Thomas Y. Lee

Thomas Y. Lee
  • Adjunct Associate Professor

Contact Information

  • office Address:

    3730 Walnut Street
    573 Jon M. Huntsman Hall
    Philadelphia, PA 19104

Research Interests: healthcare services, information technology support for product and service innovation, regulatory disclosures and analysis, text and data mining

Links: CV, Personal Website

Overview

Thomas Lee served as an Assistant Professor at the Wharton School from 2002 – 2009. He moved to San Francisco in 2009 and teaches courses on Web innovation and product design at Wharton’s San Francisco campus. He conducts research on information and communication technologies to support innovation and new product development. Specifically, he develops and applies text and data mining methods to user-generated content. His goal is to discover and select opportunities for product and service innovation. Recent research has mined the text of online customer reviews to induce market structure and mined electronic medical records to redesign emergency department healthcare service processes.

He holds Ph.D. and M.S. degrees from MIT’s Engineering Systems Division and B.A. and B.S. degrees in Political Science and Symbolic Systems (Artificial Intelligence) from Stanford University. He has served as a visiting scientist at the Computer Security Division of the National Institute of Standards and Technology, a research engineer at the MITRE Corporation, and as a contractor for DynCorp-Meridian supporting the Defense Advanced Research Projects Agency doing research on Internet privacy and security.

Continue Reading

Research

  • Thomas Y. Lee (2011), Automated marketing research using online customer reviews, Journal of Marketing Research, 48 (5).
  • Thomas Y. Lee (2007), Ontology Induction from On-line Customer Reviews, Group Decision and Negotiation, 16(3). Abstract

    We present an unsupervised, domain-independent technique for inducing a product-specific ontology of product features based upon online customer reviews. We frame ontology induction as a logical assignment problem and solve it with a bounds consistency constrained logic program. Using shallow natural language processing techniques, reviews are parsed into phrase sequences where each phrase refers to a single concept. Traditional document clustering techniques are adapted to collect phrases into initial concepts. We generate a token graph for each initial concept cluster and find a maximal clique to define the corresponding logical set of concept sub-elements. The logic program assigns tokens to clique sub-elements. We apply the technique to several thousand digital camera customer reviews and evaluate the results by comparing them to the ontologies represented by several prominent online buying guides. Because our results are drawn directly from customer comments, differences between our automatically induced product features and those in extant guides may reflect opportunities for better managing customer-producer relationships rather than errors in the process.

  • Thomas Y. Lee and Yingwei Yang (2004), Constraint-based wrapper specification and verification for cooperative information systems, Information Systems, 29(7): 617-36. 10.1016/j.is.2003.12.006 Abstract

    Abstract
    In this paper, we propose the use of semistructured constraints in wrappers to mitigate the impact of poor extraction accuracy on Cooperative Information System (CIS) data quality. Wrappers are a critical element of CISs whenever the constituent information systems publish semistructured text such as forms, reports, and memos rather than structured databases. The accuracy of CIS data that stem from text depends upon the wrappers as well as the accuracy of the underlying sources. Wrapper specification is the process of defining patterns (i.e. regular expressions) to extract information from semistructured text. Wrapper verification is the process of ensuring extraction accuracy—that the extracted information faithfully reflects the underlying source. We focus on the problem of extraction accuracy. We use constraints on semistructured data for both wrapper specification and verification. Consequently, we perform extraction and verification simultaneously. We apply the concept to wrappers for a Uniform Domain Name Dispute Resolution Policy (UDRP) CIS of arbitration decisions. UDRP decisions are currently distributed across arbitration authorities on three continents. The accuracy of data extracted using constraint-based specification and verification is measured by Type I and Type II errors.

  • Petros Kavassalis, Joseph P. Bailey, Thomas Y. Lee (2000), Open-layered networks: the growing importance of market coordination, Decision Support Systems, 28(1-2): 137-153. 10.1016/S0167-9236(99)00080-9 Abstract

    Based upon the Internet perspective, this paper will attempt to clarify and revise several ideas about the separation between infrastructure facilities and service offerings in digital communications networks. The key notions that we will focus on in this paper are: (i) the bearer service (BS) as a technology-independent interface which exports blind network functionality to applications development; and (ii) the organizational consequences associated with the emergence of a sustainable market of BS: a clear movement at the level of industrial structure from traditional hierarchies to more market coordination.

Teaching

Past Courses

  • OIDD6590 - Advanced Topics

    The specific content of this course varies from semester to semester, depending on student and faculty interest. Recent topics have included global operations, product design and development, quality management, and logistics strategy. See department for course description. Prerequisites for the course change semester to semester depending on the course content.

Awards And Honors

  • Undergraduate Excellence in Teaching, 2012
  • Wharton nominee for Lindback Award for Distinguished Teaching, Wharton School, 2006
  • David W. Hauck Award for Excellence in Teaching, Wharton School, 2005

In the News

Knowledge @ Wharton

Activity

Latest Research

Thomas Y. Lee (2011), Automated marketing research using online customer reviews, Journal of Marketing Research, 48 (5).
All Research

In the News

Why Companies Need to Address Caregiver Burnout

Wharton's Stephanie Creary talks with experts about how companies can craft more supportive policies for caregivers who are struggling to balance their responsibilities at work and home.Read More

Knowledge @ Wharton - 2024/07/30
All News

Awards and Honors

Undergraduate Excellence in Teaching 2012
All Awards