@wentorai/research-plugins 1.0.0 → 1.2.0

package/skills/domains/humanities/digital-humanities-methods/SKILL.md

@@ -0,0 +1,232 @@
+---
+name: digital-humanities-methods
+description: "Computational methods for humanities research with text and network analysis"
+metadata:
+  openclaw:
+    emoji: "📜"
+    category: "domains"
+    subcategory: "humanities"
+    keywords: ["digital humanities", "text analysis", "corpus linguistics", "network analysis", "cultural analytics", "computational methods"]
+    source: "https://clawhub.ai/digital-humanities"
+---
+
+# Digital Humanities Methods
+
+## Overview
+
+Digital Humanities (DH) applies computational methods to humanistic inquiry — analyzing literary texts, historical records, cultural artifacts, and social networks at scale. This guide covers the core computational methods used in DH research: text analysis, topic modeling, network analysis, spatial analysis, and corpus linguistics. These methods complement rather than replace traditional close reading and archival research.
+
+## Text Analysis
+
+### Preprocessing Pipeline
+
+```python
+import re
+from collections import Counter
+
+def preprocess_text(text: str, language: str = "en") -> list:
+    """Standard preprocessing for humanities text analysis."""
+    # Lowercase
+    text = text.lower()
+
+    # Remove metadata markers (page numbers, headers)
+    text = re.sub(r'\[page \d+\]', '', text)
+    text = re.sub(r'\n{3,}', '\n\n', text)
+
+    # Tokenize (simple whitespace + punctuation split)
+    tokens = re.findall(r'\b[a-z]+\b', text)
+
+    # Remove stopwords (customize per corpus!)
+    # Standard lists often remove words meaningful in literary analysis
+    # e.g., "not", "but", "never" carry sentiment — keep them if relevant
+    stopwords = {"the", "a", "an", "is", "are", "was", "were", "in",
+                 "on", "at", "to", "for", "of", "with", "and", "or"}
+    tokens = [t for t in tokens if t not in stopwords and len(t) > 2]
+
+    return tokens
+
+# Word frequency analysis
+def word_frequencies(tokens: list, top_n: int = 50) -> list:
+    return Counter(tokens).most_common(top_n)
+```
+
+### Stylometry (Authorship Analysis)
+
+```python
+"""Stylometric features for authorship attribution."""
+
+def extract_style_features(text: str) -> dict:
+    """Extract stylistic features from a text."""
+    sentences = text.split('.')
+    words = text.split()
+    chars = list(text)
+
+    return {
+        "avg_sentence_length": len(words) / max(len(sentences), 1),
+        "avg_word_length": sum(len(w) for w in words) / max(len(words), 1),
+        "vocabulary_richness": len(set(words)) / max(len(words), 1),
+        "hapax_ratio": sum(1 for w, c in Counter(words).items() if c == 1) / max(len(set(words)), 1),
+        "comma_rate": text.count(',') / max(len(words), 1),
+        "semicolon_rate": text.count(';') / max(len(words), 1),
+        "question_rate": text.count('?') / max(len(sentences), 1),
+        "exclamation_rate": text.count('!') / max(len(sentences), 1),
+    }
+```
+
+### Sentiment Analysis for Historical Texts
+
+```python
+# Note: Modern NLP sentiment tools are trained on contemporary text.
+# For historical texts, consider:
+# 1. Historical sentiment lexicons (e.g., NRC Emotion Lexicon adapted)
+# 2. Period-specific word lists
+# 3. Manual validation on a sample before scaling
+
+from transformers import pipeline
+
+# Modern text sentiment (use with caution on historical texts)
+sentiment = pipeline("sentiment-analysis")
+result = sentiment("It was the best of times, it was the worst of times.")
+
+# Better: keyword-based approach with custom lexicons
+POSITIVE = {"virtue", "honor", "glory", "triumph", "beauty", "noble"}
+NEGATIVE = {"vice", "shame", "defeat", "ruin", "wretched", "base"}
+
+def lexicon_sentiment(tokens: list, pos: set, neg: set) -> float:
+    """Simple lexicon-based sentiment score."""
+    pos_count = sum(1 for t in tokens if t in pos)
+    neg_count = sum(1 for t in tokens if t in neg)
+    total = pos_count + neg_count
+    if total == 0:
+        return 0.0
+    return (pos_count - neg_count) / total
+```
+
+## Topic Modeling
+
+```python
+from sklearn.feature_extraction.text import CountVectorizer
+from sklearn.decomposition import LatentDirichletAllocation
+
+def run_topic_model(documents: list, n_topics: int = 10,
+                     n_top_words: int = 15):
+    """LDA topic modeling on a corpus of documents."""
+    # Vectorize
+    vectorizer = CountVectorizer(max_df=0.95, min_df=2,
+                                  max_features=5000,
+                                  stop_words="english")
+    dtm = vectorizer.fit_transform(documents)
+    feature_names = vectorizer.get_feature_names_out()
+
+    # Fit LDA
+    lda = LatentDirichletAllocation(n_components=n_topics,
+                                     random_state=42,
+                                     max_iter=50)
+    lda.fit(dtm)
+
+    # Display topics
+    topics = {}
+    for topic_idx, topic in enumerate(lda.components_):
+        top_words = [feature_names[i] for i in topic.argsort()[-n_top_words:]]
+        topics[f"Topic {topic_idx}"] = top_words
+        print(f"Topic {topic_idx}: {', '.join(top_words)}")
+
+    return lda, topics, dtm
+```
+
+## Network Analysis
+
+### Social Network from Letters/Correspondence
+
+```python
+import networkx as nx
+
+def build_correspondence_network(letters: list) -> nx.Graph:
+    """Build a social network from letter metadata.
+
+    Args:
+        letters: list of dicts with 'sender', 'recipient', 'date', 'location'
+    """
+    G = nx.Graph()
+
+    for letter in letters:
+        sender = letter["sender"]
+        recipient = letter["recipient"]
+
+        if G.has_edge(sender, recipient):
+            G[sender][recipient]["weight"] += 1
+        else:
+            G.add_edge(sender, recipient, weight=1)
+
+    # Compute centrality measures
+    centrality = nx.degree_centrality(G)
+    betweenness = nx.betweenness_centrality(G)
+
+    print(f"Network: {G.number_of_nodes()} individuals, "
+          f"{G.number_of_edges()} connections")
+    print(f"Most connected: {max(centrality, key=centrality.get)}")
+    print(f"Most bridging: {max(betweenness, key=betweenness.get)}")
+
+    return G
+```
+
+## Spatial Analysis (GIS for Humanities)
+
+Common applications:
+- Mapping historical events or migration patterns
+- Georeferencing historical maps
+- Spatial analysis of literary settings
+
+```python
+import folium
+
+def create_historical_map(events: list, title: str = "Historical Events"):
+    """Create an interactive map of historical events.
+
+    Args:
+        events: list of dicts with 'name', 'lat', 'lon', 'date', 'description'
+    """
+    center_lat = sum(e["lat"] for e in events) / len(events)
+    center_lon = sum(e["lon"] for e in events) / len(events)
+
+    m = folium.Map(location=[center_lat, center_lon], zoom_start=5)
+
+    for event in events:
+        popup = f"<b>{event['name']}</b><br>{event['date']}<br>{event['description']}"
+        folium.Marker(
+            location=[event["lat"], event["lon"]],
+            popup=popup,
+            tooltip=event["name"]
+        ).add_to(m)
+
+    m.save(f"{title.replace(' ', '_').lower()}.html")
+    return m
+```
+
+## Key Data Sources for DH
+
+| Source | Content | Access |
+|--------|---------|--------|
+| **Project Gutenberg** | 70,000+ free ebooks | gutenberg.org |
+| **HathiTrust** | 17M+ digitized volumes | hathitrust.org |
+| **Internet Archive** | Books, media, web archives | archive.org |
+| **EEBO / ECCO** | Early English books (1475-1800) | Institutional |
+| **Perseus Digital Library** | Greek and Latin classics | perseus.tufts.edu |
+| **Europeana** | European cultural heritage | europeana.eu |
+| **DPLA** | US digital public library | dp.la |
+| **Old Bailey Online** | London criminal trials (1674-1913) | oldbaileyonline.org |
+
+## Methodological Considerations
+
+1. **Close reading still matters**: Computational methods reveal patterns; interpretation requires humanistic expertise
+2. **Corpus bias**: Digitized collections over-represent certain periods, languages, and genres
+3. **OCR quality**: Historical texts often have high OCR error rates — validate before analysis
+4. **Anachronism**: Modern NLP tools may misinterpret historical language use
+5. **Interdisciplinary collaboration**: Best DH work pairs domain expertise with technical skills
+
+## References
+
+- Moretti, F. (2013). *Distant Reading*. Verso.
