Home > Research > Publications & Outputs > Constructing Corpora from Images and Text

Research

Links

Text available via DOI:

View graph of relations

Constructing Corpora from Images and Text: An introduction to Visual Constituent Analysis

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Chapter

Published

Standard

Constructing Corpora from Images and Text: An introduction to Visual Constituent Analysis. / Christiansen, Alex; Dance, William; Wild, Alexander.
Corpus Approaches to Social Media. ed. / Sofia Rüdiger ; Daria Dayter. John Benjamins, 2020. p. 149-174 (Studies in Corpus Linguistics).

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Chapter

Harvard

Christiansen, A, Dance, W & Wild, A 2020, Constructing Corpora from Images and Text: An introduction to Visual Constituent Analysis. in S Rüdiger & D Dayter (eds), Corpus Approaches to Social Media. Studies in Corpus Linguistics, John Benjamins, pp. 149-174. https://doi.org/10.1075/scl.98

APA

Christiansen, A., Dance, W., & Wild, A. (2020). Constructing Corpora from Images and Text: An introduction to Visual Constituent Analysis. In S. Rüdiger , & D. Dayter (Eds.), Corpus Approaches to Social Media (pp. 149-174). (Studies in Corpus Linguistics). John Benjamins. https://doi.org/10.1075/scl.98

Vancouver

Christiansen A, Dance W, Wild A. Constructing Corpora from Images and Text: An introduction to Visual Constituent Analysis. In Rüdiger S, Dayter D, editors, Corpus Approaches to Social Media. John Benjamins. 2020. p. 149-174. (Studies in Corpus Linguistics). doi: 10.1075/scl.98

Author

Christiansen, Alex ; Dance, William ; Wild, Alexander. / Constructing Corpora from Images and Text : An introduction to Visual Constituent Analysis. Corpus Approaches to Social Media. editor / Sofia Rüdiger ; Daria Dayter. John Benjamins, 2020. pp. 149-174 (Studies in Corpus Linguistics).

Bibtex

@inbook{71980773bfc3472b94e7025e49f5ba01,
title = "Constructing Corpora from Images and Text: An introduction to Visual Constituent Analysis",
abstract = "Visual analysis represents a significant oversight in the corpus literature, and possibly one that may lead to unintended omissions, particularly when analysing social media. In this chapter we introduce Visual Constituent Analysis (VCA), a method of multimodal corpus construction that allows researchers to construct and analyse visual aspects of online media in large-scale corpora. The chapter addresses the shortcomings of a purely textual approach to discourse analysis when dealing with social media texts and offers a solution using computer {\textquoteleft}Vision{\textquoteright}-based image annotation (in our case Google Cloud Vision). Finally, we demonstrate how our approach can be used to analyse a sample of 150,000 micro-blog posts from Twitter and show the difference in level of user interaction with combined image/texts over language-only social media texts.",
author = "Alex Christiansen and William Dance and Alexander Wild",
year = "2020",
month = nov,
day = "30",
doi = "10.1075/scl.98",
language = "English",
isbn = "9789027207944",
series = "Studies in Corpus Linguistics",
publisher = "John Benjamins",
pages = "149--174",
editor = "{R{\"u}diger }, {Sofia } and Daria Dayter",
booktitle = "Corpus Approaches to Social Media",

}

RIS

TY - CHAP

T1 - Constructing Corpora from Images and Text

T2 - An introduction to Visual Constituent Analysis

AU - Christiansen, Alex

AU - Dance, William

AU - Wild, Alexander

PY - 2020/11/30

Y1 - 2020/11/30

N2 - Visual analysis represents a significant oversight in the corpus literature, and possibly one that may lead to unintended omissions, particularly when analysing social media. In this chapter we introduce Visual Constituent Analysis (VCA), a method of multimodal corpus construction that allows researchers to construct and analyse visual aspects of online media in large-scale corpora. The chapter addresses the shortcomings of a purely textual approach to discourse analysis when dealing with social media texts and offers a solution using computer ‘Vision’-based image annotation (in our case Google Cloud Vision). Finally, we demonstrate how our approach can be used to analyse a sample of 150,000 micro-blog posts from Twitter and show the difference in level of user interaction with combined image/texts over language-only social media texts.

AB - Visual analysis represents a significant oversight in the corpus literature, and possibly one that may lead to unintended omissions, particularly when analysing social media. In this chapter we introduce Visual Constituent Analysis (VCA), a method of multimodal corpus construction that allows researchers to construct and analyse visual aspects of online media in large-scale corpora. The chapter addresses the shortcomings of a purely textual approach to discourse analysis when dealing with social media texts and offers a solution using computer ‘Vision’-based image annotation (in our case Google Cloud Vision). Finally, we demonstrate how our approach can be used to analyse a sample of 150,000 micro-blog posts from Twitter and show the difference in level of user interaction with combined image/texts over language-only social media texts.

U2 - 10.1075/scl.98

DO - 10.1075/scl.98

M3 - Chapter

SN - 9789027207944

T3 - Studies in Corpus Linguistics

SP - 149

EP - 174

BT - Corpus Approaches to Social Media

A2 - Rüdiger , Sofia

A2 - Dayter, Daria

PB - John Benjamins

ER -