Narrative-Contextual Estimation Protocol (NCEP) and NCEPtion

Teaching AI to Read Between the Lines

by J. Oliver Glasgow

Goals:

1. This paper will teach you how to use advanced graph AI in a way that perhaps it wasn’t originally intended, but for which it is absolutely well-suited — namely to be your Big Data group and provide what were previously expensive insights for free (or close to it) thus democratizing large data analytics. Think of this a building a framework like a factory builds an assembly line. The framework, itself, is not your product, but rather a repeatable approach that can be used to build any product. This paper lays out how to build this framework to create whatever insight you may desire.
2. To demonstrate the feasibility of this framework, this paper will then create a sample product to prove this framework actually works. But you will find that this product is far more valuable than a mere “widget.” This example is a revolutionary metric that produces insights that may improve or even overhaul our approach to learning/teaching history for all disciplines and the related theses, research, conclusions, and ultimately publications for higher learning. This new metric is called the Truth-Acceptance Scale (TAS), and it measures a society’s prevalent leanings on valuing willful ignorance on one side of the scale (zero) to seeking truth at all costs on the other side (ten). If we understand the TAS for a given period of time, it will help us more accurately evaluate the documented learnings from that time, and may even change long-held beliefs in their conclusions.

Introduction

In the evolving landscape of data interpretation and analysis, a novel approach has emerged, blending the capabilities of modern artificial intelligence with the intuitive nature of human narrative. This approach, known as the Narrative-Contextual Estimation Protocol (NCEP), and its application process, NCEPtion, represents a significant leap in utilizing AI for efficient and cost-effective decision-making insights.

Historically, comprehensive analysis projects have relied heavily on data scientists. These projects typically involve extensive data gathering, normalization, and application of multifaceted machine learning models. The objective has always been to extract clear, actionable insights from complex data sets, aiding human decision-makers in navigating binary or multifaceted choices. However, this traditional approach often demands considerable time, resources, and financial investment.

The implementation of NCEPtion deviates from this norm by harnessing the power of conversational AI, specifically advanced graph AI systems, to interpret and analyze data through a narrative-driven framework. This method expands on Narrative-Driven Data Interpretation (NDDI) by translating complex analytical tasks into a series of structured, human-readable narratives that AI can process, thereby generating insights akin to those derived from traditional, more resource-intensive methods.

The essence of NCEPtion, the act of implementing the NCEP protocol, lies in its ability to simplify the analytical process without compromising the depth and quality of insights. By crafting a detailed narrative framework, users can guide AI in dissecting and interpreting data within specific contextual boundaries. This framework, built on structured yet easily understandable language, allows AI to perform tasks that previously required specialized data analysis teams.

However, like any automated tool, NCEPtion operates under the principle of “garbage in, garbage out.” The accuracy and relevance of its outputs heavily depend on the quality and precision of the input narrative. Therefore, constructing an effective model within the NCEP framework requires a disciplined approach, ensuring that the narrative accurately reflects the desired analysis scope and depth.

The following sections of this paper will delve into the structure and components of the NCEP framework. We will explore how to effectively fill in this framework, ensuring that the narrative fed into AI systems is primed for yielding insightful, relevant, and contextually grounded results. Through this exploration, the paper aims to demonstrate the efficacy of executing an NCEPtion as pioneering tools in the realm of AI-assisted data interpretation, marking a significant stride in the journey towards more accessible and efficient analytical methodologies.

NCEPtion Protocol Outline

The NCEPtion Protocol is meant to be a template of sorts. Think of it as similar to building your own assembly line, that’s what we are focused on here — and what is it for? That’s entirely up to you. It could be cars or candy; the basic structure is the same. Leave the numbering and headings that are in bold, but replace the normal font words with your own words and delete the examples. A complete reference model is provided after this protocol.

NOTE: Truth-Acceptance Scale (TAS) is an example of a specific insight that a researcher might be interested in. There are many, many others. In the below framework, we will use TAS for the examples. We could have just as easily used Patient Treatment Response Analysis, Market Trend Analysis, or Climate Change Impact Assessment.

Although the examples provided in this paper predominantly center on societal data (TAS) for ease of initial comprehension (think of it as we are building cars instead of candy), it is essential to recognize that the application of this protocol, which is the assembly line in the above metaphor, is not confined to any single discipline. The NCEP framework can be effectively utilized to derive insights across a diverse array of fields and topics.

