The next speaker in this session at the 2026 International Communication Association conference in Cape Town is Magdalena Wojcieszak, who is presenting work towards a news content quality classifier. The consumption of online news is diverse: people consume traditional news article,s blog content, YouTube news videos, news podcasts, and many different formats.
But how do we assess the quality of all this content? There are various different measures for this, and many of them are problematic, not least for their domain- rather than article-level assessments and their conflation of quality with ideological bias; some also include factuality and other features as a contributor to overall quality scores.
This new approach focusses on the key journalistic features of clarity, depth, sourcing, engaging writing, (avoidance of) clickbait, importance, (absence of) personal frames, and (avoidance of) one-sidedness. Ideological bias is not explicitly included here, but can be included in further downstream analysis.
The project developed a transformer-based classifier which focusses on these attributes, and tested this on a set of some 1,400 manually labelled news excerpts in English. It then applied this to some 194,000 news articles from 28 English-language outlets to assess their content quality; a factor analysis identified three broader dimensions: rigorous and substantial news (clarity, depth, sources, non-clickbait); severity and civic seriousness (importance, non-personal reporting , non-engagement); and impartiality (non-onesidedness, non-ideological bias).
These results do not correlate directly with other existing media quality rating approaches, and this is partly the point: these rating schemes all have their own problems, and do not capture article-level differences.
The next step here is to apply these measures to content from alternative news platforms and formats such as Medium, Substack, YouTube, and podcasts. It will be interesting to see how these rate against these three assessment dimensions.
