Transforming Text into Big data: Leveraging Government Documents to Enhance Theory-Driven Research in Public Administrations

Bjarke Lund-Sørensen

Transforming Text into Big data: Leveraging Government Documents to Enhance Theory-Driven Research in Public Administrations

Publikation: Bog/antologi/afhandling/rapport › Ph.d.-afhandling

Abstract

En stor del af den offentlige forvaltning er baseret på udarbejdelsen af skriftlige dokumenter, der anvendes til at udvikle politikker, love og strategier, dokumentere overholdelse af krav og regler samt informere og samarbejde med den private sektor og offentligheden. Disse dokumenter indeholder et væld af informationer om offentlig forvaltning, men anvendes kun i systematiske
kvantitative analyser i stærkt begrænset omfang og i begrænsede sammenhænge. Derfor er der et stort uudnyttet potentiale i, hvordan store mængder offentlige dokumenter kan anvendes bedre i forskning inden for offentlig forvaltning.

Denne afhandling undersøger, hvordan teknologiske udviklinger og brugen af
maskinlæring og kunstig intelligens gør det muligt at analysere store mængder offentlige dokumenter kvantitativt. Afhandlingen betegner dette som big data-analyse og tager empirisk udgangspunkt i kontrakter mellem det offentlige og private. Offentligt indkøb udgør en markant andel af den offentlige sektors forbrug og er baseret på udarbejdelsen af skriftlige kontraktdokumenter. Systematiske big data-analyser af disse kontraktdokumenter på tværs af
produkter og services kan bidrage med vigtige indsigter til offentligt indkøb. Samtidig kan de udgøre et eksempel på potentialet ved big data-analyser i offentlig forvaltning.

Afhandlingen består af fem artikler. Den første artikel er et review af den eksisterende forskning der anvender big data-analyse og identificerer en række udfordringer for udbredelsen af sådanne analyser i forvaltningsforskningen. Den eksisterende forskning anvender kun i begrænset omfang tekstdokumenter og sjældent lange og ustrukturerede dokumenter, der netop kendetegner
offentlig forvaltning. Teori er desuden underprioriteret, og analyserne har et snævert fokus på forudsigelse af bestemte outcomes. Dette udfordrer anvendelsen i offentlig forvaltning, som kvantitativt har et udpræget fokus på at estimere, hvordan faktorer påvirker outcomes baseret på et teoretisk grundlag.

Derfor præsenterer afhandlingen to teoridrevne tilgange til big data-analyse i offentlig forvaltning. Den ene tilgang anvendes i to artikler, hvor big data-analyse benyttes til at måle teoretisk udviklede begreber, som derefter anvendes i en estimationsanalyse. I den ene artikel udvikles en af de første kvantitative målinger af beskyttelse af medarbejdere i outsourcingkontrakter. Artiklen finder, at prioritering af pris og finansiel kapacitet har indflydelse på, hvordan
kommuner beskytter medarbejdere. I den anden artikel udvikles et kvantitativt mål for grønne offentlige indkøb og viser, hvordan politiske interesser, indkøbes kompleksitet og indkøbskapaciteten påvirker, hvor grønt kommuner køber ind. Den anden teoridrevne tilgang til big data-analyse i offentlig forvaltning bygger på en endnu stærkere inspiration fra big data-analyse, hvor den analytiske tilgang er baseret på prædiktion. Tilgangen anvendes i en artikel, som forsøger
at forudsige målbarhed og aktivspecifikation. Den hidtidige forskning har haft vanskeligt ved at måle disse begreber på tværs af mange forskellige typer produkter og services. Artiklen lykkes med at måle disse begreber på tværs af 178 typer af produkter og services. Artiklen er præregistreret for at sikre den teoridrevne forankring.

Afhandlingens sidste artikel viser, at på trods af, at der er et stort potentiale for big data-analyse med tekstdata, så indfries dette kun ved teoretisk funderet forskning og kvalitative indsigter om datamaterialet tæt knyttet til det pågældende forskningsfelt. Samlet set bidrager afhandlingen til, hvordan big data-analyse og kvantitativ tekstanalyse kan anvendes til at måle og analysere centrale begreber i offentlige forvaltning, som den hidtidige forskning har haft vanskeligt ved at kvantificere. Afhandlingen opstiller to teoridrevne tilgange til at kvalificere fremtidige big data-analyser af tekstdokumenter, som kan give nye indsigter i offentlig forvaltningsforskning og bidrage til en mere systematisk anvendelse af tekstdata i praksis.

