Natural language processing methods applied to big data text collections selected from billions of tweets and terabytes of webpages will produce useful summaries.

• Cluster-based processing with Hadoop, Solr, and other tools
• Tweet and webpage analysis
• Text pre-processing: stop word removal, stemming/lemmatization
• Text analysis packages: part of speech, named entities, topic analysis
• Natural language processing toolkit
• Text classification, document clustering
• Approaches to summarization, including extractive, abstractive, deep learning

Prerequisite: CS3114 or CS3654 or CS4624.

For more information see: http://fox.cs.vt.edu/CS4984Fall2018.pdf