Dataset

Twitter Wordbag

Added By Infochimps

The service for this API has ceased

Our apologies for the inconvenience this may cause.

Twitter Wordbag unlocks word importance and frequency data across the Twitter universe. Discover any Twitter user’s word usage frequency, or most characteristic words, relative to the average of all Twitter users, by simply querying a screen name or user ID. This Twitter word API allows you to find word usage by individual user, and access valuable statistics about that users’s language propensities on Twitter.

Use the Twitter Wordbag API to design custom visualizations based upon unique users and their individual Twitter language usage or most characteristic terms. For example, build a word cloud that can be customized to individual user language, or create a widget to visualize a user’s Twitter influence and their most characteristic terms that garner that influential position.

Sign up for the API today. Click on “App Gallery” to check out the amazing capabilities of this data. See what others have created using the Twitter Word Usage API!


Methodology

Twitter Wordbag is a collection of tokens (terms) that a Twitter user tweets more frequently than the average user. For example the @infochimps Wordbag would include the tokens “viz”, “opendata”, “supercomputer” and “cluster”, since those are terms used more often by @infochimps than by the average Twitter user. Tokens that are used often amongst all Twitter users though, for example @infochimps tweets “the” often, but not much more or less than it is tweeted across all of Twitter, would not be included. The tokens give insight into the kind of conversations users are engaging in and their interests.


Twitter Analysis APIs

Looking for other ways to measure Twitter influence across the social network? The Infochimps have developed numerous other Twitter analysis APIs:

  • Trstrank : measure user reputation, importance and influence relative to the entire Twitter network.
  • Twitter Strong Links : Meausre a user’s engagement and connection strength, relative to other Twitter users
  • Twitter Influence Metrics : how influential and engaged is a particular Twitter user, relative to all others in the social network?

Use Cases

  • Build a word cloud for a Twitter user
  • Find users interested in a particular topic
  • Create custom advertising according to words used by your customers
  • Build a library of closely related vocabulary to a particular keyword

The Twitter analysis generated in this API is outlined in the terms found below in the “API Documentation” tab. For each query, responses are found below in “Response Documentation.” Each response includes a term followed by the score for how characteristic or frequently that term is used by the queried screen name or user ID. The calculation is analogous to TF-IDF, in that the assigned score indicates the importance and strength of that term for a given user, relative to the corpus or full collection of Twitter word usage.

The API allows for search functionality that returns only the highest frequency 100 Twitter term results for your custom query, and screens out the rest. The simplicity of the API provides ease of use with connecting your program or tool to the Twitter data. Once the API key is implemented in your code, you’ll never have to worry about refreshing the feed or updating the request for new information.

Test the functionality of the API now using the “Sample Request” below. Try one of the samples below, or enter your own details in the Sample Request:

screen_name: infochimps
user_id: 15748351