A sentiment-based approach to measuring multidimensional party positions using transformer

Existing automated position scaling models from texts rely on the conflict-driven assumption, forcing models to search the linguistic space for differentiating features between political subjects. This leads models to conflate rhetorical styles with political sentiments when subjects are not inherently conflictual. This article introduces ContextScale, a sentiment-based position scaling framework leveraging pre-trained Transformer models to predict policy topics and political sentiments and measure topic-specific position scores across multiple policy dimensions at the sequence level. ContextScale offers an alternative way to gauge party positions, focusing on how political texts express attitudes toward policy issues rather than on contrast between actors. Validity tests demonstrate its ability to capture nuances in party positioning and its adaptability across languages, text domains, and theoretical models.

Authors

Institutions

Publication Details

Journal
Political Science Research and Methods
Published
2026-11-19
DOI
https://doi.org/10.1017/psrm.2026.10145
Primary Topic
Computational and Text Analysis Methods
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

A sentiment-based approach to measuring multidimensional party positions using transformer

Hung Hoang Viet Nguyen
Political Science Research and Methods
Computational and Text Analysis Methods
article

A sentiment-based approach to measuring multidimensional party positions using transformer

Hung Hoang Viet Nguyen
article en

Abstract

Existing automated position scaling models from texts rely on the conflict-driven assumption, forcing models to search the linguistic space for differentiating features between political subjects. This leads models to conflate rhetorical styles with political sentiments when subjects are not inherently conflictual. This article introduces ContextScale, a sentiment-based position scaling framework leveraging pre-trained Transformer models to predict policy topics and political sentiments and measure topic-specific position scores across multiple policy dimensions at the sequence level. ContextScale offers an alternative way to gauge party positions, focusing on how political texts express attitudes toward policy issues rather than on contrast between actors. Validity tests demonstrate its ability to capture nuances in party positioning and its adaptability across languages, text domains, and theoretical models.

Political Science Research and Methods
University of Bremen (DE)
Computational and Text Analysis Methods
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon