MétaCan
Menu
Back to cohort
Record W4400529059 · doi:10.1145/3626772.3661362

Reflections on the Coding Ability of LLMs for Analyzing Market Research Surveys

2024· article· en· W4400529059 on OpenAlexaff
Shi Zong, Santosh Kolagati, Amit Chaudhary, Josh Seltzer, Jimmy Lin

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldSocial Sciences
TopicComputational and Text Analysis Methods
Canadian institutionsUniversity of Waterloo
Fundersnot available
KeywordsCoding (social sciences)Market researchData scienceComputer scienceBusinessMarketingSocial scienceSociology

Abstract

fetched live from OpenAlex

The remarkable success of large language models (LLMs) has drawn people's great interest in their deployment in specific domains and downstream applications. In this paper, we present the first systematic study of applying large language models (in our case, GPT-3.5 and GPT-4) for the automatic coding (multi-class classification) problem in market research. Our experimental results show that large language models could achieve a macro F1 score of over 0.5 for all our collected real-world market research datasets in a zero-shot setting. We also provide in-depth analyses of the errors made by the large language models. We hope this study sheds light on the lessons we learn and the open challenges large language models have when adapting to a specific market research domain.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.162
metaresearch head score (Gemma)0.490
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Not applicable · Consensus signal: none
GenreCandidate signal: Commentary · Consensus signal: none
Teacher disagreement score0.162
Threshold uncertainty score0.854

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.1620.490
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.002
Bibliometrics0.0050.003
Science and technology studies0.0020.018
Scholarly communication0.0130.022
Open science0.0040.007
Research integrity0.0040.011
Insufficient payload (model declined to judge)0.0060.002

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.449
GPT teacher head0.598
Teacher spread0.149 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designNot applicable
Domainnot available
GenreCommentary

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations1
Published2024
Admission routes1
Has abstractyes

Explore more

Same topicComputational and Text Analysis MethodsFrench-language works237,207