2018 Agenda

New Fact Extraction Capabilities of PolyAnalyst

Presented by Margaret Glide, Computational Linguist / Data Analysis Consultant
Tell the story behind your information extractions: make real world connections between your Entity Extraction results and explore the complex web of information relationships with the new Fact Extraction node.

DEMO: Performing Customer Survey Analysis – Electronic Devices

Presented by Brian Howard, Sales Manager
Effective and wholesome customer survey analysis requires the analysis of open-ended text responses. And for most companies like the globally reaching electronics distributor we will be using as an example, sentiment analysis is a focal point for understanding their customers. Join me to see a demonstration of a text analysis project and web report showcasing techniques for building custom dictionaries, extracting key topics from data-driven analysis, and visualizing and tracking customer satisfaction in multiple ways.

Computational Linguistics for Advanced Text Analytics

Presented by Rebecca Hale, Lead Computational Linguist
This presentation goes beyond the basics of Text Analytics by taking an in-depth look at Computational Linguistics, the bones of text analysis. Attendees will learn how understanding Computational Linguistics increases the accuracy of analysis, creating richer data and leading to better business discoveries.

News Analysis: Monitoring Customers and Investees

Presented by Jason Liu, Senior Data Analysis Consultant

This presentation illustrates how a news analysis solution helps a major bank to monitor its customers and investees.

DEMO: Data-driven Techniques for Improving Results of a Survey Analysis Project

Presented by Kathryn Verhoeven, Data Analysis Consultant
A wealth of valuable information is hidden in the unstructured text data of customer surveys. This session will demonstrate various data-driven analysis techniques that can be used to improve a survey analysis project.

New Text Clustering in PolyAnalyst™: Latent Semantic Analysis

Presented by Sergei Ananyan, CEO
Most techniques for relating textual information rely on intellectually created links such as chosen keywords, authority indexing terms, or bibliographic citations. Similarity between semantic content of whole documents offers an attractive alternative. Latent semantic analysis provides an effective dimension reduction method for the purpose of topic modeling.

Panel Discussion: Applications and Difficulties in Advanced Analytics

Speaker Panel / Round Table
Guest Speakers, Jonathan Frey & Eric Su, will be discussing the application & difficulties in advanced analytics

DEMO: Best Practices for Creating a Taxonomy for Customer Survey Analysis

Presented by Bipin Inamdar, Senior Data Analysis Consultant
Learn how to build taxonomies efficiently for gaining meaningful insights into natural-language feedback from your customers.

PDL Overview: Pattern Definition Language for Building Precise Queries

Presented by Min Chen, Data Analysis Consultant
Learning how to proficiently use PDL, PolyAnalyst’s proprietary search query syntax, will greatly help users harness the power of PolyAnalyst’s text mining capabilities. This session will highlight techniques for creating better search queries in PolyAnalyst.

Domain-Specific Sentiment Analysis

Presented by Elli Bourlai, Computational Linguist / Data Analysis Consultant
This presentation discusses the benefits and challenges associated with sentiment analysis and presents the new domain-specific Sentiment Analysis solution of PolyAnalyst.

DEMO: Building Informative Web Reports in PolyAnalyst™ – Survey Analysis

Presented by Wilson Zhou, Data Analysis Consultant

Learn how to build informative web reports explore the result of a voice of customer survey. You will learn our new features of web reports, and how it is empowered within PolyAnalyst™.

Best Practices for Finding Important Patterns with PDL

Presented by Yi Wang, Senior Data Analysis Consultant
This presentation will review a variety of PDL functions with parameter settings for building complex and advanced queries.

Social Media Analysis: Monitoring Product Reviews

Presented by Kathryn Verhoeven, Data Analysis Consultant
Social media use continues to grow, with consumers increasingly interacting directly with companies about their products and services. This presentation will highlight the use of data and text analysis to monitor Facebook, Twitter, and social news sources and how companies can gain useful insights.

DEMO: Employee Survey Analysis

Presented by Bipin Inamdar, Senior Data Analysis Consultant
Case study of how PolyAnalyst is used for gaining operational insights from periodic and exit interviews of the employees of a major US healthcare provider.

DEMO: Dictionary and Ontology Use and Management in PolyAnalyst™

Presented by Min Chen, Data Analysis Consultant
This demo will cover how different dictionaries including ontologies are maintained and used in PolyAnalyst.

