Connecting Natural Language Processing and Survey Methodology: Potentials, Challenges, and Open Questions

MCML Authors

Bolei Ma

→ Group Frauke Kreuter
 Social Data Science and AI

Anna-Carolina Haensch

Dr.

→ Group Frauke Kreuter
 Social Data Science and AI

Tobias Holtdirk

→ Group Frauke Kreuter
 Social Data Science and AI

Frauke Kreuter

Prof. Dr.

Principal Investigator

Social Data Science and AI

Abstract

Recent generative AI technologies, particularly Large Language Models (LLMs), have increased interest in Natural Language Processing (NLP) methods for scientists and practitioners across disciplines. In this position paper, we highlight one such discipline — survey methodology, which not only uses more and more NLP techniques, e.g., using LLMs to simulate survey respondents, but also stands to benefit NLP, e.g., informing the design of NLP annotation and evaluation tasks. We argue for increasing synergies between NLP and Survey Methodology to realize the potential at their intersection. We also outline challenges that impede progress on these potential synergies and present 10 open questions to encourage further reflection.

misc

---

Preprint

May. 2025

---

Authors

I. Sen • B. Ma • G. Ahnert • A.-C. Haensch • T. Holtdirk • F. Kreuter • M. Strohmaier

---

Links

DOI

---

Research Area

 C4 | Computational Social Sciences