Catalogue
Every dataset is built on the same pipeline and the same sampling frame, so a record from one joins cleanly to a record from another on region and date.
01
The base layer. Every topic in the taxonomy gets a weekly salience share and a mean stance per region, computed on transcribed speech rather than captions or hashtags. Confidence intervals ship with every point.
Dataset detail02
Daily tracking of named political actors, the issues attached to them and the narrative frames used to carry them. Built for teams that need to see a frame move before it reaches national press.
Dataset detail03
Category-level demand signal derived from what people say they are about to buy, switch away from, or cannot afford. Brand mentions are resolved to a canonical entity list you can map to your own tickers.
Dataset detail04
The longest history we carry. Sentiment and intensity on labour, prices, housing and credit — designed to be tested against official releases such as the DOL claims print and CPI.
Dataset detailTell us the market and the question. We return a real slice — schema, sample sizes and confidence intervals included — not a brochure.