Originalsprog	Engelsk

Udgivelsessted	Roskilde
Forlag	Roskilde Universitet
Antal sider	339
Status	Udgivet - 2024

Navn	FS & P Ph.D. afhandlinger
ISSN	0909-9174

Bibliografisk note

Vejleder: Kim Sass Mikkelsen
Bi-vejleder: Jon Kvist

Citer dette

@phdthesis{28f36d0c3e664f3c8e9b7d3be1477e9f,

title = "Transforming Text into Big data: Leveraging Government Documents to Enhance Theory-Driven Research in Public Administrations",

abstract = "A significant part of public administration is based on creating written documents, which are used to develop policies, laws, and strategies, document compliance with requirements and regulations, and inform and collaborate with the private sector and the public. These documents contain a wealth of information on public administration but are only used in systematic quantitative analyses to alimited extent and in limited contexts. Therefore, there is significant untapped potential in how large quantities of public documents can be better used in research on public administration.This dissertation investigates how technological advancements and the use of machine learning and artificial intelligence enable the quantitative analysis of large volumes of public documents. The dissertation refers to this as big data analysis and focuses empirically on contracts between the public and private sectors. Public procurement constitutes a significant portion of the public sector spending and is based on written contract documents. Systematic big data analyses of these contract documents across products and services can provide important insights into public procurement At the same time, they can serve as an example of the potential of big data analysis in public administration.The dissertation consists of five articles. The first article Is a review of the existingresearch that uses big data analysis and identifies a series of challenges for the widespread use of such analyses in public administration research. The existing research only uses text documents to a limited extent and rarely long and unstructured documents, which are characteristic of public administration. Theory is also underprioritized, and the analyses focus narrowly on predicting specific outcomes. This challenges its application in public administration, which quantitatively focuses on estimating how factors influence outcomes based on a theoretical foundation.Therefore, the dissertation presents two theory-driven approaches to big data analysis in public administration. One approach is used in two articles, where big data analysis is used to measure theoretically developed concepts, which are then used in an estimation analysis. One article develops one of the first quantitative measures of employee protection in outsourcing contracts. The article finds that prioritization of price and financial capacity influences how municipalities protect employees. The other article develops a quantitative measure for green publicprocurement and shows how political interests, procurement complexity, and procurement capacity affect how green municipalities purchase. The other theory-driven approach to big data analysis in public administration is based on even stronger inspiration from big data analysis, where the analytical approach is based on prediction. This approach is used in an article that attempts to predict measurability and activity specificity. Previous research has struggled to measure these concepts across many different types of products and services. The article succeeds in measuring these concepts across 178 types of products and services. The article is preregistered to ensure its theory-driven anchoring.The last article of the dissertation shows that although there Is great potential for big data analysis with text data, this is only realized through theoretically grounded research and qualitative insights about the data material closely related to the domain research field. Overall, the dissertation contributes to how big data analysis and quantitative text analysis can be used to measure and analyze key concepts in public administration, which previous research has struggledto quantify. The dissertation outlines two theory-driven approaches to qualify future big data analyses of text documents, which can provide new insights into public administration research and contribute to more systematic use of text data in practice.",

author = "Bjarke Lund-S{\o}rensen",

note = "Supervisor: Kim Sass Mikkelsen Co-Supervisor: Jon Kvist",

year = "2024",

language = "English",

series = "FS & P Ph.D. afhandlinger",

publisher = "Roskilde Universitet",

}

TY - BOOK

T1 - Transforming Text into Big data

T2 - Leveraging Government Documents to Enhance Theory-Driven Research in Public Administrations

