手法を比較

	Wordfish Scaling	Ideal Point Estimation	Wordscores
分野	Political Science	Political Science	心理測定学
系統	Latent structure	Latent structure	Latent structure
提唱年	2008	2004	2003
提唱者	Jonathan Slapin and Sven-Oliver Proksch	Clinton, Jackman & Rivers (Bayesian formulation); Poole & Rosenthal (spatial tradition)	Michael Laver, Kenneth Benoit, John Garry
種類	Unsupervised latent-position model for word-count data	Latent-variable spatial model of binary choice data	Text analysis and dimension reduction
原典	Slapin, J. B., & Proksch, S.-O. (2008). A Scaling Model for Estimating Time-Series Party Positions from Texts. American Journal of Political Science, 52(3), 705–722.	Clinton, J., Jackman, S., & Rivers, D. (2004). The Statistical Analysis of Roll Call Data. American Political Science Review, 98(2), 355–370.	Laver, M., Benoit, K., & Garry, J. (2003). Extracting policy positions from political texts using words as data. American Political Science Review, 97(2), 311-331.
別名	Wordfish text scaling, Poisson scaling of texts, Unsupervised text scaling, Wordfish position estimation	Ideal point model, Item response theory for roll calls, Spatial voting model, Bayesian ideal points	—
関連	4	4	5
概要	Wordfish scaling is an unsupervised text-as-data method that estimates a single latent position for each political document — a party manifesto, a legislative speech, a press release — directly from its word frequencies, without any reference texts or hand coding. Introduced by Slapin and Proksch in 2008, it models word counts as draws from a Poisson distribution whose rate depends on a document position and word-specific parameters, recovering, for example, a left–right ordering of parties purely from how often each word appears in each text.	Ideal point estimation recovers the latent policy positions — ideal points — of political actors from their observed binary choices, most often legislators' yea/nay votes on roll calls. Building on the spatial theory of voting and formalized as a Bayesian item-response model by Clinton, Jackman, and Rivers in 2004, it places each legislator and each bill in a low-dimensional policy space and estimates positions so that the probability a legislator votes yea increases as the bill's 'yea' outcome moves closer to that legislator's ideal point.	Wordscores is a text-based scaling method developed by Laver, Benoit, and Garry (2003) that estimates the policy positions of political actors based on word frequencies in their texts. By comparing word usage in reference texts of known positions with test texts, the method infers the latent political dimension of any document without requiring manual coding or training data.