Literature review
AuraScore 87/100

Streaming Audience Churn and Engagement Literature Review Specification

Systematically synthesize academic and industry literature on video streaming churn, fatigue, and engagement models into a research specification.

Use this template when designing an empirical literature review to evaluate subscriber churn dynamics, consumption fatigue, and recommendation efficacy for an entertainment streaming platform. It guides the creation of a rigorous literature review protocol and evidence synthesis specification.

Template

Role: Principal Media Economist & Audience Scientist specializing in SVOD consumption dynamics.

Context

  • Target Platform: {{streaming_platform}}
  • Target Audience Cohort: {{target_subscriber_cohort}}
  • Core Churn Hypotheses: {{churn_hypotheses}}
  • Academic & Industry Databases: {{academic_databases}}
  • Temporal Window: {{review_timeframe}}
  • Subscription Model: {{monetization_tier}}

Task

Synthesize peer-reviewed media economics literature, consumer psychology studies, and algorithmic streaming research into a structured literature review specification that validates or refutes {{churn_hypotheses}} for {{streaming_platform}}.

Method

  1. Establish explicit inclusion and exclusion criteria based on {{review_timeframe}} and relevance to {{monetization_tier}}.
  2. Query {{academic_databases}} for empirical studies on content discovery friction, binge-watching fatigue, and catalog valuation.
  3. Map behavioral subscriber economics models specifically applicable to {{target_subscriber_cohort}}.
  4. Extract quantitative effect sizes, hazard rate models, and qualitative findings regarding churn triggers.
  5. Categorize findings across content library depth, algorithmic UI personalization, and price sensitivity.
  6. Evaluate methodological validity, statistical power, and industry transferability of each cited study.
  7. Synthesize competing theoretical models into a unified behavioral framework for {{streaming_platform}}.
  8. Formulate operational hypotheses and experimental test specifications derived directly from the literature.

Constraints

  • MUST cite empirical literature with identifiable statistical methodologies (e.g., survival analysis, discrete choice experiments).
  • MUST NOT rely on unverified trade blog commentary or non-peer-reviewed vendor promotional reports.
  • Every theoretical claim MUST be explicitly linked to {{churn_hypotheses}}.
  • Prioritize publications focusing on {{target_subscriber_cohort}} behavior.
  • Limit scope to evidence addressing {{monetization_tier}} streaming mechanics.

Output format

Generate a formal Literature Review Specification containing:

  1. Executive Protocol Summary (max 200 words)
  2. Search Strategy & Database Inclusion Matrix (table format: database, query strings, filter criteria)
  3. Thematic Evidence Synthesis (3 titled subsections: Algorithmic Discovery, Consumption Fatigue, Pricing Sensitivity; 300-450 words each)
  4. Methodological Quality Appraisal (scored table: citation, sample size, methodology, bias risk)
  5. Derived Empirical Hypotheses & Experimental Spec (minimum 4 formal hypotheses with independent/dependent variables)

Self-review

  • Confirm that all 4 formal hypotheses directly map back to {{churn_hypotheses}}.
  • Verify that search strings and exclusion criteria cover the entire {{review_timeframe}}.
  • Ensure each section meets its designated length and tabular requirements.
AuraScore breakdown
87/100Provisional
Instruction clarity15/15 · Strong

Explicit role, a named task, and discrete steps the model can follow.

Context architecture12/12 · Strong

Background, inputs and variables the model needs before it starts.

Constraint engineering10/12 · Adequate

Hard boundaries — what the model must and must not do.

Output specification14/14 · Strong

A named, field-level shape for the response.

Reasoning structure10/10 · Strong

Ordered work items that force analysis before an answer.

Model compatibility10/10 · Strong

Length and structure that travel across frontier models.

Token efficiency5/10 · Thin

Signal density — instruction weight without padding.

Reusability7/7 · Strong

Documented variables so the scaffold adapts to new inputs.

Robustness3/5 · Adequate

Quality bar, assumptions and behaviour when inputs are thin.

Observed performance1/5 · Thin

How much real usage the template has behind it.

research-analysis
research-literature
media-entertainment
streaming-media
audience-research
churn-analysis