Warranty Claims Analysis: Detecting Root Causes and Emerging Issues, Detecting Fraud

Presented by Bipin Inamdar, Senior Data Analysis Consultant
Warranty claims provide a window into how your product or service is working for the customer. PolyAnalyst makes consuming warranty claims data – which is often textual, technical and messy – easy.

DEMO: Sentiment Analysis with PolyAnalyst™

Presented by Margaret Glide, Computational Linguist / Data Analysis Consultant
How do customers feel about your products or services? This session shows you three methods to effectively perform Sentiment Analysis within PolyAnalyst™.

When PDL is Not Enough: Introducing XPDL, the Language for Fact Extraction

Presented by Rebecca Hale, Lead Computational Linguist
This presentation will explore the need for XPDL to extract information, rather than only classifying it with PDL, and discuss different types of entities and relationships that can be designed for domain-specific knowledge targeting in text analysis systems.

Demo: Analysis of Automobile Repair Notes to Improve Engineering & Fraud Detection

Presented by Zhen Li, Data Analysis Consultant
We will walk you through the process of automobile repair notes in PolyAnalyst using a demo PA project. Entity extraction of the notes, significant issues with different car model and dealer anomaly behavior detection will be included.

DEMO: Social Media Analysis – Product Reviews

Presented by Min Chen, Data Analysis Consultant
This demo will go over an actual project on social media analysis of product review data, the main focus will be how to efficiently create taxonomy according to existing categorization structure and adjust queries from poor quality training labels.

XPDL: New Language for Accurate Information Extraction

Presented by Margaret Glide, Computational Linguist / Data Analysis Consultant
How can we use XPDL to give us the most accurate business insights? In this presentation, we’ll see how we can use the default entities and some simple XPDL principles to leverage your specific business needs.

Guest Speaker – Discovering Hidden Trends in Consumer Eye-tracking Data

Presented by Nobuyuki Fukawa, Associate Professor of Marketing
As visual marketing gains a more critical role in marketing communications, consumer eye-tracking data has been utilized to assess the effectiveness of those marketing efforts. With eye-tracking data, researchers can capture consumers’ visual attention effectively and may predict their behavior better than with traditional memory measures. However, due to the complexity of data: its volume, velocity and variety, known as 3Vs of Big Data, marketers have been slow in fully utilizing eye-tracking data. These data properties may pose a challenge for researchers to analyze eye-tracking data, especially gaze sequence data, with traditional statistical approaches. Commonly, researchers may analyze gaze sequences by computing average probabilities of gaze transitions from a particular area of interest to another area of interest. When the variance of gaze sequence data in the sample is small, this method would uncover a meaningful “global” trend, a trend consistent across all the individuals. However, when the variance is large, this method may not enable researchers to understand the nature of the variance, or the “messiness” of data. In this presentation, first, to overcome this challenge, we propose an innovative method of analyzing gaze sequence data. Our proposed method enables researchers to reveal a “local” trend, a trend shared by only some individuals in the sample. Second, we illustrate the benefits of our method through analyzing gaze sequence data collected in an advertising study. Finally, we discuss the implications of our proposed method.

DEMO: Risk Management: Syncing Marketing Materials and Government Regulations

Presented by Jason Liu, Senior Data Analysis Consultant
This demo shows how a production solution solves specific task, and how the key elements of the production solution are created.

XPDL Example – Repair Notes Analysis: Extracting Relations Between Parts and Issues

Presented by Di Cao, Data Analysis Consultant
Learn how to use XPDL to efficiently define and extract patterns between parts and issues.

PHARMA/LIFE SCIENCES: Competitive Intelligence / Tasks and Challenges

Presented by Kathryn Verhoeven, Data Analysis Consultant
Automated text analysis systems enable businesses to efficiently monitor the competitive landscape. By performing in-depth analysis of mainstream and industry-specific news sources, businesses can monitor the activities of competitors, reveal emerging customer needs, and identify new market trends and promising technologies. This presentation will highlight the key tasks, challenges, and results provided by an automated competitive intelligence solution.

INSURANCE: Making Sense of Claim Notes: Information Extraction

Presented by Chris Farris, Data Analysis Consultant
Information is often locked behind unstructured text and needs to be extracted. In this presentation learn how advanced text analysis techniques allow us to extract complicated and extremely sensitive information from claims notes for later use.

