R packages and research software
This page lists R packages and reproducible research tools developed for eye-tracking, behavioural data analysis, and transparent research workflows.
Call for Papers – MDPI Information Special Issue on HCI in Marketing | Guest Editor: S. Balaskas | Deadline: 30 Apr 2026
This page lists R packages and reproducible research tools developed for eye-tracking, behavioural data analysis, and transparent research workflows.
gp3tools is an R package for importing, validating, analysing, modelling, and reporting Gazepoint GP3 and Gazepoint Analysis eye-tracking exports. It supports folder-level workflows, master-table validation, pupil preprocessing and audits, AOI summaries, fixation and transition workflows, model preparation, reporting checklists, and statistical-extension plots. CRAN: Package gp3tools
Research Paper: Balaskas, S. gp3tools: An R Package for Reproducible Analysis and Reporting of Gazepoint GP3 Eye-Tracking Exports. J. Eye Mov. Res. 2026, 19, 76. https://doi.org/10.3390/jemr19040076
gpbiometrics provides reproducible tools for importing, checking, preprocessing, summarising, modelling, and reporting Gazepoint Biometrics and Gazepoint GP3 biometric exports. It is designed for researchers working with electrodermal activity, pulse/heart-rate channels, interbeat intervals, TTL markers, stimulus/event timing, and multimodal Gazepoint workflows.
gp3ml is a governance-first R package for leakage-resistant and group-aware predictive modelling and validation using Gazepoint-derived research data. The package is designed for explicitly observed, non-sensitive outcomes and declared scientific purposes. It is not a generic automatic machine- learning wrapper and does not perform autonomous model selection.
gp3sequences is an independent R package for transparent, reproducible, and auditable analysis of ordered categorical sequences. It is designed for ordinary long-format data frames and is not restricted to Gazepoint exports, eye-tracking data, particular hardware, or proprietary software.