A new, scalable measure of party ideology uses the descriptive tags found in political parties' Wikipedia infoboxes. By treating those tags as signals under a simple tag-assignment model, the approach places both parties and ideology labels in a shared spatial scale.
🗂️ How party positions were inferred
- Data source: ideology tags supplied in infoboxes on political parties' Wikipedia pages.
- Modeling approach: a simple model of tag assignment is used to scale tags and estimate the locations of parties and ideologies in a common space.
🔎 What the evidence shows
- The recovered scale maps cleanly onto familiar left–right distinctions.
- Estimated party positions correlate well with ratings from existing large-scale expert surveys, with the strongest alignment to general left–right ideology ratings.
- Party position estimates demonstrate high stability in a test–retest scenario.
📈 Why this matters
- The Wikipedia-based measure produces valid and reliable left–right scores that are comparable to scores obtained via conventional expert coding methods.
- The technique offers potentially unlimited party coverage and a measurement strategy that can be applied beyond Wikipedia to other tag-based sources.
