Recipes / Compare how two markets covered the same event
Compare how two markets covered the same event
/search in semantic mode. The parameters matter less
than the reasoning behind them, so that is most of what is below.
The request
GET /search?q=<event>&mode=semantic&language=<a>&from=…&to=…
GET /search?q=<event>&mode=semantic&language=<b>&from=…&to=…Why these parameters
The one recipe here that deliberately does **not** collapse to stories. When you are studying how framing differs, the individual articles are your data and clustering destroys exactly what you are trying to measure. Run one query per language over an identical window so the comparison is like for like.
What comes back
Two article sets over the same period. Compare volume, the tone distribution, and which outlets participated. Volume differences usually say more about the size of the local press than about attention, so normalise before concluding anything.
How this goes wrong
Comparing sentiment across markets without fixing the outlet sets. Editorial stance varies more between publishers than between countries, so an unfixed comparison measures which publishers each query happened to reach.
Adapting it
To compare framing rather than volume, sample a fixed number of articles per market rather than taking everything, or the larger press will dominate any qualitative reading. To compare over time, hold both the outlet sets and the window length constant between runs; changing either makes the series meaningless and the change is easy to make accidentally.
Running it for real
This is analysis rather than monitoring, so run it deliberately rather than on a schedule. Record the exact queries, windows and outlet sets alongside the results — comparative findings are the ones most likely to be challenged, and being unable to reproduce your own numbers six weeks later is a bad position to defend from.
When this is the wrong tool
Comparison across markets is the analysis most likely to produce a confident wrong answer, because so many things differ at once. Press size, publication rhythm, syndication density and editorial convention all vary by market, and any of them can produce a difference that looks substantive and is structural. Normalise for press size before comparing volume, hold windows and outlet sets constant, and be sceptical of any finding that survives only one framing. This recipe is also not suitable for automated monitoring — it needs a person deciding what the comparison means, and a scheduled version of it will produce a time series whose movements are mostly artefacts.