Dataset Information

Characterising Online News Comments: A Multi-Dimensional Cruise Through Online Registers.

ABSTRACT: News organisations often allow public comments at the bottom of their news stories. These comments constitute a fruitful source of data to investigate linguistic variation online; their characteristics, however, are rather understudied. This paper thus contributes to the description of online news comments and online language in English. In this spirit, we apply multi-dimensional analysis to a large dataset of online news comments and compare them to a corpus of online registers, thus placing online comments in the space of register variation online. We find that online news comments are involved-evaluative and informational at the same time, but mostly argumentative in nature, with such argumentation taking an informal shape. Our analyses lead us to conclude that online registers are a different mode of communication, neither spoken nor written, with individual variation across different types of online registers.

SUBMITTER: Ehret K

PROVIDER: S-EPMC8238081 | biostudies-literature | 2021

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Characterising Online News Comments: A Multi-Dimensional Cruise Through Online Registers.

Ehret Katharina K Taboada Maite M

Frontiers in artificial intelligence 20210614

News organisations often allow public comments at the bottom of their news stories. These comments constitute a fruitful source of data to investigate linguistic variation online; their characteristics, however, are rather understudied. This paper thus contributes to the description of online news comments and online language in English. In this spirit, we apply multi-dimensional analysis to a large dataset of online news comments and compare them to a corpus of online registers, thus placing on ...[more]

PMID: 34195609

Similar Datasets

Project description:BackgroundThe aim of this study was to understand online public perceptions of the debate surrounding the choice of annual influenza vaccinations or wearing masks as a condition of employment for healthcare workers, such as the one enacted in British Columbia in August 2012.MethodsFour national and 82 local (British Columbia) Canadian online news sites were searched for articles posted between August 2012 and May 2013 containing the words "healthcare workers" and "mandatory influenza vaccinations/immunizations" or "mandatory flu shots and healthcare workers." We included articles from sources that predominantly concerned our topic of interest and that generated reader comments. Two researchers coded the unedited comments using thematic analysis, categorizing codes to allow themes to emerge. In addition to themes, the comments were categorized by: 1) sentiment towards influenza vaccines; 2) support for mandatory vaccination policies; 3) citing of reference materials or statistics; 4) self-identified health-care worker status; and 5) sharing of a personal story.Results1163 comments made by 648 commenters responding to 36 articles were analyzed. Popular themes included concerns about freedom of choice, vaccine effectiveness, patient safety, and distrust in government, public health, and the pharmaceutical industry. Almost half (48%) of commenters expressed a negative sentiment toward the influenza vaccine, 28% were positive, 20% were neutral, and 4% expressed mixed sentiment. Of those who commented on the policy, 75% did not support the condition to work policy, while 25% were in favour. Of the commenters, 11% self-identified as healthcare workers, 13% shared personal stories, and 18% cited a reference or statistic.InterpretationThe perception of the influenza vaccine in the comment sections of online news sites is fairly poor. Public health agencies should consider including online forums, comment sections, and social media sites as part of their communication channels to correct misinformation regarding the benefits of HCW influenza immunization and the effectiveness of the vaccine.

Project description:Attitudes are a fundamental characteristic of human activity. Their main function is the situational assessment of phenomena in practice to maintain action ability and to provide orientation in social interaction. In sociolinguistics, research into attitudes toward varieties and their speakers is a central component of the analysis of linguistic and cultural dynamics. In recent years, computational linguistics has also shown an increased interest in the social conditionality of language. To date, such approaches have lacked a linguistically based theory of attitudes, which, for example, enables an exact terminological differentiation between publicly taken stances and the assumed underlying attitudes. Against this backdrop, the present study contributes to the connection of sociolinguistic and computational linguistic approaches to the analysis of language attitudes. We model a free text corpus of user comments from the RTL.lu news platform using representation learning (Word2Vec). In the aggregated data, we look for contextual similarities between vector representations of words that provide evidence of stances toward multilingualism in Luxembourg. We then contrast this data with the results of a quantitative attitudes study, which was carried out as part of the crowdsourcing project "Schnëssen." The combination of the different datasets enables the reconstruction of socially pertinent attitudes represented in public discourse. The results demonstrate the central importance of attitudes toward the different languages in Luxembourg for the cultural self-understanding of the population. We also introduce a tool for the automatic orthographic correction of Luxembourgish texts (spellux). In view of the ongoing standardization of Luxembourgish and a lack of rule knowledge in the population, orthographic variation-among other factors like code-switching or regional dialects-poses a great challenge for the automatic processing of text data. The correction tool enables the orthographic normalization of Luxembourgish texts and with that a consolidation of the vocabulary for the training of word embedding models.

Dataset Information

Characterising Online News Comments: A Multi-Dimensional Cruise Through Online Registers.

Publications

Characterising Online News Comments: A Multi-Dimensional Cruise Through Online Registers.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets