Critical Analysis Skill (Is-It-Ture)

A comprehensive framework for systematic dialectical examination of viewpoints, factual statements, or web content, based on the critical thinking methodology of "Asking the Right Questions" by Browne and Keeley.

Core Analysis Process

Step 1: Determine Analysis Type

Classify the input into one of the following types:

Step 2: Factual Statement Verification Framework

For each factual statement, systematically verify the following dimensions:

2.1 Source Tracing

• Original Source: Where did this data/conclusion originate?
• Authority: Does the source have professional credentials (academic journals, government agencies, renowned research institutions)?
• Timeliness: Is the information outdated? Are there more recent studies or data?

2.2 Multi-Source Cross-Validation (Mandatory Step)

Multi-source cross-validation must be performed for ALL types of input (factual statements, opinion-based statements, web content):

2.2.1 Verification Strategies

2.2.2 Source Reliability Ratings

2.2.3 Information Source Type Identification

2.2.4 Cross-Validation Checklist

• Was the original source found? What is the original source?
• Are there 3+ independent reliable sources supporting this information?
• Are there any reliable sources that contradict this?
• Has this information been denied or corrected by authoritative institutions?
• Does the information come from known misinformation sources?
• Is there any out-of-context or selective quoting?
• Have the data/statistics been deliberately distorted (scale, base, comparison method)?

2.2.5 Information Tracing Path

Original Input
    ↓
Is a specific source mentioned? (research/report/institution/person)
    ├─ Yes → Trace that source → Verify source reliability → Find original data
    └─ No → Multi-keyword search → Attempt to find reliable sources
              ↓
        Reliable source found?
            ├─ Yes → Compare original statement with original information
            └─ No → Mark as "source unknown" → Lower credibility rating

2.3 Scientific Principle Verification

• Consistency with Known Scientific Principles: Does the statement align with established scientific theories?
• Mechanism Explanation: Can it explain the underlying causal mechanism?
• Boundary Conditions: What are the applicable conditions and scope of this conclusion?

2.4 Evidence Quality Assessment

• Direct Evidence: Is there direct experimental data, statistical data, or research results supporting it?
• Indirect Evidence: Is the inference chain rigorous?
• Sample Quality: Is the research sample representative? Is the sample size sufficient?
• Research Design: Is the research methodology scientific? Are there design flaws?

2.5 Logical Consistency

• Internal Consistency: Are there internal contradictions within the statement?
• External Consistency: Does it align with other reliable evidence?
• Causation vs. Correlation: Has causation been confused with correlation?

Step 3: Opinion-Based Statement Analysis Framework

Deconstruct opinion-based statements into their components for systematic analysis, while performing multi-source cross-validation on any factual content involved:

3.1 Thesis Identification

• Core Question: What question is the author trying to answer?
• Thesis Type: Descriptive (what is) or Prescriptive (what should be)?

3.2 Conclusion Extraction

• Main Conclusion: What is the author's core claim?
• Sub-conclusions: What specific points support the main conclusion?
• Conclusion Priority: Which are main points and which are supporting arguments?

3.3 Argument Structure Analysis

Argument = Conclusion + Reasons + Evidence + Hidden Assumptions

• Reasons: What reasons does the author use to support the conclusion?
• Evidence Types:
  • Personal experience/cases
  • Unofficial expert opinions
  • Eyewitness testimony
  • Typical cases
  • Quoted authorities/experts
  • Personal observation
  • Research results/statistical data
  • Analogies
  • Presumed premises
• Evidence Quality: How strong a conclusion can this type of evidence support?

3.4 Assumption Identification

Explicit Assumptions (clearly stated by the author):

• What are the author's preconditions?

Implicit Assumptions (unstated but necessary):

• Value Assumption: What does the author consider more important? (efficiency vs. fairness, individual vs. collective, etc.)
• Descriptive Assumption: What does the author believe about how the world works?

Questions for Examining Assumptions:

• Is this assumption true/correct?
• If the assumption is false, does the conclusion still hold?
• Does this assumption conflict with reader or societal consensus?

3.5 Position Analysis

• Author's Position: From what standpoint is the author speaking?
• Beneficiary: Who benefits from this viewpoint?
• Conflict of Interest: Is there obvious interest-driven motivation?
• Reader's Position: Is the reader automatically placed in a certain position?

Step 4: Common Fallacy Identification

Examine arguments in opinion-based statements for logical fallacies:

Step 5: Web/Article Content Processing

For web content, additionally perform the following steps:

5.1 Source Reliability Assessment

• Website Reputation: What is the nature of the website? (government/academic/commercial/personal blog)
• Author Information: Is author information provided? What is the author's professional background?
• Citations: Are reliable sources cited?
• Update Date: Is the information current?

