English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The field of machine learning has recently made significant progress inreducing the requirements for labelled training data when building new models.These `cheaper' learning techniques hold significant potential for the socialsciences, where development of large labelled training datasets is often asignificant practical impediment to the use of machine learning for analyticaltasks. In this article we review three `cheap' techniques that have developedin recent years: weak supervision, transfer learning and prompt engineering.For the latter, we also review the particular case of zero-shot prompting oflarge language models. For each technique we provide a guide of how it worksand demonstrate its application across six different realistic social scienceapplications (two different tasks paired with three different dataset makeups).We show good performance for all techniques, and in particular we demonstratehow prompting of large language models can achieve high accuracy at very lowcost. Our results are accompanied by a code repository to make it easy forothers to duplicate our work and use it in their own research. Overall, ourarticle is intended to stimulate further uptake of these techniques in thesocial sciences.

Cheap Learning: Maximising Performance of Language Models for Social Data Science Using Minimal Data