Mining the Talk: Unlocking the Business Value in Unstructured Information

Description

This is the first book to provide techniques and approaches for mining knowledge from unstructured business information and the business value of this analysis. Mining the Talk describes a fundamentally new approach to mining knowledge from unstructured business information. This unstructured information in "free form text" that the authors refer to as "talk". It's simply the way humans have been communicating with each other for thousands of years, and it's the most prevalent kind of data to be found. Potentially, its also the most valuable, because hidden inside the talk is little bits and pieces of important information, which if aggregated and summarized could communicate actionable intelligence about how any business is running, how its customers and employees perceive it, what is going right and what is going wrong, and possibly solutions to the most pressing problems the business faces. These are examples of the gold that is waiting to be discovered if business can only "Mine the Talk". The primary methodology employed centers on the creation of natural classifications (taxonomies) of the data objects. The book illustrates that the only way to insure the "naturalness" of taxonomies is through expert human intervention at every stage of the taxonomy generation and modeling process. After giving a high level overview the approach, the book dives into a series of real world examples showing how the mining techniques work in practice.

《挖掘對話》是第一本提供從非結構化商業資訊中挖掘知識的技術和方法，以及這種分析的商業價值的書籍。本書描述了一種從非結構化商業資訊中挖掘知識的全新方法。這些非結構化資訊以「自由形式文本」的形式存在，作者稱之為「對話」。這只是人類數千年來一直在彼此溝通的方式，也是最常見的資料形式。潛在地，它也是最有價值的，因為在對話中隱藏著重要信息的一點一滴，如果進行匯總和總結，就可以傳達關於企業運營方式、顧客和員工對企業的看法、問題和可能的解決方案等可行的情報。這些都是等待被發現的寶藏，只要企業能夠「挖掘對話」。主要的方法是通過創建資料對象的自然分類（分類法）來實現。本書說明了確保分類法的「自然性」的唯一方法是在分類法生成和建模過程的每個階段都進行專家人工干預。在概述了這種方法之後，本書深入介紹了一系列實際案例，展示了挖掘技術在實踐中的應用。