· Introduction Application of the Framework

• Instructions: Tell the AI precisely what you want it to do, then tell it the format of the output that you desire.
• Example: “ I want you to do two different tasks. The first is to use the following framework to execute the Application below. The second is to take what you learn from the process of executing the Application to state changes to the Framework to make subsequent executions more effective. State these changes in the form of “edit item n.a. to say this: {updated text here}””

1. Task and Context

• Instructions: Clearly articulate the objective of estimating the Subject score for a specific historical time period. Provide context for the task.
• Example: “Objective: Estimate the TAS score for the Enlightenment era, focusing on the society’s approach to rationalism and empiricism.”

2. Defining the Subject Factors

• Instructions: Enumerate and explain each of the factors (the more the better, you should try for at least seven — our example below uses 20), including their measurement criteria min/max (in our example, we use willfully ignorant/seeks truth or W.I./S.T.) and its scoring scale.
• Example: “Factor a: Use of adjectives with ‘truth’. Score 1–5 based on the frequency and context of adjective usage with ‘truth’.”

3. Data Collection and Analysis Guidelines

• Instructions: Specify guidelines for collecting and analyzing historical data relevant to the Subject factors.
• Example: “Collect data from Enlightenment period texts, focusing on philosophical writings, public speeches, and laws. Apply the TAS scoring rubric to each factor.”

4. Normalization and Weighting Instructions

• Instructions: Describe the process for normalizing and weighting scores of each Subject factor to ensure consistency.
• Example: “After scoring each factor, normalize scores to a 0–10 scale. Weight factors based on their impact during the Enlightenment era.”

5. Aggregation and Scaling Method

• Instructions: Explain how to aggregate and scale the normalized and weighted scores of all Subject factors.
• Example: “Aggregate normalized scores of all factors. Scale this aggregate score to fit a 0–10 range, using a smoothing algorithm to account for anomalies.”

6. Interpretation and Contextualization

• Instructions: Provide guidelines for interpreting the Subject score in the context of significant historical and cultural developments of the time period.
• Example: “Interpret the TAS score considering the Enlightenment’s key historical events and cultural shifts. Cross-reference with established historical narratives.”

7. Request for Subject Score Calculation

• Instructions: Detail the process for requesting and presenting the Subject score for a specific historical period.
• Example: “Request the TAS score for the Enlightenment era, ensuring the score is contextualized with its historical background.”

· Application of the Framework

• Instructions: Describe how to apply the framework to a specific historical case study.
• Example: “Apply the TAS framework to estimate the score for the period when Hippocrates was writing. Consider the pre-Alexander era’s cultural and historical context.”

Example Model

Introduction to the Application of Narrative-Contextual Estimation Protocol (NCEP) and NCEPtion

The Truth Acceptance Scale (TAS) Model

In the realm of sociocultural analysis, understanding the nuances and dynamics of a society’s relationship with truth and facts is a complex yet crucial endeavor. This understanding not only sheds light on historical and contemporary behaviors but also aids in anticipating future societal trends. The Truth Acceptance Scale (TAS) model, developed as a pioneering application of the Narrative-Contextual Estimation Protocol (NCEP) and its operational process, NCEPtion, serves as an exemplary case study in this context.

The TAS model is designed to measure a society’s receptivity and openness to objective truth, quantifying this attribute on a scale from 0 to 10. Here, a score of 0 represents a society deeply entrenched in willful ignorance, where beliefs are upheld despite contradicting facts, while a score of 10 signifies a society that highly values truth, even when it challenges long-held beliefs. The TAS model seeks to provide a nuanced understanding of how societies interact with the concept of truth, influenced by various factors such as media diversity, educational standards, and public discourse.

As an NCEPtion, the TAS model transcends traditional data analysis methodologies by integrating a narrative-driven framework into AI systems. This integration allows for the distillation of complex societal behaviors and attitudes into accessible, actionable insights. By crafting a detailed narrative structure that encompasses various sociocultural factors, the model guides AI in analyzing historical and contemporary data, enabling a comprehensive assessment of a society’s truth acceptance levels.

The introduction of the TAS model within the NCEP framework represents a significant advancement in the field of sociocultural analytics. It exemplifies how narrative-driven AI analysis can streamline the process of understanding intricate societal dynamics, offering a cost-effective and efficient alternative to traditional data analysis methods. This paper will delve into the specifics of the TAS model, exploring its components, methodology, and the role of NCEPtion in its application. Through this exploration, we aim to showcase the versatility and effectiveness of narrative-contextual approaches in harnessing AI’s potential for sociocultural analysis.

