Teaching the Computer to Code Frames in News: Comparing Two Supervised Machine Learning Approaches to Frame Analysis

Burscher, Björn; Odijk, Daan; Vliegenthart, Rens; Rijke, Maarten de; Vreese, Claes H. de

doi:10.1080/19312458.2014.937527

Cited by 93 publications

(102 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, prior research has shown that human coding of large corpuses is generally very time-consuming and costly (see Burscher et al, 2014;Mikhaylov et al, 2012). Moreover, when different researchers are instructed to simultaneously annotate a certain number of documents, inter-coder reliability tends to be far from optimal.…”

Section: Using a Computer To Code Framesmentioning

confidence: 99%

“…In this case, an algorithm is trained to accurately perform a binary classification task: is frame X present in the article or not? Burscher et al (2014) estimate that 300 articles should suffice for the algorithm to generate sufficiently accurate predictions for the frame codes corresponding to all newspaper articles in the corpus.…”

Section: Using a Computer To Code Framesmentioning

confidence: 99%

“…The 300 articles were hand-coded according to a coding scheme derived from the work of Burscher et al (2014). 2 For each media frame, the coding scheme contains two yes-or-no indicator questions.…”

Section: Using a Computer To Code Framesmentioning

confidence: 99%

See 2 more Smart Citations

Nationality swapping in the Olympic Games 1978–2017: A supervised machine learning approach to analysing discourses of citizenship and nationhood

Jansen

2018

International Review for the Sociology of Sport

View full text Add to dashboard Cite

While the practice of nationality swapping in sports traces back as far as the Ancient Olympics, it seems to have increased over the past decades. Cases of Olympic athletes who switched their national allegiances are often surrounded with controversy. Two strands of thought could help explain this controversy. First, these cases are believed to be indicative of the marketisation of citizenship. Second, these cases challenge established discourses of national identity as the question 'who may represent the nation?' becomes contested. Using state-of-the-art machine learning techniques, I analysed 1534 English language newspaper articles about Olympic athletes who changed their nationalities . The results indicate: (i) that switching national allegiance has not necessarily become more controversial; (ii) that most media reports do not frame nationality switching in economic terms; and (iii) that nationality swapping often occurs fairly unnoticed. I therefore conclude that a marketisation of citizenship is less apparent in nationality switching than some claim. Moreover, nationality switches are often mentioned rather casually, indicating the generally banal character of nationalism. Only under certain conditions does 'hot' nationalism spark the issue of nationhood.

show abstract

Section: Using a Computer To Code Framesmentioning

confidence: 99%

Section: Using a Computer To Code Framesmentioning

confidence: 99%

See 1 more Smart Citation

Nationality swapping in the Olympic Games 1978–2017: A supervised machine learning approach to analysing discourses of citizenship and nationhood

Jansen

2018

International Review for the Sociology of Sport

View full text Add to dashboard Cite

show abstract

“…Here the advantages of crowdsourcing tools should lead to a serious consideration of these as an alternative to employing and training human coders. Such data, even with less than perfect reliability scores (e.g., Burscher, Odijk, Vliegenthart, De Rijke, & De Vreese, 2014), can be important tools for algorithm development in machine learning procedures. Furthermore, crowdsourcing offers the opportunity to reveal group decisions that may depict more valid results than the judgment of one single trained expert coder and also may be easier to replicate.…”

Section: Overall Conclusionmentioning

confidence: 99%

Content Analysis by the Crowd: Assessing the Usability of Crowdsourcing for Coding Latent Constructs

Lind

Gruber

Boomgaarden

2017

Communication Methods and Measures

View full text Add to dashboard Cite

Crowdsourcing platforms are commonly used for research in the humanities, social sciences and informatics, including the use of crowdworkers to annotate textual material or visuals. Utilizing two empirical studies, this article systematically assesses the potential of crowdcoding for less manifest contents of news texts, here focusing on political actor evaluations. Specifically, Study 1 compares the reliability and validity of crowdcoded data to that of manual content analyses; Study 2 proceeds to investigate the effects of material presentation, different types of coding instructions and answer option formats on data quality. We find that the performance of the crowd recommends crowdcoded data as a reliable and valid alternative to manually coded data, also for less manifest contents. While scale manipulations affected the results, minor modifications of the coding instructions or material presentation did not significantly influence data quality. In sum, crowdcoding appears a robust instrument to collect quantitative content data.

show abstract

“…For this purpose, we used an automated content analysis method based on supervised machine learning (Burscher et al 2014). Two yes/no questions are used in this method to determine whether an article entails conflict frame.…”

Section: Samplementioning

confidence: 99%

Towards A Typology of Conflict Frames

2017

View full text Add to dashboard Cite

Conflict-framing literature has suffered from a lack of consistent conceptualization and consequently the aim of this paper is to unravel the dimensionality of conflict frames. We conducted a content analysis (N = 1536) to develop a typology of conflict news coverage. Using factor analysis, different aspects of conflict news are distinguished with level of substantiveness and interventionism as the main dimensions. Furthermore, the study focuses on the occurrence of these different types of conflict frames in the news and the role of contextual factors. For example, results indicate that articles with conflict frames contain more interventionism and less strategic framing online, more journalistic intervention in quality newspapers and less substantive news in election times when compared to routine periods. The study contributes to the literature by offering a more nuanced view of the presence of different types of conflict news in the media.

show abstract

Teaching the Computer to Code Frames in News: Comparing Two Supervised Machine Learning Approaches to Frame Analysis

Cited by 93 publications

References 52 publications

Nationality swapping in the Olympic Games 1978–2017: A supervised machine learning approach to analysing discourses of citizenship and nationhood

Nationality swapping in the Olympic Games 1978–2017: A supervised machine learning approach to analysing discourses of citizenship and nationhood

Content Analysis by the Crowd: Assessing the Usability of Crowdsourcing for Coding Latent Constructs

Towards A Typology of Conflict Frames

Contact Info

Product

Resources

About