For the substantial analysis conducted in this book, parties’ policy positions at two stages of the representation process must be identified. This is achieved through an automated content analysis comprising two steps. This chapter describes the second step, in which domain-specific text corpora created in the previous step are used to determine the parties’ domain-specific positions. These positions are estimated using the unsupervised scaling method Wordfish. The chapter details which documents are selected for the analysis and how the data is prepared to enhance performance. Separate positions are estimated for the electoral arena and each parliamentary year, resulting in domain-specific policy positions of five parties at up to six different points in time during six legislative terms. The chapter concludes with an extensive discussion of the validity of the new data.