Electronic Thesis and Dissertation Repository

Degree

Master of Science

Program

Computer Science

Supervisor

Mercer, Robert E.

2nd Supervisor

Xiao, Lu

Affiliation

Syracuse University

Co-Supervisor

Abstract

Tension is an emotional experience that can occur in different contexts. This phenomenon can originate from a conflict of interest or uneasiness during an interview. In some contexts, such experiences are associated with negative emotions such as fear or distress. People tend to adopt different hedging strategies in such situations to avoid criticism or evade questions.

In this thesis, we analyze several survivor interview transcripts to determine different characteristics that play crucial roles during tension situation. We discuss key components of tension experiences and propose a natural language processing model which can effectively combine these components to identify tension points in text-based oral history interviews. We validate the efficacy of our model and its components with experimentation on some standard datasets. The model provides a framework that can be used in future research on tension phenomena in oral history interviews.

Available for download on Monday, April 01, 2019

Included in

Linguistics Commons

Share

COinS