Analyzing social media data often requires processing text-based messages to categorize their content, eliminate false positives, assess the sentiments expressed, and perform related functions. Such efforts require extracting context from textual data, a capability offered through InfoSphere BigInsights, an IBM platform based on the Apache Hadoop project. This article introduces you to the text analytic development and runtime environments of BigInsights, highlighting how you can use Eclipse-based tools to create, test, and publish text extractors on your cluster so you can analyze content relevant to your application.

Authors: Cynthia M. Saracco, Gary Robinson, and Vijay Bommireddipalli

Link: http://www.ibm.com/developerworks/library/bd-socialmediabiginsights/index.html

Join The Discussion

Your email address will not be published. Required fields are marked *