Topic Modeling for Exploring Cancer-Related Coverage in Journalistic Texts

Hariman, Naomi; Vries, Marjolein de; Smeets, Ionica

doi:10.1007/978-3-030-31978-6_4

Cited by 1 publication

(5 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The distances of topics are scaled multidimensionally onto two axes [50]. Rela tively large and nonoverlapping bubbles in the map suggest a proper topic model resul [49]. Each bubble represents a different topic ranging from Topic 1 to Topic 7 in our study The bubbles shown in Figure 2 are relatively large and do not overlap, thus confirming the reasonability of using seven topics and suggesting that this approach produces a good topic model.…”

Section: Topic Modeling Resultssupporting

confidence: 63%

“…The distances of topics are scaled multidimensionally onto two axes [50]. Relatively large and nonoverlapping bubbles in the map suggest a proper topic model result [49]. Each bubble represents a different topic ranging from Topic 1 to Topic 7 in our study.…”

Section: Topic Modeling Resultsmentioning

confidence: 97%

“…The inter-topic distance map is shown in Figure 2. Each bubble in the inter-topic distance map represents a topic, and the area of the bubble indicates the prevalence of this topic [49]. The distances of topics are scaled multidimensionally onto two axes [50].…”

Section: Topic Modeling Resultsmentioning

confidence: 99%

“…The bubbles shown in Figure 2 are relatively large and do not overlap, thus confirming the reasonability of using seven topics and suggesting that this approach produces a good topic model. The topics are ordered in descending order of prevalence in the corpus [49]. The inter-topic distance map is shown in Figure 2.…”

Section: Topic Modeling Resultsmentioning

confidence: 99%

“…Each bubble represents a different topic ranging from Topic 1 to Topic 7 in our study The bubbles shown in Figure 2 are relatively large and do not overlap, thus confirming the reasonability of using seven topics and suggesting that this approach produces a good topic model. The topics are ordered in descending order of prevalence in the corpus [49] Table 3 shows the results of the topic model including seven topics and the top twenty relevant words for each topic in the corpus. The numbers of topics are in accord ance with the numbers shown in the inter-topic distance map.…”

Section: Topic Modeling Resultsmentioning

confidence: 99%

See 4 more Smart Citations

Exploring the Influencing Factors of COVID-19 Vaccination Willingness among Young Adults in China

Huang

et al. 2023

IJERPH

View full text Add to dashboard Cite

Vaccine uptake is considered as one of the most effective methods of defending against COVID-19 (coronavirus disease 2019). However, many young adults are hesitant regarding COVID-19 vaccines, and they actually play an important role in virus transmission. Based on a multi-theory model, this study aims to explore the influencing factors related to COVID-19 vaccine willingness among young adults in China. Using semi-structured interviews, this study explored the factors that would motivate young adults with vaccine hesitancy to get the COVID-19 vaccine. Thematic analysis was used to analyze the interview data with topic modeling as a complementarity method. After comparing the differences and similarities of results generated by thematic analysis and topic modeling, this study ultimately identified ten key factors related to COVID-19 vaccination intention, including the effectiveness and safety of vaccines, application range of vaccine, etc. This study combined thematic analysis with machine learning and provided a comprehensive and nuanced picture of facilitating factors for COVID-19 vaccine uptake among Chinese young adults. Results may be taken as potential themes for authorities and public health workers in vaccination campaigns.

show abstract

Section: Topic Modeling Resultssupporting

confidence: 63%

Section: Topic Modeling Resultsmentioning

confidence: 97%