Keyword Extraction Explorer Tool

The Keyword Extraction Explorer Tool is an interactive web application designed to help users explore and compare different keyword extraction models without requiring coding experience.The tool provides a user-friendly interface for extracting and visualising the most important words and phrases from text using four different Natural Language Processing (NLP) models: YAKE (Yet Another Keyword Extractor)TF-IDF with Cosine SimilarityRAKE-NLTK (Rapid Automatic Keyword Extraction)TextRank.Users can input text (optimal length: 50-1000 words), select an extraction model, adjust parameters such as the number of keywords and n-gram range, and receive colour-coded results showing keyword relevance.The tool provides three types of output:A statistical summaryHighlighted text with keywords marked by relevance level (high/medium/low)A detailed ranked table of extracted keywords with scoresThis educational resource is aimed primarily at researchers, students, digital humanists, and professionals in the Galleries, Libraries, Archives, and Museums (GLAM) sector, who wish to understand and experiment with keyword extraction methods.Built with Gradio, scikit-learn, YAKE, RAKE-NLTK, NetworkX, and NLTK, the tool runs entirely in a web browser and is deployed as a Hugging Face Space.The tool was created as a result of a Digital Scholarship at Oxford (DiSc) funded research project "Extracting Keywords from Crowdsourced Collections" (Nov 2024-July 2025).Acknowledgment: The code to build this tool was developed with the assistance of Claude Opus 4 (Anthropic). Access: https://huggingface.co/spaces/SorrelC/KeywordExtraction-Explorer-Tool