AU - Lund-Sørensen, Bjarke

N1 - Supervisor: Kim Sass Mikkelsen Co-Supervisor: Jon Kvist

PY - 2024

Y1 - 2024

N2 - A significant part of public administration is based on creating written documents, which are used to develop policies, laws, and strategies, document compliance with requirements and regulations, and inform and collaborate with the private sector and the public. These documents contain a wealth of information on public administration but are only used in systematic quantitative analyses to alimited extent and in limited contexts. Therefore, there is significant untapped potential in how large quantities of public documents can be better used in research on public administration.This dissertation investigates how technological advancements and the use of machine learning and artificial intelligence enable the quantitative analysis of large volumes of public documents. The dissertation refers to this as big data analysis and focuses empirically on contracts between the public and private sectors. Public procurement constitutes a significant portion of the public sector spending and is based on written contract documents. Systematic big data analyses of these contract documents across products and services can provide important insights into public procurement At the same time, they can serve as an example of the potential of big data analysis in public administration.The dissertation consists of five articles. The first article Is a review of the existingresearch that uses big data analysis and identifies a series of challenges for the widespread use of such analyses in public administration research. The existing research only uses text documents to a limited extent and rarely long and unstructured documents, which are characteristic of public administration. Theory is also underprioritized, and the analyses focus narrowly on predicting specific outcomes. This challenges its application in public administration, which quantitatively focuses on estimating how factors influence outcomes based on a theoretical foundation.Therefore, the dissertation presents two theory-driven approaches to big data analysis in public administration. One approach is used in two articles, where big data analysis is used to measure theoretically developed concepts, which are then used in an estimation analysis. One article develops one of the first quantitative measures of employee protection in outsourcing contracts. The article finds that prioritization of price and financial capacity influences how municipalities protect employees. The other article develops a quantitative measure for green publicprocurement and shows how political interests, procurement complexity, and procurement capacity affect how green municipalities purchase. The other theory-driven approach to big data analysis in public administration is based on even stronger inspiration from big data analysis, where the analytical approach is based on prediction. This approach is used in an article that attempts to predict measurability and activity specificity. Previous research has struggled to measure these concepts across many different types of products and services. The article succeeds in measuring these concepts across 178 types of products and services. The article is preregistered to ensure its theory-driven anchoring.The last article of the dissertation shows that although there Is great potential for big data analysis with text data, this is only realized through theoretically grounded research and qualitative insights about the data material closely related to the domain research field. Overall, the dissertation contributes to how big data analysis and quantitative text analysis can be used to measure and analyze key concepts in public administration, which previous research has struggledto quantify. The dissertation outlines two theory-driven approaches to qualify future big data analyses of text documents, which can provide new insights into public administration research and contribute to more systematic use of text data in practice.

AB - A significant part of public administration is based on creating written documents, which are used to develop policies, laws, and strategies, document compliance with requirements and regulations, and inform and collaborate with the private sector and the public. These documents contain a wealth of information on public administration but are only used in systematic quantitative analyses to alimited extent and in limited contexts. Therefore, there is significant untapped potential in how large quantities of public documents can be better used in research on public administration.This dissertation investigates how technological advancements and the use of machine learning and artificial intelligence enable the quantitative analysis of large volumes of public documents. The dissertation refers to this as big data analysis and focuses empirically on contracts between the public and private sectors. Public procurement constitutes a significant portion of the public sector spending and is based on written contract documents. Systematic big data analyses of these contract documents across products and services can provide important insights into public procurement At the same time, they can serve as an example of the potential of big data analysis in public administration.The dissertation consists of five articles. The first article Is a review of the existingresearch that uses big data analysis and identifies a series of challenges for the widespread use of such analyses in public administration research. The existing research only uses text documents to a limited extent and rarely long and unstructured documents, which are characteristic of public administration. Theory is also underprioritized, and the analyses focus narrowly on predicting specific outcomes. This challenges its application in public administration, which quantitatively focuses on estimating how factors influence outcomes based on a theoretical foundation.Therefore, the dissertation presents two theory-driven approaches to big data analysis in public administration. One approach is used in two articles, where big data analysis is used to measure theoretically developed concepts, which are then used in an estimation analysis. One article develops one of the first quantitative measures of employee protection in outsourcing contracts. The article finds that prioritization of price and financial capacity influences how municipalities protect employees. The other article develops a quantitative measure for green publicprocurement and shows how political interests, procurement complexity, and procurement capacity affect how green municipalities purchase. The other theory-driven approach to big data analysis in public administration is based on even stronger inspiration from big data analysis, where the analytical approach is based on prediction. This approach is used in an article that attempts to predict measurability and activity specificity. Previous research has struggled to measure these concepts across many different types of products and services. The article succeeds in measuring these concepts across 178 types of products and services. The article is preregistered to ensure its theory-driven anchoring.The last article of the dissertation shows that although there Is great potential for big data analysis with text data, this is only realized through theoretically grounded research and qualitative insights about the data material closely related to the domain research field. Overall, the dissertation contributes to how big data analysis and quantitative text analysis can be used to measure and analyze key concepts in public administration, which previous research has struggledto quantify. The dissertation outlines two theory-driven approaches to qualify future big data analyses of text documents, which can provide new insights into public administration research and contribute to more systematic use of text data in practice.

M3 - Ph.D. thesis

T3 - FS & P Ph.D. afhandlinger

BT - Transforming Text into Big data

PB - Roskilde Universitet

CY - Roskilde

ER -