Data Cleansing and Management in PolyAnalyst™

Presented by Ruonan Liu, Data Analysis Consultant
Data cleansing and data management is the process we clean and reorganize our data. It’s the foundation of generating more reliable results for analysts. We will cover duplicate removal, typo correction, abbreviation expansion and data integration in this topic.

PHARMA/LIFE SCIENCES: Competitive Intelligence / Tasks and Challenges

Presented by Kathryn Verhoeven, Data Analysis Consultant
Automated text analysis systems enable businesses to efficiently monitor the competitive landscape. By performing in-depth analysis of mainstream and industry-specific news sources, businesses can monitor the activities of competitors, reveal emerging customer needs, and identify new market trends and promising technologies. This presentation will highlight the key tasks, challenges, and results provided by an automated competitive intelligence solution.

INSURANCE: Entity Complication and Resolution in Claims Notes

Presented by Chris Farris
You have seen an overview of how information is extracted – now take a dive into some complications. Parties can be referenced in many different ways. Learn how to unify these references together to solve a complicated text analysis problem.

Overview: Machine Learning Tools of PolyAnalyst™

Presented by Min Chen, Data Analysis Consultant
This presentation will go over different machine learning tools in PolyAnalyst.

PHARMA/LIFE SCIENCES: Gaining Insights from Customer Support Data

Presented by Yi Wang, Senior Data Analysis Consultant
We will walk through a case project of customer support data for a pharmaceutical company and mentions several aspects of ways exploring the data to get insights.

INSURANCE: Improving Subrogation Prediction through Text Analytics

Presented by Jeff Palan, Data Analysis Consultant
A look at how text analytics can improve subrogation prediction analysis.

Overview: Visualization and Reporting Tools of PolyAnalyst™

Presented by Owen Shi, Lead HCI/UX Designer
Learn the current capability, the new design and the future strategies of data visualization tool of PolyAnalyst™

PHARMA/LIFE SCIENCES: External Resources in Pharma: Ontologies and Public Data Sources

Presented by Jason Liu, Senior Data Analysis Consultant
This presentation talks about what ontologies and public data sources in Pharma are available in PolyAnalyst.

INSURANCE DEMO: Fact Extraction for Subrogation Prediction

Presented by Chris Farris, Data Analysis Consultant
Be exposed to how information is extracted inside of PolyAnalyst. See for yourself how this intricate text analysis is performed within the system and learn how you can generalize the techniques for your own needs.

DEMO: Bubble Chart, Statistical Widget, GIS in Reports

Presented by Bingqing Huang, HCI/UX Designer
This demo showcases bubble chart, statistical widget and GIS map in Web Report. It includes a brief presentation about benefits and examples of using these visulizations and follows by a live demo of how to create them in PolyAnalyst.

PHARMA/LIFE SCIENCES: Adverse report analysis: verification and classification

Yi Wang, Senior Data Analysis Consultant
How does PolyAnalyst handle with adverse event case reports to extract adverse events and map them to proper medDRA dictionary Preferred Terms.

INSURANCE: Fraud Detection in P&C Insurance

Presented by Ruonan Liu, Data Analysis Consultant
Fraud in P&C insurance takes 10 percent of the payout which is around 34 billion dollars annually. Fraud cuts profits for insurers, limits their ability to offer competitive premiums to their customers and worsens their loss and combined ratios. The policyholders Benefits also suffer due to higher premiums.By reducing fraudulent claims, insurance companies will see a significant increase in their profits.

Statistical & Distribution Analysis Tools

Presented by Min Chen, Data Analysis Consultant
Structured data analysis involves the development of statistical models based on numbers, dates, and categories. This session will explore the different capabilities PolyAnalyst has, such as: finding associations, numerical modeling, anomaly detection, time series, etc.

PHARMA/LIFE SCIENCES DEMO: Classifying Adverse Events to MedDRA

Presented by Jason Liu, Senior Data Analysis Consultant
This demo shows how exactly can we classify adverse events to MedDRA.

INSURANCE: Fraud Detection in Healthcare Insurance

Presented by Brian Howard, Sales & Marketing Manager
Automated data analysis systems have become a valuable fraud detection tool for healthcare insurance companies, particularly in detecting anomalies and suspicious activity that is often missed through manual analysis. This presentation will highlight a study involving the implementation of data and text analysis for healthcare insurance fraud detection.

