Descriptive Section Clarity

Descriptive Section Clarity is a metric that evaluates the readability and linguistic simplicity of explanatory text.

LLMs and other AI systems parse text more effectively when it is written in clear, direct, and unambiguous language. This metric uses established linguistic formulas and computational analysis to score content on factors like sentence complexity, word choice, and use of active voice. High-clarity content minimizes the risk of misinterpretation by AI models, ensuring that the intended meaning is accurately captured and synthesized.

Calculation Methodology

This metric combines several standard readability scores with structural analysis.

Standard Readability Metrics (60% weight)

Extract the clean text from the main content sections of the page. Using a linguistic analysis library (e.g., textstat in Python), calculate a suite of standard readability scores. Key scores include:

• Flesch Reading Ease: Scores text on a 100-point scale; higher scores indicate easier readability. A score of 60-70 is considered acceptable for a general audience.
• Gunning Fog Index: Estimates the years of formal education a person needs to understand the text on the first reading.
• SMOG Index: Another grade-level readability test.

Normalize and average these scores to produce a single readability value.

Structural Simplicity (20% weight)

• Average Sentence Length: Calculate the average number of words per sentence. Shorter sentences are generally easier to parse.
• Average Paragraph Length: Calculate the average number of sentences per paragraph. Shorter paragraphs focused on a single idea improve clarity.

Scores are assigned based on deviation from ideal ranges (e.g., 15-20 words per sentence).

Voice and Diction (20% weight)

• Active Voice Percentage: Programmatically determine the percentage of sentences written in the active voice versus the passive voice. Active voice is more direct and less ambiguous.
• Jargon Density: Use an LLM to identify and count the number of industry-specific jargon terms. A high density can negatively impact clarity for a general audience.

Calculating The Descriptive Section Clarity Score

The calculation of the Descriptive Section Clarity Score is a multi-step process that involves analyzing the HTML structure of the page. Here is a simplified pseudo-code representation of how this score is calculated.

BEGIN
 FETCH and EXTRACT clean text from the webpage.

 // Calculate Readability Metrics
 COMPUTE standard scores like Flesch Reading Ease and Gunning Fog Index.
 NORMALIZE and AVERAGE to get a readability_score.

 // Calculate Structural Simplicity
 CALCULATE average sentence length and average paragraph length.
 COMPUTE structural_score based on deviation from ideal ranges.

 // Calculate Voice and Diction
 DETERMINE percentage of sentences in active vs. passive voice.
 USE LLM to identify and count jargon.
 COMPUTE voice_diction_score.

 CALCULATE final_score as the weighted average of the three components.
 RETURN final_score.
END

Conclusion

Descriptive Section Clarity is a key component of GEO that focuses on the quality of your writing. By writing clear, concise, and easy-to-understand content, you can improve your chances of being understood and ranked by AI systems, as well as provide a better experience for your human readers.