+- Jockers, M. L. (2013). *Macroanalysis: Digital Methods and Literary History*. University of Illinois Press.
+- [Programming Historian](https://programminghistorian.org/) — Free tutorials for DH methods
+- [DH Tools Directory](https://dirtdirectory.org/)

package/skills/domains/humanities/ethical-philosophy-guide/SKILL.md

@@ -0,0 +1,244 @@
+---
+name: ethical-philosophy-guide
+description: "Applied ethics research methods and major ethical frameworks"
+metadata:
+  openclaw:
+    emoji: "⚖️"
+    category: "domains"
+    subcategory: "humanities"
+    keywords: ["ethics", "applied ethics", "moral philosophy", "bioethics", "AI ethics", "normative theory"]
+    source: "https://plato.stanford.edu/entries/ethics-applied/"
+---
+
+# Applied Ethics Research Guide
+
+## Overview
+
+Applied ethics is the branch of philosophy that addresses concrete moral questions in specific domains: medicine, technology, business, environment, law, and research itself. Unlike metaethics (which asks what moral terms mean) or normative ethics (which develops general moral theories), applied ethics works at the intersection of philosophical reasoning and real-world decision-making.
+
+The field has exploded in relevance as emerging technologies -- artificial intelligence, gene editing, autonomous weapons, surveillance systems -- create moral dilemmas that existing law and policy cannot resolve. Applied ethics research requires both philosophical rigor (clear argument structure, engagement with existing frameworks) and empirical grounding (understanding the technology, institution, or practice being evaluated).
+
+This guide covers the major ethical frameworks used in applied ethics, methods for constructing and evaluating ethical arguments, the landscape of subfields (bioethics, AI ethics, research ethics, environmental ethics), and practical guidance for publishing in philosophy and interdisciplinary venues.
+
+## Major Ethical Frameworks
+
+### Framework Comparison
+
+| Framework | Core Principle | Decision Procedure | Strengths | Weaknesses |
+|-----------|---------------|-------------------|-----------|------------|
+| Utilitarianism | Maximize aggregate well-being | Calculate consequences | Clear, impartial | Ignores rights, demandingness |
+| Kantianism | Respect rational autonomy | Apply categorical imperative | Rights-based, universalizable | Rigid, conflicting duties |
+| Virtue ethics | Cultivate excellent character | Ask "what would a virtuous person do?" | Context-sensitive, holistic | Vague, culturally relative |
+| Care ethics | Attend to relationships | Prioritize care for vulnerable | Relational, concrete | Limited scope, partiality |
+| Contractualism | Principles no one could reasonably reject | Seek overlapping consensus | Fair, procedural | Excludes non-agents |
+| Rights-based | Protect fundamental entitlements | Identify and enforce rights | Strong protections | Rights conflicts, indeterminacy |
+
+### Applying Frameworks to a Case
+
+```
+Framework application template:
+
+CASE: A hospital must allocate a scarce drug among three patients.
