{"references": ["Bolukbasi, Tolga, Kai-Wei Chang, James Y Zou, Venkatesh Saligrama, and Adam T Kalai. 2016. \"Man Is to Computer Programmer as Woman Is to Homemaker? Debiasing Word Embeddings,\" 9. https://arxiv.org/abs/1607.06520.", "Caliskan, Aylin, Joanna J. Bryson, and Arvind Narayanan. 2017. \"Semantics Derived Automatically from Language Corpora Contain Human-Like Biases.\" Science 356 (6334): 183\u201386. https://doi.org/10.1126/science.aal4230.", "Egerod, Benjamin, and Robert Klemmensen. 2020. \"Scaling Political Positions from Text: Assumptions, Methods and Pitfalls.\" In, 498\u2013521. 1 Oliver's Yard, 55 City Road London EC1Y 1SP: SAGE Publications Ltd. https://doi.org/10.4135/9781526486387.n30.", "Kurita, Keita, Nidhi Vyas, Ayush Pareek, Alan W Black, and Yulia Tsvetkov. 2019. \"Measuring Bias in Contextualized Word Representations.\" https://doi.org/10.18653/v1/W19-3823.", "Lauderdale, Benjamin E., and Alexander Herzog. 2016. \"Measuring Political Positions from Legislative Speech.\" Political Analysis 24 (3): 374\u201394. https://doi.org/10.1093/pan/mpw017. Rheault, Ludovic, and Christopher Cochrane. 2020. \"Word Embeddings for the Analysis of Ideological Placement in Parliamentary Corpora.\" Political Analysis 28 (1): 112\u201333. https://doi.org/10.1017/pan.2019.26.", "Smilkov, Daniel, Nikhil Thorat, Charles Nicholson, Emily Reif, Fernanda B. Vi\u00e9gas, and Martin Wattenberg. 2016. \"Embedding Projector: Interactive Visualization and Interpretation of Embeddings.\" http://arxiv.org/abs/1611.05469.", "Volkens, Andrea, Tobias Burst, Werner Krause, Pola Lehmann, Theres Matthie\u00df, Sven Regel, Bernhard We\u00dfels, Lisa Zehnter, and Wissenschaftszentrum Berlin F\u00fcr Sozialforschung (WZB). 2021. \"Manifesto Project Dataset.\" https://doi.org/10.25522/MANIFESTO.MPDS.2021A."]}

Retrieving valid numerical estimates for positional stances toward politics has always been challenging in many disciplines. While social science has long used surveys and content analysis to this end, some methods try to scale positions from textual data automatedly. As one of these, the idea of representing words in a geometric space has been rediscovered. Generating valid estimates from textual data would save countless hours of coding. Connectedly, valid automation of such estimation would significantly increase the visible universe of analyzable textual data. It would also enable researchers to get fine-grained numerical values, perform algebraic calculations with them, and help standardize text as data usage across studies.