skills.rest
LinusConradM
LinusConradMCOMMUNITY
Explore all skills by this author →
GitHub

text-analytics-expert

Identify gaps in CRPD keyword dictionaries and surface orphan topics across treaty document types.

Updated Mar 27, 2026
Search Tags:#nlp#topic modeling#corpus linguistics#text analytics#crpd dashboard#dictionary expansion#framing analysis
One-click install
npx skills add https://github.com/LinusConradM/test_crpd_dashboard --skill text-analytics-expert
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: text-analytics-expert
Source: https://github.com/LinusConradM/test_crpd_dashboard/tree/main/.claude/skills/text-analytics-expert
Command: npx skills add https://github.com/LinusConradM/test_crpd_dashboard --skill text-analytics-expert

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The CRPD data platform relies on keyword dictionaries to measure rights-based language across treaty documents, but gaps in coverage and semantic variation can cause missed signals and uneven framing analysis.

Core Features & Use Cases

  • Validate and expand article keyword dictionaries using corpus evidence, concordance, and semantic similarity analyses.
  • Identify orphan topics via BERTopic/LDA on the full chunk corpus and map them to missing dictionary entries to improve coverage.
  • Analyze framing and discourse to distinguish substantive vs boilerplate mentions and track language shifts over time across document types.

Quick Start

Analyze the CRPD document corpus using NLP methods to expand the keyword dictionary and identify emerging topics.

Frequently Asked Questions about text-analytics-expert

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

FAQPage Schema
How do I expand keyword dictionaries for text analytics using corpus evidence?▼

Expand keyword dictionaries by validating existing terms against corpus evidence, applying concordance and semantic similarity analyses to the full CRPD document corpus to identify semantic variation gaps and improve rights-based language coverage.

How does framing analysis distinguish substantive mentions from boilerplate text?▼

Framing analysis distinguishes substantive mentions by analyzing discourse patterns across document types, tracking language shifts over time to separate meaningful rights-based discussions from repetitive boilerplate text in the corpus.

What are the limitations of keyword-based measurement in corpus linguistics?▼

Keyword-based measurement in corpus linguistics carries inherent limitations, as gaps in coverage and semantic variation can cause missed signals, requiring validation steps and clear caveats about interpreting rights-based language shifts.

Can I use BERTopic and LDA to find orphan topics in a treaty document corpus?▼

Yes, you can apply BERTopic and LDA to the full CRPD chunk corpus to discover orphan topics not captured by existing articles, then map those topics to missing entries to validate and expand dictionary coverage.

How do I analyze framing patterns across different CRPD document types?▼

Analyze framing patterns by applying text analytics across CRPD doc_types including State Reports, LOI, Written Replies, Concluding Observations, and Responses to track language shifts and distinguish substantive discourse over time.

Related Skills

Explore More Data & Analytics Skills→
tondevreltondevrel
19

spacy-nltk

Tokenize, lemmatize, tag, and extract named entities from text with spaCy and NLTK.

Community
Advanced
sanky369sanky369
29

seo-strategy

Guide keyword research, content production, and link-building for 90-day SEO plans.

Community
Advanced
xjtulycxjtulyc
33

corpus-linguistics

Extract tokens, frequencies, collocations, keywords, and KWIC concordances from raw text.

Community
Advanced
Ritabrata-ChakrabortyRitabrata-Chakraborty

scikit-learn

Automate machine learning workflows with scikit-learn preprocessing, model selection, and evaluation.

Community
Advanced