Working with Document Structure and Information Extraction from Tables

Presented by Di Cao, Data Analysis Consultant
This presentation talks about finding tables from different kinds of documents and how we use fuzzy logic to extract information and relations from those tables.

PHARMA/LIFE SCIENCES: Medical Device Repair Notes Analysis

Presented by Di Cao, Data Analysis Consultant
Delicate medical device may have thousands of parts, finding those parts and their corresponding issues is a great challenge. This presentation will show you how we create a semi-automated analysis process that can extract relations between parts and issues.

HEALTHCARE: Extracting and Interpreting Clinical Findings from Medical Records

Presented by Min Chen, Data Analysis Consultant
Healthcare professionals benefit by having a system that automatically extracts clinical findings, but a system that goes one step further, and interprets clinical findings, is indispensable. This presentation will describe such a system.

Multi-Lingual Capabilties of PolyAnalyst™

Presented by Elli Bourlai, Computational Linguist / Data Analysis Consultant
Analyzing textual data in multiple languages is something few software systems have mastered. This session presents the multilingual capabilities of PolyAnalyst at each stage of a project workflow.

PHARMA/LIFE SCIENCES, GUEST Speaker, Eric Su: Techniques in Classifying Externally Acquired Documents

Presented by Eric Su, Constultant, Eli Lilly & Co.
Millions of documents from acquired companies are unclassified. Classifying these documents is desirable for browsing and searching. Presented here are techniques and challenges of rule- and machine learning-based classification using labeled internal documents as training data.

HEALTHCARE: Can Medical Coding of EMRs be Automated?

Presented by Jeff Palan, Data Analysis Consultant
A in-depth look at medical coding, EMRs, and the challenges and potential solutions available for automation.

Integrating Analytics with a Case Management System

Presented by Bipin Inamdar, Senior Data Analysis Consultant
What comes after PolyAnalyst identifies issues to resolve? Case management system allows you to stay on top of the resolution process.

PHARAM/LIFE SCIENCES DEMO: Information Extraction from Medical Device Support Notes

Presented by Zhen Li, Data Analysis Consultant
We will walk you trhough the process of medical device support data analysis in PolyAnalyst using a demo Project. The focus will be on extracing key information from the avalanche of text data using entity extraction techniques.

HEALTHCARE DEMO: Data Redaction / Anonymizing Personal Information

Presented by Yi Wang, Senior Data Analysis Consultant
This demo will show several basic ways that PolyAnalyst automatically or manually anonymizes the personal information such as people name, email address etc.

PolyAnalyst™ Scheduler and Integration with External Systems

Presented by Bipin Inamdar, Senior Data Analysis Consultant
Automate PolyAnalyst and make it a part of your wider software ecosystem.

PHARMA/LIFE SCIENCES: Research Literature: Extracting Entities, Relations and Emerging Trends

Presented by Kathryn Verhoeven, Data Analysis Consultant
The rate of new research publications in any given field continues to increase, making it difficult for researchers to stay updated on current and potential research areas of interest. This presentation will examine how automated text analysis techniques can help researchers obtain meaningful literature summaries, perform knowledge discovery, and identify trends.

HEALTHCARE: Analyzing Employee and Customer Surveys

Presented by Di Cao, Data Analysis Consultant
Learn how to build an automated analysis process to help you extract useful insights from employee and customer surveys with PolyAnalyst new features.

Working with BIG DATA: PolyAnalyst Grid™

Presented by Pavel Anaschenko, Chief Technology Officer
This presentation will discuss how data and text analysis systems can adapt to handle such large data sets, and provide an overview of best practices for performing text analysis on a BIG scale.

PHARMA/LIFE SCIENCES: Fact Finding in Pre-Indexed Standard Resources: PubMed, Patents, and More

Presented by Yi Wang, Senior Data Analysis Consultant
We will talk through how PolyAnalyst loads, cleansing, indexing the standard resource data and how to find some useful patterns in those pre-indexed data.

HEALTHCARE: Medical Research Data Analysis

Presented by Kathryn Verhoeven, Data Analysis Consultant
Public research resources and databases such as PubMed offer valuable and up-to-date information on the state of medical research. This presentation will show how automated text analysis can be applied to gain insights from medical research data.

HCI/UIX: How Megaputer Designs Software

Presented by Owen Shi, Lead HCI/UX Designer
Learn how Megaputer design team provides human-centered design solution to satisfy the user needs.