Workshop
Thursday, April 2, 2015 in San Francisco
Full-day: 9:00am - 4:30pm
Room: Salon 10-11
Text Analytics:
From Getting Started to Successful Applications
Participants will receive a free copy of Tom’s book - Text Analytics: How to Conquer Information Overload, Get Real Business Value from Social Media, and turn Smart Text into Big Data
Intended Audience:
Anyone interested in getting greater value from unstructured text – developers, data and predictive analysts, business – from decision makers to business analysts
Knowledge Level:
No previous experience is required but knowledge of information technologies or techniques in a range of areas will deepen your experience – from search to predictive analytics.
Workshop Description
Text Analytics continues to grow over 20% a year and while we have already seen one hype-bust cycle with sentiment analysis, the field is experiencing a steady growth both in the number of organizations utilizing it, but also in the range of new types of applications.
This workshop covers all you need to know whether you just want to build a single application or you want to build a text analytics foundation for a complete range of applications. We will cover:
- The basic analytic techniques from machine learning to sophisticated rule building.
- A survey of the vendor space of text analytics companies including new Cloud-based social media companies
- An evaluation process for choosing the right text analytics software for your organization – and how to integrate it with other information applications such as search or content management
- An iterative development process that you can use to go from raw content to finished applications
- Best practices for different development techniques and the most common pitfalls and how to avoid and/or overcome them
- The range of types of applications that can be built with text analytics with multiple case studies of the most exciting new applications
Tom will dive into the guts of text analytics offerings and demonstrate how organizations can employ multiple methodologies (from advanced text mining algorithms to usability of the software to the economic health of the vendor) to both select the best platform for your project(s) and to get a quick start on building your first application.
Using a variety of real world examples, we will cover such practical application approaches as:
- How to use text analytics to improve search with better relevance ranking as well as using extraction to feed a faceted navigation interface
- How to add intelligence and sophistication to social media analysis through deeper auto-categorization capabilities and disambiguation to feed advanced predictive analytics
- How to use a combination of auto-categorization, entity extraction, sentiment analysis, and even auto-summarization to power applications that range from customer support to legal review to business intelligence
- How to use text mining techniques to not only support advanced analytics application but also to build semantic resources that can be used in a broad range of information applications.
- What additional structural resources you will need such as taxonomies or ontologies
- Who are the right people to develop and maintain those resources
- How to begin to develop taxonomies and categorization catalogs when you don’t have any
- And how to adapt those resources if they do exist in your organization.
We will also look at text analytics in a broader organizational context:
The workshop will include a series of hands on exercises in which participants will explore how to develop text analytics rules and resources and refine them.
Finally, we will take quick but deep dive into some of the latest theoretical developments in linguistics and cognitive science that have surprisingly practical implications. These include such concepts as semantic networks, natural level categories, intertwingedness, and the use of ensemble methods that mimic how the human brain works.
Whatever your interest in text analytics, this workshop will help you learn new skills and develop your existing skills to new heights.
Instructor
Tom Reamy, Program Chair Text Analytics World
Chief Knowledge Architect
KAPS Group. LLC
Tom Reamy is currently the Chief Knowledge Architect and founder of KAPS Group, a group of knowledge architecture, taxonomy, and text analytics consultants. Tom has 20 years of experience in information architecture, enterprise search, intranet management and consulting, education software, and text analytics consulting. Tom's academic background includes a Master's in the History of Ideas, research in artificial intelligence and cognitive science, and a strong background in philosophy, particularly epistemology. He has published articles in various journals and is a frequent speaker at knowledge management conferences. When not writing or developing KM projects, he can usually be found at the bottom of the ocean in Carmel taking photos of strange creatures.
