text-mining-science

Extract topics, entities, claims, and trends from scientific literature corpora.

33|6|Updated Mar 17, 2026

Search Tags:#topic modeling #text mining #tf-idf #trend detection #claim extraction #scientific ner #research literature

Ready to run

npx skills add https://github.com/xjtulyc/awesome-rosetta-skills --skill text-mining-science

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: text-mining-science
Source: https://github.com/xjtulyc/awesome-rosetta-skills/tree/main/skills/22-interdisciplinary/text-mining-science
Command: npx skills add https://github.com/xjtulyc/awesome-rosetta-skills --skill text-mining-science

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you extract actionable knowledge from scientific literature by identifying topics, scientific entities, claims, and emerging trends within research text corpora.

Core Features & Use Cases

Topic modeling for scientific corpora: Use LDA or NMF to discover latent themes in abstracts or full-text.
Scientific information extraction: Extract named entities such as methods, metrics, datasets, genes/chemicals/diseases (via configurable pattern logic) and pull claim-like sentences from paper text.
Trend and keyword analysis: Combine TF-IDF, RAKE-inspired phrase scoring, and temporal comparisons to detect research fronts across years.
Similarity and recommendation foundations: Build document-topic representations and keyword vectors that can support literature search and recommendation.

Quick Start

Use the text-mining-science skill on a set of scientific abstracts to produce topic clusters, top keywords, and a timeline of emerging terms.

Frequently Asked Questions about text-mining-science

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I extract topics and scientific entities from research literature text corpora?▼

Topic modeling and scientific entity extraction from research literature text corpora is done using classical NLP pipelines. Apply LDA or NMF to discover latent themes, and use regex-based scientific NER to pull out methods, metrics, datasets, genes, chemicals, and diseases.

What is the best way to detect emerging research trends across time windows in scientific abstracts?▼

Trend detection across time windows in scientific abstracts is performed by combining TF-IDF, RAKE-inspired phrase scoring, and temporal comparisons. This approach identifies research fronts by comparing term frequency changes across different years in the literature.

Can I extract claim-like sentences and keywords from full-text research papers without deep learning models?▼

Claim-like sentences and keywords can be extracted from full-text research papers using classical NLP pipelines rather than deep learning models. TF-IDF vectorization, RAKE-inspired phrase scoring, and pattern-based claim extraction pull structured insights directly from the text.

Does topic modeling for scientific corpora require Python tooling like scikit-learn and NLTK?▼

Topic modeling for scientific corpora requires Python tooling such as scikit-learn for vectorization and matrix decompositions. NLTK is optional and used specifically for text preprocessing tasks like tokenization before applying LDA or NMF algorithms.

What limitations exist when using regex-based scientific NER for extracting methods, datasets, and metrics?▼

Regex-based scientific NER for extracting methods, datasets, and metrics relies on configurable pattern logic rather than contextual understanding. This means it may miss entities not matching predefined patterns and requires manual pattern tuning for different scientific domains.

How do I build document-topic representations for literature search and recommendation?▼

Document-topic representations for literature search and recommendation are built by applying LDA or NMF topic modeling to the text corpus. The resulting topic distributions and keyword vectors serve as foundational features to support similarity calculations and recommendation workflows.