Yes-Yes-Yes: Proactive Data Collection for ACL Rolling Review and Beyond

TL;DR

This paper introduces 'Yes-Yes-Yes', a donation-based data collection workflow for peer review in NLP, addressing data scarcity in under-resourced domains while considering ethical and legal aspects, and studies its impact on dataset size and bias.

Contribution

It presents the first systematic, ethically compliant proactive data collection method for peer review, specifically tailored for the ACL Rolling Review platform.

Findings

Increased dataset size through proactive collection.

Identification of biases from donation behavior.

Ethical and legal framework for data collection.

Abstract

The shift towards publicly available text sources has enabled language processing at unprecedented scale, yet leaves under-serviced the domains where public and openly licensed data is scarce. Proactively collecting text data for research is a viable strategy to address this scarcity, but lacks systematic methodology taking into account the many ethical, legal and confidentiality-related aspects of data collection. Our work presents a case study on proactive data collection in peer review -- a challenging and under-resourced NLP domain. We outline ethical and legal desiderata for proactive data collection and introduce "Yes-Yes-Yes", the first donation-based peer reviewing data collection workflow that meets these requirements. We report on the implementation of Yes-Yes-Yes at ACL Rolling Review and empirically study the implications of proactive data collection for the dataset size and the biases induced by the donation behavior on the peer reviewing platform.