DEEP TEXT: USING TEXT ANALYTICS TO CONQUER INFORMATION OVERLOAD, GET REAL VALUE FROM SOCIAL MEDIA, AND ADD BIG (GER) TEXT TO BIG DATA

摘要

In Deep Text, Tom Reamy, a professional text analytics consultant and erstwhile Information Architect for Charles Schwab's corporate intranet, attempts a broad overview of current practices and implementation methods in enterprise text analytics. In the first of five parts, he offers a definition of text analytics that, skirting only the outermost edges of computer and data science, encompasses, and yet shuns, the otherwise rich fields of text mining, Natural Language Processing, neural networks, and deep learning algorithms. He describes how his early disenchantment with the slow progress of high-quality semantic text interpretation through machine learning and Artificial Intelligence and his skepticism of algorithm-based text analysis has led him to develop a framework for "deep text" methods. These "deep text" methods comprise a highly context-driven taxonomy- and rule-based text categorization approach, and, as Reamy explains, successfully advance corporate knowledge-management strategies by producing more actionable business intelligence than the "auto-categorization" approaches currently offered by various software vendors.