+
+UTILITARIAN ANALYSIS:
+- Calculate expected QALYs (quality-adjusted life years) for each patient
+- Allocate to the patient who gains the most QALYs
+- Consider: indirect effects on family, society, precedent
+- Verdict: Maximize aggregate health outcomes
+
+KANTIAN ANALYSIS:
+- Can the allocation principle be universalized?
+- Does the procedure respect each patient's dignity?
+- Are patients treated as ends in themselves, never merely as means?
+- Verdict: Fair lottery or first-come-first-served (equal respect)
+
+VIRTUE ETHICS ANALYSIS:
+- What would a compassionate, just, courageous physician do?
+- Does the decision reflect practical wisdom (phronesis)?
+- How does this decision shape the character of the institution?
+- Verdict: Context-dependent judgment by virtuous practitioner
+
+CARE ETHICS ANALYSIS:
+- What are the relationships and dependencies involved?
+- Who is most vulnerable?
+- How can we maintain trust and care in the allocation process?
+- Verdict: Attend to the most vulnerable, preserve relationships
+```
+
+## Constructing Ethical Arguments
+
+### Argument Structure in Applied Ethics
+
+```
+Standard philosophical argument form:
+
+THESIS: Autonomous weapons should be banned under international law.
+
+ARGUMENT:
+P1: Weapons that cannot reliably distinguish combatants from civilians
+    violate International Humanitarian Law (IHL).
+P2: Current autonomous weapons systems cannot reliably make this
+    distinction in complex combat environments.
+P3: There is no clear technological pathway to solving the distinction
+    problem within a meaningful timeframe.
+C1: Therefore, autonomous weapons violate IHL. (from P1, P2)
+C2: Therefore, they should be banned until the distinction problem
+    is solved. (from C1, P3, plus the precautionary principle)
+
+OBJECTION 1: AI targeting may be MORE accurate than human soldiers.
+RESPONSE: Accuracy in controlled tests does not equal reliability
+in unpredictable combat environments. Moreover, IHL requires not
+just accuracy but accountability -- someone must be responsible
+for each targeting decision.
+
+OBJECTION 2: A ban would disadvantage compliant nations.
+RESPONSE: This is an argument for multilateral treaties, not
+against the ban itself. The same logic applies to chemical weapons.
+```
+
+### The Method of Reflective Equilibrium
+
+```
+Rawls's reflective equilibrium (standard method in applied ethics):
+
+1. Start with CONSIDERED JUDGMENTS
+   - Strong moral intuitions about specific cases
+   - Example: "Torturing children for fun is wrong"
+
+2. Formulate MORAL PRINCIPLES
+   - Abstract rules that explain and organize judgments
+   - Example: "It is wrong to cause suffering without justification"
+
+3. Check for COHERENCE
+   - Do principles match judgments?
+   - Do principles conflict with each other?
+
+4. ADJUST until equilibrium
+   - Revise judgments that conflict with well-supported principles
+   - Revise principles that conflict with firm judgments
+   - Iterate until coherent
+
+5. Result: A REFLECTIVE EQUILIBRIUM
+   - Mutually supporting set of principles and judgments
+   - Not infallible, but rationally justified
+```
+
+## Major Subfields
+
+### Bioethics
+
+| Topic | Key Question | Key Framework |
+|-------|-------------|---------------|
+| Informed consent | When is consent valid? | Autonomy (Beauchamp & Childress) |
+| End-of-life care | When may treatment be withdrawn? | Sanctity of life vs. quality of life |
+| Genetic enhancement | Is it permissible to enhance embryos? | Therapy/enhancement distinction |
+| Organ allocation | How to distribute scarce organs fairly? | Justice (utilitarian vs. egalitarian) |
+| Research ethics | What protections do subjects need? | Belmont principles |
+| Reproductive ethics | Autonomy over reproductive decisions? | Rights-based, feminist ethics |
+
+### AI Ethics
+
+```
+Key areas of AI ethics research:
+
+1. FAIRNESS AND BIAS
+   - Algorithmic discrimination (hiring, lending, criminal justice)
+   - Definitions of fairness (demographic parity, equalized odds, calibration)
+   - Impossibility results: some fairness criteria are mutually incompatible
+
+2. TRANSPARENCY AND EXPLAINABILITY
+   - Right to explanation (GDPR Article 22)
+   - Interpretable vs. post-hoc explanation
+   - Epistemic opacity of deep learning
+
+3. ACCOUNTABILITY AND RESPONSIBILITY
+   - Responsibility gap: who is liable when AI causes harm?
