Natural language processing for modeling stable writing characteristics of users

Namseok Lee, Kwangsu Cho

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The aim of this study was to propose a new method to model writing characteristics of users with consistency. This study explored the possibility of modeling the characteristics by analyzing linguistic features of drafts and written comments of the same users in a peer review system. The drafts and comments were collected from 41 undergraduate students who were taking an introductory physics course in the U.S. Natural language processing was used for analyzing drafts and written comments produced by the participants. The results of this study showed that users who wrote drafts by using abstract nouns, different words across sentences, and structurally complex sentences, tended to write comments with abstract nouns, diverse words, and structurally complex sentences. These results implied that users' stable writing characteristics could be modeled based on linguistic features such as ambiguity, lexical diversity, and syntactic complexity.

Original languageEnglish
Title of host publicationInformation Technology Convergence, Secure and Trust Computing, and Data Management, ITCS 2012 and STA 2012
Pages63-70
Number of pages8
DOIs
Publication statusPublished - 2012
Event4th International Conference on Information Technology Convergence and Services, ITCS 2012 and 9th FTRA International Conference on Secure and Trust Computing, Data Management, and Applications, STA 2012 - Gwangju, Korea, Republic of
Duration: 2012 Sept 62012 Sept 8

Publication series

NameLecture Notes in Electrical Engineering
Volume180 LNEE
ISSN (Print)1876-1100
ISSN (Electronic)1876-1119

Other

Other4th International Conference on Information Technology Convergence and Services, ITCS 2012 and 9th FTRA International Conference on Secure and Trust Computing, Data Management, and Applications, STA 2012
Country/TerritoryKorea, Republic of
CityGwangju
Period12/9/612/9/8

All Science Journal Classification (ASJC) codes

  • Industrial and Manufacturing Engineering

Fingerprint

Dive into the research topics of 'Natural language processing for modeling stable writing characteristics of users'. Together they form a unique fingerprint.

Cite this