Sample Model — TAS Estimator

You can copy and paste the following NCEP (between the orange stripes) into your chosen AI, updating the bold text in the last section to any time range of interest — for example, you could just write “when Hippocrates was writing, when the word hypostasis started showing up in various writings” instead of “1950–1960 AD.”

Introduction — Pilot test:

I want you to use the following framework to execute the Application below.

Complete Framework for Estimating TAS Score for a Specific Time Period

1. Task and Context: “The objective is to estimate the Truth Acceptance Scale (TAS) score for a specified historical time period. The TAS is a measure that reflects a society’s openness and receptivity to objective truth on a scale of 0 to 10, 0 being a society is fearful of offending someone, and will allow them to live in ignorance denying basic facts that challenge some belief that they hold to be true (willfully ignorant — W.I.) and 10 being a society values truth over human emotions and a person is more willing to instantly admit they were wrong when confronted by some truth that contradicts some long-held belief and good manners suggest that the person set aside ineffective behaviors for something more beneficial to the individual (seeks truth — S.T.), based on various influencing factors.”
2. Description of the TAS Factors: “Consider the following 20 factors prioritized for the ease of data collection for the TAS assessment. For each, I will provide the measurement consideration in the format of W.I/S.T. For each, you can assign a numerical value on a scale of 1 to 5 (1 being the lowest, indicative of a trend towards W.I., and 5 being the highest, indicative of a trend towards S.T.):
   a. use of adjectives with ‘truth’: more/less (by way of example for this first one, use of “more” adjectives with ‘truth’, a score of 1 might indicate excessive use of adjectives suggesting ambiguity and relativism, while a score of 5 indicates “less” or minimal use of adjectives, suggesting a more objective and singular understanding of truth),
   b. prevalence of logical fallacies: more=1 to less=5,
   c. media sources embracing multiple viewpoints (heterodoxy) : less=1 to more=5,
   d. complexity of communication laws: more=1 to less=5,
   e. orthodoxy viewed as more virtuous than heterodoxy: more=1 to less=5,
   f. cognitive dissonance: more=1 to less=5,
   g. confirmation bias: more=1 to less=5,
   h. belief perseverance: more=1 to less=5,
   i. groupthink: more=1 to less=5,
   j. social desirability bias: more=1 to less=5,
   k. intellectual humility: less=1 to more=5,
   l. religious persecutions: more=1 to less=5,
   m. tolerance of immorality: more=1 to less=5,
   n. diversity of information: less=1 to more=5,
   o. dominance of exclusive thought centers: more=1 to less=5,
   p. engagement with counterarguments: less=1 to more=5,
   q. public trust in institutions: more=1 to less=5,
   r. ratio of “accusations of lies” to “citations of truth”: more accusations of lies=1 to less=5,
   s. law enforcement exceptions based on demographic distinctions: more=1 to less=5,
   t. educational standards: lower=1 to higher=5
3. Data Collection and Analysis Guidelines: “Gather historical data relevant to the 20 TAS factors for the period in question. Analyze literary works, media sources, public speeches, laws, and educational materials and for each TAS factor, apply the rubric to determine a score based on the defined criteria. Consider both quantitative and qualitative aspects of each factor within the historical context. In historical analysis, there might be periods where data for certain TAS factors is sparse or unavailable. Use a logical approach to adjust the weight of those sparse factors so that they do not artificially lower the final outcome score. For example, In cases of sparse data, use available information and logical deductions based on historical parallels to provide a provisional TAS score. This score should be treated as an estimate subject to refinement as more data becomes available. In your analysis, consider not only the significant events and cultural shifts but also prevailing philosophies, technological advancements, and global influences that might have impacted the society’s truth acceptance. Implement a systematic approach to evaluate the representativeness and reliability of historical data sources. This should involve cross-referencing multiple sources for each TAS factor, evaluating the credibility and historical context of these sources, and considering the potential biases they may contain. This rigorous approach will help ensure that the analysis is grounded in diverse, credible, and contextually relevant information, contributing to a more accurate and comprehensive TAS estimation.”
4. Normalization and Weighting Instructions: “Different factors might have varied impacts depending on the era, use a flexible weighting system that can adapt to the specific historical context of the time period being analyzed so as to avoid potentially over-correcting spikes in relation to immediately previous or later neighboring time periods. For example, after scoring each factor, normalize these scores to a standard scale (e.g., 0 to 10) to ensure consistency across all factors. This normalization could involve a simple linear transformation of the original 1–5 scores to the 0–10 scale. Normalize the scores for each of the 20 TAS factors. Assign weights to these factors based on their perceived impact on truth acceptance during the specified period. Weights assigned to each factor should reflect their perceived impact on truth acceptance for the specific historical context. Determine the weights either through historical expert consensus or by using a standard weighting system that accounts for the specific characteristics of the era being analyzed. Integrate a validation step that cross-references the calculated TAS score with established historical narratives and scholarly interpretations. This step should involve comparing the TAS findings with authoritative historical texts, academic papers, and expert analyses relevant to the period in question. The goal is to ensure that the TAS score is consistent with the broader, academically accepted understanding of the era, while also identifying any significant deviations or unique insights revealed by the TAS analysis.”
5. Aggregation and Scaling Method: “Aggregate the normalized and weighted scores of all factors. Scale this aggregate score to fit a 0–10 range, with 0 indicating low truth acceptance or W.I. and 10 indicating high truth acceptance or S.T. To avoid over-correction, incorporate a smoothing algorithm that accounts for spikes or anomalies in certain factors, ensuring a more balanced final TAS score”
6. Interpretation and Contextualization: “Interpret the TAS score in light of significant historical events, cultural shifts, and societal attitudes prevalent during the specified time period. If complete data for all TAS factors is unavailable, use available information to make an educated estimate of the TAS score, contextualizing it within the known broader cultural, philosophical, and societal trends of the period. Implement a comprehensive cross-referencing step to compare the TAS score with key historical narratives and prevailing academic interpretations. This process should involve a thorough review of established historical documents, scholarly works, and expert analyses pertinent to the time period. The aim is to validate that the TAS score accurately reflects the prevailing attitudes and societal conditions of the era, while also considering any potential divergences or unique insights the TAS model may offer.”
7. Request for TAS Score Calculation: “Based on the collected data and analysis of the 20 TAS factors, provide the TAS score for the specified time period. Ensure that the interpretation accounts for the historical context of the era.”