+   - Distributed responsibility across developers, deployers, users
+   - Meaningful human control over automated decisions
+
+4. PRIVACY AND SURVEILLANCE
+   - Data collection and consent
+   - Facial recognition and civil liberties
+   - Differential privacy and data protection
+
+5. EXISTENTIAL AND LONG-TERM RISK
+   - Alignment problem: ensuring AI pursues intended goals
+   - Concentration of power
+   - Autonomous weapons and escalation risks
+```
+
+### Research Ethics
+
+```
+The Belmont Principles (1979):
+
+1. RESPECT FOR PERSONS
+   - Individuals are autonomous agents
+   - Persons with diminished autonomy deserve protection
+   - Application: Informed consent procedures
+
+2. BENEFICENCE
+   - Do no harm (non-maleficence)
+   - Maximize benefits, minimize risks
+   - Application: Risk-benefit assessment
+
+3. JUSTICE
+   - Fair distribution of research burdens and benefits
+   - No exploitation of vulnerable populations
+   - Application: Equitable subject selection
+
+Modern additions:
+- Community engagement and benefit sharing
+- Data sovereignty (especially for Indigenous communities)
+- Dual-use research oversight
+```
+
+## Writing Ethics Papers
+
+```
+Applied ethics paper structure:
+
+1. INTRODUCTION (1-2 pages)
+   - Motivating case or real-world problem
+   - Thesis statement (clear normative claim)
+   - Roadmap of the argument
+
+2. BACKGROUND (2-3 pages)
+   - Empirical context (what is the technology/practice?)
+   - Existing policy and legal landscape
+   - Previous philosophical literature
+
+3. ARGUMENT (5-10 pages)
+   - Present the main argument step by step
+   - Each premise defended with evidence or reasoning
+   - Consider and respond to objections (minimum 2-3)
+   - Distinguish your position from nearby views
+
+4. IMPLICATIONS (2-3 pages)
+   - Policy recommendations
+   - Institutional design proposals
+   - Limitations and open questions
+
+5. CONCLUSION (1 page)
+   - Restate thesis and main contribution
+   - Acknowledge what remains unresolved
+
+Style: Clear, jargon-minimal prose. Philosophy values precision over complexity.
+```
+
+## Best Practices
+
+- **Engage with the strongest version of opposing views.** Straw man arguments are immediately detected by reviewers.
+- **Ground abstract arguments in concrete cases.** Applied ethics must be applied.
+- **Collaborate with domain experts.** Ethics of AI requires understanding AI; ethics of medicine requires understanding clinical practice.
+- **Distinguish empirical from normative claims.** "X is the case" versus "X ought to be the case."
+- **Check the Stanford Encyclopedia of Philosophy (SEP)** for authoritative surveys of any topic before writing.
+- **Be explicit about your framework.** State which ethical tradition you are working within and why.
+
+## References
+
+- [Stanford Encyclopedia of Philosophy](https://plato.stanford.edu/) -- Peer-reviewed reference for all areas of philosophy
+- Beauchamp, T. L. & Childress, J. F. (2019). Principles of Biomedical Ethics, 8th ed. Oxford UP.
+- Floridi, L. & Cowls, J. (2019). A Unified Framework of Five Principles for AI in Society. Harvard Data Science Review.
+- Singer, P. (2011). Practical Ethics, 3rd ed. Cambridge UP.
+- [PhilPapers](https://philpapers.org/) -- Comprehensive index of philosophy research