The paper presents a novel method for extracting policy positions from political texts, treating texts as collections of word data rather than interpretative discourses. This approach is compared with traditional text analysis methods and applied to replicate published estimates of policy positions of British and Irish political parties on economic and social policy dimensions. The method is also extended to analyze policy positions in non-English languages and legislative speeches. The technique uses word frequencies to estimate policy positions, providing uncertainty measures for the estimates, which allows for assessing the significance of differences between estimated positions. The authors argue that their "language-blind" word scoring technique is more efficient and accurate than traditional methods, offering a significant advancement in the field of political text analysis.The paper presents a novel method for extracting policy positions from political texts, treating texts as collections of word data rather than interpretative discourses. This approach is compared with traditional text analysis methods and applied to replicate published estimates of policy positions of British and Irish political parties on economic and social policy dimensions. The method is also extended to analyze policy positions in non-English languages and legislative speeches. The technique uses word frequencies to estimate policy positions, providing uncertainty measures for the estimates, which allows for assessing the significance of differences between estimated positions. The authors argue that their "language-blind" word scoring technique is more efficient and accurate than traditional methods, offering a significant advancement in the field of political text analysis.