@inproceedings{kunilovskaya-plum-2021-text-preprocessing,
title = "Text Preprocessing and its Implications in a Digital Humanities Project",
author = "Kunilovskaya, Maria and
Plum, Alistair",
editor = "Djabri, Souhila and
Gimadi, Dinara and
Mihaylova, Tsvetomila and
Nikolova-Koleva, Ivelina",
booktitle = "Proceedings of the Student Research Workshop Associated with RANLP 2021",
month = sep,
year = "2021",
address = "Online",
publisher = "INCOMA Ltd.",
url = "https://aclanthology.org/2021.ranlp-srw.13",
pages = "85--93",
abstract = "This paper focuses on data cleaning as part of a preprocessing procedure applied to text data retrieved from the web. Although the importance of this early stage in a project using NLP methods is often highlighted by researchers, the details, general principles and techniques are usually left out due to consideration of space. At best, they are dismissed with a comment {``}The usual data cleaning and preprocessing procedures were applied{''}. More coverage is usually given to automatic text annotation such as lemmatisation, part-of-speech tagging and parsing, which is often included in preprocessing. In the literature, the term {`}preprocessing{'} is used to refer to a wide range of procedures, from filtering and cleaning to data transformation such as stemming and numeric representation, which might create confusion. We argue that text preprocessing might skew original data distribution with regard to the metadata, such as types, locations and times of registered datapoints. In this paper we describe a systematic approach to cleaning text data mined by a data-providing company for a Digital Humanities (DH) project focused on cultural analytics. We reveal the types and amount of noise in the data coming from various web sources and estimate the changes in the size of the data associated with preprocessing. We also compare the results of a text classification experiment run on the raw and preprocessed data. We hope that our experience and approaches will help the DH community to diagnose the quality of textual data collected from the web and prepare it for further natural language processing.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kunilovskaya-plum-2021-text-preprocessing">
<titleInfo>
<title>Text Preprocessing and its Implications in a Digital Humanities Project</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Kunilovskaya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alistair</namePart>
<namePart type="family">Plum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Student Research Workshop Associated with RANLP 2021</title>
</titleInfo>
<name type="personal">
<namePart type="given">Souhila</namePart>
<namePart type="family">Djabri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dinara</namePart>
<namePart type="family">Gimadi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tsvetomila</namePart>
<namePart type="family">Mihaylova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivelina</namePart>
<namePart type="family">Nikolova-Koleva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd.</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper focuses on data cleaning as part of a preprocessing procedure applied to text data retrieved from the web. Although the importance of this early stage in a project using NLP methods is often highlighted by researchers, the details, general principles and techniques are usually left out due to consideration of space. At best, they are dismissed with a comment “The usual data cleaning and preprocessing procedures were applied”. More coverage is usually given to automatic text annotation such as lemmatisation, part-of-speech tagging and parsing, which is often included in preprocessing. In the literature, the term ‘preprocessing’ is used to refer to a wide range of procedures, from filtering and cleaning to data transformation such as stemming and numeric representation, which might create confusion. We argue that text preprocessing might skew original data distribution with regard to the metadata, such as types, locations and times of registered datapoints. In this paper we describe a systematic approach to cleaning text data mined by a data-providing company for a Digital Humanities (DH) project focused on cultural analytics. We reveal the types and amount of noise in the data coming from various web sources and estimate the changes in the size of the data associated with preprocessing. We also compare the results of a text classification experiment run on the raw and preprocessed data. We hope that our experience and approaches will help the DH community to diagnose the quality of textual data collected from the web and prepare it for further natural language processing.</abstract>
<identifier type="citekey">kunilovskaya-plum-2021-text-preprocessing</identifier>
<location>
<url>https://aclanthology.org/2021.ranlp-srw.13</url>
</location>
<part>
<date>2021-09</date>
<extent unit="page">
<start>85</start>
<end>93</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Text Preprocessing and its Implications in a Digital Humanities Project
%A Kunilovskaya, Maria
%A Plum, Alistair
%Y Djabri, Souhila
%Y Gimadi, Dinara
%Y Mihaylova, Tsvetomila
%Y Nikolova-Koleva, Ivelina
%S Proceedings of the Student Research Workshop Associated with RANLP 2021
%D 2021
%8 September
%I INCOMA Ltd.
%C Online
%F kunilovskaya-plum-2021-text-preprocessing
%X This paper focuses on data cleaning as part of a preprocessing procedure applied to text data retrieved from the web. Although the importance of this early stage in a project using NLP methods is often highlighted by researchers, the details, general principles and techniques are usually left out due to consideration of space. At best, they are dismissed with a comment “The usual data cleaning and preprocessing procedures were applied”. More coverage is usually given to automatic text annotation such as lemmatisation, part-of-speech tagging and parsing, which is often included in preprocessing. In the literature, the term ‘preprocessing’ is used to refer to a wide range of procedures, from filtering and cleaning to data transformation such as stemming and numeric representation, which might create confusion. We argue that text preprocessing might skew original data distribution with regard to the metadata, such as types, locations and times of registered datapoints. In this paper we describe a systematic approach to cleaning text data mined by a data-providing company for a Digital Humanities (DH) project focused on cultural analytics. We reveal the types and amount of noise in the data coming from various web sources and estimate the changes in the size of the data associated with preprocessing. We also compare the results of a text classification experiment run on the raw and preprocessed data. We hope that our experience and approaches will help the DH community to diagnose the quality of textual data collected from the web and prepare it for further natural language processing.
%U https://aclanthology.org/2021.ranlp-srw.13
%P 85-93
Markdown (Informal)
[Text Preprocessing and its Implications in a Digital Humanities Project](https://aclanthology.org/2021.ranlp-srw.13) (Kunilovskaya & Plum, RANLP 2021)
ACL