Blended Reading

Stulpe, Alexander; Lemke, Matthias

doi:10.1007/978-3-658-07224-7_2

Cited by 27 publications

(9 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…According to this simple typology, the analysis carried out for this study can be defined as an analysis for which mostly "close reading" was performed following very basic techniques of "distant reading." The "sequential" (Stulpe & Lemke, 2016) combination of techniques is based on the assumption that these have a varying utility for the three main steps of analysis made. These three steps are described in the following, whereby the mode of text analysis they resemble is named.…”

Section: Methods Of Analysis: Combining Close and Distant Readingmentioning

confidence: 99%

The Construction of a New Policy Domain in Debates on German Internet Policy

Reiberg¹

2017

European Policy Analysis

View full text Add to dashboard Cite

Within the past two decades, the emergence of a new policy domain has become evident in several countries. One example is Germany, where the political parties appointed spokespeople for Internet policy and a standing parliamentary committee for a “digital agenda” has been established. In this paper, the question of how political actors are constructing the new domain of Internet policy is addressed with an empirical analysis. While briefly describing the underlying theoretical framework, it is argued that the development of the new policy domain can be understood as a process of “collaborative meaning making” (Fligstein & McAdam, 2012). During this process, networks of political actors settle for a shared understanding regarding the societal problems that give reason to state intervention and the form this intervention may take. The empirical study is focused on the first debates on German Internet policy. Two text corpora containing parliamentary minutes and articles of five major newspapers are analyzed using close as well as distant reading techniques. The results show how political actors established a shared understanding regarding the policy domain and how this resulted in its particular governmental institutionalization.

show abstract

Section: Methods Of Analysis: Combining Close and Distant Readingmentioning

confidence: 99%

The Construction of a New Policy Domain in Debates on German Internet Policy

Reiberg¹

2017

European Policy Analysis

View full text Add to dashboard Cite

show abstract

“…It can be used to deal with new and different questions than those based on close reading. Hermeneutic contexts of meaning or the reconstruction of specific individual behaviour patterns cannot be determined to the extent that is known from qualitative research, but texts can be structured with the help of algorithms and can thus be converted for mathematical operations (Stulpe and Lemke 2016). Texts can then be arranged, edited, sorted or searched for content, i.e.…”

Section: Distant Readingmentioning

confidence: 99%

“…structures and recurring patterns can be researched (Hockey 2000;Heyer et al 2006: 3). In this case study, we use the method of topic modelling, more precisely Latent Dirichlet Allocation (LDA), which can be understood as a distant reading method (Stulpe and Lemke 2016). Before we go into more detail, we will first explain how the data extraction from the web archive was done and how a corpus was built.…”

Section: Distant Readingmentioning

confidence: 99%

Using web archives for an explorative study of the web presence of German parties during the European election 2019

et al. 2023

View full text Add to dashboard Cite

In the digital age, political science is faced with a shift of election campaigns and political discourse to digital or virtual arenas. Because the internet is a highly volatile medium and online content can become inaccessible after the campaign season, new challenges for research arise as well as the need for the preservation of online content. Moreover, the sheer volume of data researchers have to deal with has reached levels where traditional methods are being highly challenged. This paper puts forth a web harvesting workflow with a strong focus on granular extraction of unstructured information (publication dates) for automated analysis. As our approach is methodological, we would like to point out the benefits that researches in political science may draw from adapting our methodology. We demonstrate this by analysing an event-based web crawl of German parties participating in the election campaign for the European Parliamentary Election in 2019. We employ distant reading methods to generate topic models, which are subsequently evaluated by hermeneutic analysis of a subset of the data.

show abstract

“…Various combinations of TM and annotation approaches have been suggested, where TM is used to structure the corpus and to answer more general research questions, and where only a limited sub-set of texts is then manually annotated, effectively reducing the amount of annotated text (Stulpe & Lemke, 2016). The methodological approach we present in this article follows a different logic.…”

Section: Existing Approaches To Analyse the Content Of Large Text Corpora In The Social Sciencesmentioning

confidence: 99%

Integrating Manual and Automatic Annotation for the Creation of Discourse Network Data Sets

Haunss

Kuhn

Padó

et al. 2020

PaG

View full text Add to dashboard Cite

This article investigates the integration of machine learning in the political claim annotation workflow with the goal to partially automate the annotation and analysis of large text corpora. It introduces the MARDY annotation environment and presents results from an experiment in which the annotation quality of annotators with and without machine learning based annotation support is compared. The design and setting aim to measure and evaluate: a) annotation speed; b) annotation quality; and c) applicability to the use case of discourse network generation. While the results indicate only slight increases in terms of annotation speed, the authors find a moderate boost in annotation quality. Additionally, with the help of manual annotation of the actors and filtering out of the false positives, the machine learning based annotation suggestions allow the authors to fully recover the core network of the discourse as extracted from the articles annotated during the experiment. This is due to the redundancy which is naturally present in the annotated texts. Thus, assuming a research focus not on the complete network but the network core, an AI-based annotation can provide reliable information about discourse networks with much less human intervention than compared to the traditional manual approach.

show abstract

Blended Reading

Cited by 27 publications

References 19 publications

The Construction of a New Policy Domain in Debates on German Internet Policy

The Construction of a New Policy Domain in Debates on German Internet Policy

Using web archives for an explorative study of the web presence of German parties during the European election 2019

Integrating Manual and Automatic Annotation for the Creation of Discourse Network Data Sets

Contact Info

Product

Resources

About