Revisiting Pontoppidan: Sentiment analysis and topic modelling on ‘Eagle's Flight’

Author:

Vlachos Evgenios12ORCID,Husen Kamilla Jensen13ORCID

Affiliation:

1. University Library of Southern Denmark University of Southern Denmark Odense Denmark

2. The Maersk Mc‐Kinney Moller Institute University of Southern Denmark Odense Denmark

3. Department of Language, Culture, History and Communication University of Southern Denmark Odense Denmark

Abstract

AbstractOur aim is to examine the evolution of Henrik Pontoppidan's authorship by comparing the five different editions that exist of his short story ‘Eagle's Flight’ (‘Ørneflugt’), as well as enriching the understanding of the story. We attempt to validate the existing views of ‘Eagle's Flight’ based on classic literary analysis (qualitative part) by approaching them from a different perspective, that of digital text analysis (quantitative part). The digital analysis focuses on sentiment analysis and topic modelling as ways of discovering differences in the same story across different versions. We have chosen this story as it is relatively easy and quite fast to read, allowing the reader to validate (or not) the output of the machine learning algorithms on their own. We test whether these techniques can be applied in a Danish literature context, and how they further contribute to the analysis and understanding of the literature. Our findings suggest that the methods complement each other and point in the same direction, that Pontoppidan has changed his way of writing during the time of the authorship from a Romantic towards a more Pragmatic style. Our approach can be applied to the works of any author.

Publisher

Wiley

Subject

Literature and Literary Theory

Reference35 articles.

1. On Finding the Natural Number of Topics with Latent Dirichlet Allocation: Some Observations

2. Layers of variation: A computational approach to collating texts with revisions;Bleeker E.;Digital Humanities Quarterly,2022

3. Probabilistic topic models

4. 10.1162/jmlr.2003.3.4-5.993

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3