Singapore Management University
Kenneth Benoit
Dean, School of Social Sciences, and Lee Kong Chian Professor of Computational Social Science
My research uses large language models and machine learning to analyze political texts and social media, and my substantive work covers comparative party competition, the European Parliament, and electoral systems. My software includes the quanteda family of R packages for quantitative text analysis, with the nine packages I maintain on the Comprehensive R Archive Network (CRAN) downloaded over 6 million times.
My leadership roles have involved a mix of academic and organisational experience. Previously, I directed the Data Science Institute at the LSE and headed its Department of Methodology; before that I was Head of the Department of Political Science at Trinity College Dublin. I co-founded the European Political Science Association and served as its Executive Director until 2024, and I am now a Director and Treasurer of the European Political Science Society as well as a member of Singapore's Social Science Research Council. Leadership →
Projects
AI-Assisted Content Analysis
A book under contract with Sage, building on the quallmer R package and research on using large language models to analyze political texts. The quallmer R package development is part of this project.
quanteda
The quanteda family of R packages for the quantitative analysis of textual data, including companion packages for plotting, modelling, and obtaining statistics for textual data, plus packages for interfacing with Python’s spaCy (spacyr) and reading texts (readtext), multilingual stopwords, and counting syllables.
Expert surveys (PPMD)
Expert survey estimates of the policy positions of political parties in 47 countries, collected with Michael Laver for Party Policy in Modern Democracies.
Selected publications
LLMs and AI
View all 4 →
Using Large Language Models to Analyze Political Texts Through Natural Language Understanding
Measuring issue salience for political parties using LLMs
AI and Data Science for Public Policy
Text as data
View all 21 →
Extracting Policy Positions from Political Texts Using Words as Data-
Crowd-Sourced Text Analysis: Reproducible and Agile Production of Political Data
-
Measuring and Explaining Political Sophistication Through Textual Complexity
Measuring party positions
View all 21 →
Estimating party policy positions: Comparing expert surveys and hand-coded content analysis
Scaling Policy Preferences From Coded Political Texts-
Treating Words as Data with Error: Uncertainty in Text Statements of Policy Positions
Party competition
View all 19 →
Party Policy and Group Affiliation in the European Parliament-
The Basic Arithmetic of Legislative Decisions
-
The Evolution of Party Systems Between Elections
Campaign spending
View all 4 →-
The Campaign Value of Incumbency: A New Solution to the Puzzle of Less Effective Incumbent Spending
Incumbent and Challenger Campaign Spending Effects in Proportional Electoral Systems: The Irish Elections of 2002
For A Few Euros More: Campaign Spending Effects in the Irish Local Elections of 1999
Electoral systems
View all 15 →
Electoral Laws as Political Consequences: Explaining the Origins and Change of Electoral Institutions-
Models of Electoral System Change
Duverger’s Law and the Study of Electoral Systems
