Quantitative analysis of large amounts of journalistic texts using topic modelling

Jacobi, Carina; Atteveldt, Wouter van; Welbers, Kasper

doi:10.4324/9781315115047-7

Cited by 50 publications

(58 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…9 The lower the perplexity, the better the prediction. However, the best fit does not have to accord with the optimal interpretability of the topics (Chang et al, 2009;Jacobi et al, 2016). 10 We also equate plural and singular nouns.…”

Section: The Leiden Manifestomentioning

confidence: 99%

Co‐word maps and topic modeling: A comparison using small and medium‐sized corpora (N < 1,000)

Leydesdorff

Nerghes

2016

Asso for Info Science & Tech

View full text Add to dashboard Cite

Induced by “big data,” “topic modeling” has become an attractive alternative to mapping co‐words in terms of co‐occurrences and co‐absences using network techniques. Does topic modeling provide an alternative for co‐word mapping in research practices using moderately sized document collections? We return to the word/document matrix using first a single text with a strong argument (“The Leiden Manifesto”) and then upscale to a sample of moderate size (n = 687) to study the pros and cons of the two approaches in terms of the resulting possibilities for making semantic maps that can serve an argument. The results from co‐word mapping (using two different routines) versus topic modeling are significantly uncorrelated. Whereas components in the co‐word maps can easily be designated, the topic models provide sets of words that are very differently organized. In these samples, the topic models seem to reveal similarities other than semantic ones (e.g., linguistic ones). In other words, topic modeling does not replace co‐word mapping in small and medium‐sized sets; but the paper leaves open the possibility that topic modeling would work well for the semantic mapping of large sets.

show abstract

Section: The Leiden Manifestomentioning

confidence: 99%

Co‐word maps and topic modeling: A comparison using small and medium‐sized corpora (N < 1,000)

Leydesdorff

Nerghes

2016

Asso for Info Science & Tech

View full text Add to dashboard Cite

show abstract

“…It is an alternative to the dictionary-based analysis, which is the most popular automated analysis approach [19], and allows to work with a corpus without a prior knowledge, letting the topics emerge from the data. In the same spirit of our work, many authors, as for instance [20,21,22], emphasized the advantage of using automated text classification in social science research. For example, topic modeling have been used in discourse analysis [23], analysis of social media discussions [24,25,26], or recognition of entities in news articles [27].…”

Section: Introductionmentioning

confidence: 82%

Quantifying time-dependent Media Agenda and public opinion by topic modeling

Pinto

Albanese

Dorso

et al. 2019

Physica A: Statistical Mechanics and its Applications

View full text Add to dashboard Cite

The mass media plays a fundamental role in the formation of public opinion, either by defining the topics of discussion or by making an emphasis on certain issues. Directly or indirectly, people get informed by consuming news from the media. Naturally, two questions appear: What are the dynamics of the agenda and how the people become interested in their different topics? These questions cannot be answered without proper quantitative measures of agenda dynamics and public attention. In this work we study the agenda of newspapers in comparison with public interests by performing topic detection over the news. We define Media Agenda as the distribution of topic's coverage by the newspapers and Public Agenda as the distribution of public interest in the same topic space. We measure agenda diversity as a function of time using the Shannon entropy and differences between agendas using the Jensen-Shannon distance. We found that the Public Agenda is less diverse than the Media Agenda, especially when there is a very attractive topic and the audience naturally focuses only on this one. Using the same methodology we detect coverage bias in newspapers. Finally, it was possible to identify a complex agenda-setting dynamics within a given topic where the least sold newspaper triggered a public debate via a positive feedback mechanism with social networks discussions which install the issue in the Media Agenda.

show abstract

“…This factoranalytic approach is comparable to topic modeling that uses word distributions to detect topics, assigning words belonging to specific topics, and the co-occurrences of the words in topics, especially those using Latent Dirichlet Allocation (LDA), which assigns words into clusters using probability distributions (Blei, Ng, & Jordan, 2003). This method has been applied to the analysis of large sets of documents (for example, Jacobi, van Atteveldt, & Welbers, 2016).…”

Section: Theoretical Framework: Network Approachmentioning

confidence: 99%

Automated analysis of actor–topic networks on twitter: New approaches to the analysis of socio‐semantic networks

Hellsten

Leydesdorff

2019

Asso for Info Science & Tech

View full text Add to dashboard Cite

Social media data provide increasing opportunities for the automated analysis of large sets of textual documents. So far, automated tools have been developed either to account for the social networks among participants in the debates, or to analyze the content of these debates. Less attention has been paid to mapping cooccurrences of actors (participants) and topics (content) in online debates that can be considered as socio-semantic networks. We propose a new, automated approach that uses the whole matrix of co-addressed topics and actors for understanding and visualizing online debates. We show the advantages of the new approach with the analysis of two data sets: first, a large set of Englishlanguage Twitter messages at the Rio + 20 meeting, in June 2012 (72,077 tweets), and second, a smaller data set of Dutch-language Twitter messages on bird flu related to poultry farming in 2015-2017 (2,139 tweets). We discuss the theoretical, methodological, and substantive implications of our approach, also for the analysis of other social media data.

show abstract

Quantitative analysis of large amounts of journalistic texts using topic modelling

Cited by 50 publications

References 0 publications

Co‐word maps and topic modeling: A comparison using small and medium‐sized corpora (N < 1,000)

Co‐word maps and topic modeling: A comparison using small and medium‐sized corpora (N < 1,000)

Quantifying time-dependent Media Agenda and public opinion by topic modeling

Automated analysis of actor–topic networks on twitter: New approaches to the analysis of socio‐semantic networks

Contact Info

Product

Resources

About