06/16/2023
By Becky Lawrence

The Manning School of Business, Department of Operations and Information Systems, invites you to attend a doctoral dissertation defense by Sambit Tripathi, on “Analysis of User Generated Content in Digital Platforms.”

Candidate Name: Sambit Tripathi
Degree: Doctoral
Defense Date: Thursday, July 20, 2023
Time: 9 – 10:30 a.m. (EDT time)
Location: Via Zoom
Dissertation Title: Analysis of User Generated Content in Digital Platforms

Questions, please contact Xiaobai_Li@uml.edu

Committee:

  • Amit Deokar, Ph.D., Associate Dean, Undergraduate Programs, UMass Lowell (Co-chair)
  • Xiaobai (Bob) Li, Ph.D., Professor of Operations and Information Systems, UMass Lowell (Co-chair)
  • Shakil Quayes, Ph.D., Associate Professor of Economics, UMass Lowell
  • Prasanna Karhade, Ph.D., Associate Professor, of Decision Sciences and Managerial Economics, CUHK Business School

Brief Abstract:

This dissertation focuses on applying data analysis methods on user generated content (UGC) produced on digital platforms. The objective of this dissertation is to: (1) Analyze the order effect of online review text on e-commerce platforms, (2) Understand peer endorsements among gig workers in online labor platforms, and (3) Develop an interpretable item recommendation approach by using customer transactions in online retail platforms.

User-generated content (UGC) is a unique attribute of the Internet that influences individuals’ or organizations’ behavior on digital platforms. Some examples of UGC are retail transactions, social media posts or activities, online reviews, job posts, and video content among others. Social media, e-commerce, online labor markets, and other digital platforms rely on both generation and consumption of UGC to survive in the industry.

The first essay (Chapter 1) focuses on online review text on e-commerce platforms. Online reviews aim to help prospective buyers in their decision-making. Using a large dataset, we extract sentiments, along with novel attributes like product usage contexts and product features present in each online review and analyze their pattern over the order of the review. The second essay (Chapter 2) focuses on peer endorsements among workers in online labor platforms. We apply social value orientation theory to understand the impact of endorsements on workers’ future gig performance. We also understand the factors that influence the generation of endorsements among workers. In the third essay (Chapter 3), we develop a novel method that explains retail items recommended by a blackbox machine learning model. This approach uses topic modeling and word embeddings on historical retail transactions of an e-commerce platform.

All interested students and faculty members are invited to attend.