5.2 Content Structure Analysis

• Fact vs. Opinion Separation: Distinguish between objective facts and subjective opinions
• Contextual Completeness: Is it taken out of context? Is important background missing?
• Presentation Method: Is the data presentation misleading (truncated scales, sample selection, etc.)?

5.3 Source Cross-Validation (Web-Specific)

Web content cross-validation requires special attention to:

Step 6: Comprehensive Assessment

Based on the above analysis, provide a structured assessment conclusion:

Assessment Standards

Assessment Report Structure

## Comprehensive Assessment Report

### Verdict
[Credibility rating and brief conclusion]

### Key Findings
1. [Primary finding 1]
2. [Primary finding 2]
3. [Primary finding 3]

### Multi-Source Cross-Validation Results
- Original Source Rating: [A+/A/B+/B/C/D]
- Cross-Validation Source Count: [X independent reliable sources]
- Verification Results:
  - Supported by: [X sources]
  - Contradicted by: [X sources]
  - No reliable source found: [description]
- Information Type Identification: [Misinformation/Marketing Copy/Unverifiable Private Information/Misleading Information/Outdated Information/Normal]

### Evidence Assessment
- Evidence Source: [description]
- Evidence Quality: [assessment]
- Evidence Gap: [existing deficiencies]

### Argumentation Quality
- Logical Structure: [assessment]
- Assumption Reasonableness: [assessment]
- Potential Fallacies: [identified issues]

### Position and Interest Analysis
- Author's Position: [identified]
- Potential Bias: [identified]
- Reader Impact: [analysis]

### Reasoning Process Supporting Conclusion
[detailed reasoning chain]

### Usage Recommendations
[How to use this information, any precautions]

Usage Examples

Example 1: Factual Statement Verification

Input: "A study shows that drinking coffee every day can extend lifespan."

Analysis Output:

### Analysis Type: Factual Statement

### Source Tracing
- Research Source: [tracing results]
- Authority: [assessment]
- Sample Size and Research Design: [analysis]

### Scientific Principle Verification
- Mechanism Explanation: [whether it exists]
- Causation vs. Correlation: [distinction result]

### Evidence Assessment
- Direct Evidence: [assessment]
- Confounding Variables: [whether considered]
- Reproducibility: [whether other research supports/contradicts]

### Comprehensive Assessment
[verdict and reasoning]

Example 2: Opinion-Based Statement Verification

Input: "We should completely ban artificial intelligence because it will replace human jobs."

Analysis Output:

### Analysis Type: Opinion-based Statement

### Thesis Identification
- Core Question: Should AI be banned?
- Thesis Type: Prescriptive

### Conclusion Extraction
- Main Conclusion: AI should be completely banned
- Implicit Premise: The harm of AI replacing jobs outweighs its benefits

### Argumentation Structure
- Reason: AI will replace human jobs
- Evidence: [missing argumentation]
- Assumptions: Work is the main value of life; banning AI won't cause other problems

### Fallacy Identification
- Slippery Slope: Assuming replacement will lead to complete replacement
- False Dilemma: Ignoring the possibility of "regulated development"
- Hasty Generalization: Using partial replacement cases to generalize the whole

### Comprehensive Assessment
[verdict]

Important Notes

1. Maintain Objectivity: Do not take sides during analysis; let evidence speak
2. Distinguish Certainty from Speculation: Clearly mark what is certain vs. what is speculation
3. Acknowledge Uncertainty: Be transparent about problems that cannot be determined rather than forcing conclusions
4. Focus on Evidence Quality: Not all evidence has equal value
5. Recognize Timeliness: Information may change over time; dynamic evaluation is needed
6. Multi-perspective Examination: Multiple reasonable perspectives may exist for the same issue
7. Prioritize Multi-Source Validation: For all input, multi-source cross-validation MUST be performed first; do not rely solely on a single source
8. Be Vigilant Against Source-less Information: For information that cannot be traced to reliable sources, credibility ratings must be lowered

Output Standards

The final output MUST contain ALL of the following sections:

1. Analysis Type Determination: Clearly state whether it is factual or opinion-based
2. Multi-Source Cross-Validation (Mandatory):
   • Original source rating
   • Cross-validation results (supported/contradicted/not found)
   • Information type identification
3. Systematic Verification: Analyze item by item according to the above framework
4. Verdict: Clear credibility rating (⭐-⭐⭐⭐⭐⭐)
5. Reasoning Process: Complete reasoning chain supporting the conclusion
6. Usage Recommendations: How to correctly use this information

Credibility Downgrade Triggers

The following situations MUST trigger credibility rating downgrade: