This paper estimates the data intensity of occupations/sectors (i.e. the share of job postings per occupation/sector related to the production of data) using natural language processing (NLP) on job advertisements in the United Kingdom, Canada and the United States. Online job advertisement data collected by Lightcast provide timely and disaggregated insights into labour demand and skill requirements of different professions. The paper makes three major contributions. First, indicators created from the Lightcast data add to the understanding of digital skills in the labour market. Second, the results may advance the measurement of data assets in national account statistics. Third, the NLP methodology can handle up to 66 languages and can be adapted to measure concepts beyond digital skills. Results provide a ranking of data intensity across occupations, with data analytics activities contributing most to aggregate data intensity shares in all three countries. At the sectoral level, the emerging picture is more heterogeneous across countries. Differences in labour demand primarily explain those variations, with low data-intensive professions contributing most to aggregate data intensity in the United Kingdom. Estimates of investment in data, using a sum of costs approach and sectoral intensity shares, point to lower levels in the United Kingdom and Canada than in the United States.