Application:

“Now, estimate the Truth Acceptance Scale (TAS) score for the period of 1950–1960 AD. Use the framework provided, calculate the 20 TAS factors and their impact during this time period. Analyze the data, normalize and weight the factors, providing your score for each, and then provide the overall TAS score in the context of the significant historical and cultural developments of that time. After you finish providing this application, make a recommendation of how I can improve this framework for my next run.”

Conclusion

The development and application of the Narrative-Contextual Estimation Protocol (NCEP) and NCEPtion in this paper, exemplified through the Truth Acceptance Scale (TAS) model, signifies a transformative step in leveraging AI for sociocultural analysis. However, it’s vital to take away that this protocol can be used for distilling a large, complex data set into actionable insights in any field of study. This novel methodology transcends traditional analytical frameworks, offering a more accessible, efficient, and cost-effective approach to understanding complex subject dynamics.

Through NCEP and NCEPtion, we have demonstrated how AI, when guided by a carefully structured narrative, can provide deep insights into historical and contemporary subject attitudes toward truth. The TAS model, in particular, has shown its potential as a robust tool for assessing societal openness to objective truth across different historical periods. By evaluating various sociocultural factors through a standardized protocol, the TAS model offers a nuanced view of societal attitudes, reflecting the complexities inherent in human societies.

The effectiveness of this approach is not solely in its technological sophistication but in its conceptual simplicity. By translating intricate social dynamics into a narrative-driven framework, NCEP and the execution of NCEPtion make advanced AI analysis more accessible to a wider audience. This democratization of data analysis, where sophisticated AI tools can be utilized without extensive technical expertise, represents a significant advancement in the field of data interpretation.

However, as with any analytical tool, the accuracy and relevance of the outputs are contingent on the quality of the input narrative. This necessitates a disciplined approach in constructing the narrative framework, ensuring that the AI’s analysis is aligned with the objective and context of the study. The TAS model serves as a testament to the potential of this approach, demonstrating that when executed with rigor and precision, NCEP and NCEPtion can yield insights of comparable depth and clarity to those derived from more traditional, resource-intensive methods.

In conclusion, the introduction of NCEP and NCEPtion marks a pivotal moment in the evolution of AI-assisted sociocultural analysis. As this methodology continues to develop and refine, its applications could extend far beyond the current scope, offering valuable insights into a myriad of complex subject questions. The TAS model, as a pioneering application of this protocol, sets the stage for future innovations in this exciting and rapidly evolving field.