@inproceedings{parameswaran-etal-2022-reproducibility,
title = "Reproducibility and Automation of the Appraisal Taxonomy",
author = "Parameswaran, Pradeesh and
Trotman, Andrew and
Liesaputra, Veronica and
Eyers, David",
editor = "Calzolari, Nicoletta and
Huang, Chu-Ren and
Kim, Hansaem and
Pustejovsky, James and
Wanner, Leo and
Choi, Key-Sun and
Ryu, Pum-Mo and
Chen, Hsin-Hsi and
Donatelli, Lucia and
Ji, Heng and
Kurohashi, Sadao and
Paggio, Patrizia and
Xue, Nianwen and
Kim, Seokhwan and
Hahm, Younggyun and
He, Zhong and
Lee, Tony Kyungil and
Santus, Enrico and
Bond, Francis and
Na, Seung-Hoon",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2022.coling-1.328/",
pages = "3731--3740",
abstract = "There is a lack of reproducibility in results from experiments that apply the Appraisal taxonomy. Appraisal is widely used by linguists to study how people judge things or people. Automating Appraisal could be beneficial for use cases such as moderating online comments. Past work in Appraisal annotation has been descriptive in nature and, the lack of publicly available data sets hinders the progress of automation. In this work, we are interested in two things; first, measuring the performance of automated approaches to Appraisal classification in the publicly available Australasian Language Technology Association (ALTA) Shared Task Challenge data set. Second, we are interested in reproducing the annotation of the ALTA data set. Four additional annotators, each with a different linguistics background, were employed to re-annotate the data set. Our results show a poor level of agreement at more detailed Appraisal categories (Fleiss Kappa = 0.059) and a fair level of agreement (Kappa = 0.372) at coarse-level categories. We find similar results when using automated approaches that are available publicly. Our empirical evidence suggests that at present, automating classification is practical only when considering coarse-level categories of the taxonomy."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="parameswaran-etal-2022-reproducibility">
<titleInfo>
<title>Reproducibility and Automation of the Appraisal Taxonomy</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pradeesh</namePart>
<namePart type="family">Parameswaran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrew</namePart>
<namePart type="family">Trotman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronica</namePart>
<namePart type="family">Liesaputra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Eyers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 29th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chu-Ren</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hansaem</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Pustejovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Key-Sun</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pum-Mo</namePart>
<namePart type="family">Ryu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Donatelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadao</namePart>
<namePart type="family">Kurohashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrizia</namePart>
<namePart type="family">Paggio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seokhwan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Younggyun</namePart>
<namePart type="family">Hahm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhong</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tony</namePart>
<namePart type="given">Kyungil</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Bond</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seung-Hoon</namePart>
<namePart type="family">Na</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>There is a lack of reproducibility in results from experiments that apply the Appraisal taxonomy. Appraisal is widely used by linguists to study how people judge things or people. Automating Appraisal could be beneficial for use cases such as moderating online comments. Past work in Appraisal annotation has been descriptive in nature and, the lack of publicly available data sets hinders the progress of automation. In this work, we are interested in two things; first, measuring the performance of automated approaches to Appraisal classification in the publicly available Australasian Language Technology Association (ALTA) Shared Task Challenge data set. Second, we are interested in reproducing the annotation of the ALTA data set. Four additional annotators, each with a different linguistics background, were employed to re-annotate the data set. Our results show a poor level of agreement at more detailed Appraisal categories (Fleiss Kappa = 0.059) and a fair level of agreement (Kappa = 0.372) at coarse-level categories. We find similar results when using automated approaches that are available publicly. Our empirical evidence suggests that at present, automating classification is practical only when considering coarse-level categories of the taxonomy.</abstract>
<identifier type="citekey">parameswaran-etal-2022-reproducibility</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.328/</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>3731</start>
<end>3740</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Reproducibility and Automation of the Appraisal Taxonomy
%A Parameswaran, Pradeesh
%A Trotman, Andrew
%A Liesaputra, Veronica
%A Eyers, David
%Y Calzolari, Nicoletta
%Y Huang, Chu-Ren
%Y Kim, Hansaem
%Y Pustejovsky, James
%Y Wanner, Leo
%Y Choi, Key-Sun
%Y Ryu, Pum-Mo
%Y Chen, Hsin-Hsi
%Y Donatelli, Lucia
%Y Ji, Heng
%Y Kurohashi, Sadao
%Y Paggio, Patrizia
%Y Xue, Nianwen
%Y Kim, Seokhwan
%Y Hahm, Younggyun
%Y He, Zhong
%Y Lee, Tony Kyungil
%Y Santus, Enrico
%Y Bond, Francis
%Y Na, Seung-Hoon
%S Proceedings of the 29th International Conference on Computational Linguistics
%D 2022
%8 October
%I International Committee on Computational Linguistics
%C Gyeongju, Republic of Korea
%F parameswaran-etal-2022-reproducibility
%X There is a lack of reproducibility in results from experiments that apply the Appraisal taxonomy. Appraisal is widely used by linguists to study how people judge things or people. Automating Appraisal could be beneficial for use cases such as moderating online comments. Past work in Appraisal annotation has been descriptive in nature and, the lack of publicly available data sets hinders the progress of automation. In this work, we are interested in two things; first, measuring the performance of automated approaches to Appraisal classification in the publicly available Australasian Language Technology Association (ALTA) Shared Task Challenge data set. Second, we are interested in reproducing the annotation of the ALTA data set. Four additional annotators, each with a different linguistics background, were employed to re-annotate the data set. Our results show a poor level of agreement at more detailed Appraisal categories (Fleiss Kappa = 0.059) and a fair level of agreement (Kappa = 0.372) at coarse-level categories. We find similar results when using automated approaches that are available publicly. Our empirical evidence suggests that at present, automating classification is practical only when considering coarse-level categories of the taxonomy.
%U https://aclanthology.org/2022.coling-1.328/
%P 3731-3740
Markdown (Informal)
[Reproducibility and Automation of the Appraisal Taxonomy](https://aclanthology.org/2022.coling-1.328/) (Parameswaran et al., COLING 2022)
ACL
- Pradeesh Parameswaran, Andrew Trotman, Veronica Liesaputra, and David Eyers. 2022. Reproducibility and Automation of the Appraisal Taxonomy. In Proceedings of the 29th International Conference on Computational Linguistics, pages 3731–3740, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.