TiAb Review Plugin: A Browser-Based Tool for AI-Assisted Title and Abstract Screening

2026-04-08

AI Summary

This study addresses the lack of accessible, no-code, serverless tools for title and abstract screening in academic literature review. The authors propose the first browser-based, serverless, and code-free AI-assisted screening system, implemented as an open-source Chrome extension. The system leverages Google Sheets as a shared database to enable multi-user collaboration and stores users’ Gemini API keys locally in encrypted form to ensure privacy. It fully ports ASReview’s active learning pipeline to TypeScript, integrating both large language models (LLMs) and traditional machine learning classifiers (TF-IDF and Naive Bayes). Experiments demonstrate that the TypeScript implementation achieves 100% consistency with the original ASReview across six datasets, while the LLM-based screening attains recall rates of 94–100% and WSS@95 scores of 48.7–87.3% on five public datasets, confirming its efficacy and practicality.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Humans and AI: Crowd Sourcing and Human Computation

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Background: Server-based screening tools impose subscription costs, while open-source alternatives require coding skills. Objectives: We developed a browser extension that provides no-code, serverless artificial intelligence (AI)-assisted title and abstract screening and examined its functionality. Methods: TiAb Review Plugin is an open-source Chrome browser extension (available at https://chromewebstore.google.com/detail/tiab-review-plugin/alejlnlfflogpnabpbplmnojgoeeabij). It uses Google Sheets as a shared database, requiring no dedicated server and enabling multi-reviewer collaboration. Users supply their own Gemini API key, stored locally and encrypted. The tool offers three screening modes: manual review, large language model (LLM) batch screening, and machine learning (ML) active learning. For ML evaluation, we re-implemented the default ASReview active learning algorithm (TF-IDF with Naive Bayes) in TypeScript to enable in-browser execution, and verified equivalence against the original Python implementation using 10-fold cross-validation on six datasets. For LLM evaluation, we compared 16 parameter configurations across two model families on a benchmark dataset, then validated the optimal configuration (Gemini 3.0 Flash, low thinking budget, TopP=0.95) with a sensitivity-oriented prompt on five public datasets (1,038 to 5,628 records, 0.5 to 2.0 percent prevalence). Results: The TypeScript classifier produced top-100 rankings 100 percent identical to the original ASReview across all six datasets. For LLM screening, recall was 94 to 100 percent with precision of 2 to 15 percent, and Work Saved over Sampling at 95 percent recall (WSS@95) ranged from 48.7 to 87.3 percent. Conclusions: We developed a functional browser extension that integrates LLM screening and ML active learning into a no-code, serverless environment, ready for practical use in systematic review screening.

Problem

• title and abstract screening
• systematic review
• AI-assisted screening
• no-code tool
• serverless tool

Innovation

• browser-based AI
• serverless screening
• active learning in-browser
• LLM-assisted systematic review
• no-code tool