Political text scaling meets computational semantics

Nanni, Federico ; Glavaš, Goran ; Rehbein, Ines ; Ponzetto, Simone Paolo ; Stuckenschmidt, Heiner

PDF
3485666.pdf - Veröffentlichte Version
Download (1MB)

DOI:	https://doi.org/10.1145/3485666
URL:	https://dl.acm.org/doi/full/10.1145/3485666
Weitere URL:	https://www.researchgate.net/publication/332413071...
URN:	urn:nbn:de:bsz:180-madoc-625958
Dokumenttyp:	Zeitschriftenartikel
Erscheinungsjahr:	2021
Titel einer Zeitschrift oder einer Reihe:	ACM/IMS Transactions on Data Science : TDS
Band/Volume:	2
Heft/Issue:	4, Article 29
Seitenbereich:	1-27
Ort der Veröffentlichung:	New York, NY
Verlag:	Association for Computing Machinery
ISSN:	2577-3224 , 2691-1922
Verwandte URLs:	https://www.semanticscholar.org/paper/Po...
Sprache der Veröffentlichung:	Englisch
Einrichtung:	Außerfakultäre Einrichtungen > SFB 884
Bereits vorhandene Lizenz:	Creative Commons Namensnennung 4.0 International (CC BY 4.0)
Fachgebiet:	004 Informatik
Freie Schlagwörter (Englisch):	automated political text analysis , text-as-data , political text scaling , multilinguality
Abstract:	During the past 15 years, automatic text scaling has become one of the key tools of the Text as Data community in political science. Prominent text-scaling algorithms, however, rely on the assumption that latent positions can be captured just by leveraging the information about word frequencies in documents under study. We challenge this traditional view and present a new, semantically aware text-scaling algorithm, SemScale, which combines recent developments in the area of computational linguistics with unsupervised graph-based clustering. We conduct an extensive quantitative analysis over a collection of speeches from the European Parliament in five different languages and from two different legislative terms, and we show that a scaling approach relying on semantic document representations is often better at capturing known underlying political dimensions than the established frequency-based (i.e., symbolic) scaling method. We further validate our findings through a series of experiments focused on text preprocessing and feature selection, document representation, scaling of party manifestos, and a supervised extension of our algorithm. To catalyze further research on this new branch of text-scaling methods, we release a Python implementation of SemScale with all included datasets and evaluation procedures.