive this insight, DiscoverText users can use the “TopMeta Discovery” function to quickly “slice” a timeframe of their data into a bucket (a saved search result).

Once the “slice” is bucketed, users can perform the same TopMeta function across the hashtags (or other metadata fields) of that specific data.

Once the hashtag (or other metadata item) is selected, users can – once again – perform a quick filter, and bucket the data that matches a particular metadata item.

Finally, with the known variable isolated to a bucket, users can easily utilize functions such as TopMeta or the interactive cloud explorer in DiscoverText to pull out co-occurring links, hashtags, keywords, and other substantive insight and analyze the tweets that reference such data.

If you have any questions, feel free to email me at josh@discovertext.com.