aiml-emotion-manipulation

Calibrate a DistilBERT emotion classifier across five manipulation contexts.

934|152|Updated Mar 1, 2026

Search Tags:#benchmarking #safety #classification #emotion #manipulation-detection #isc-template

Ready to run

npx skills add https://github.com/wuyoscar/ISC-Bench --skill aiml-emotion-manipulation

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: aiml-emotion-manipulation
Source: https://github.com/wuyoscar/ISC-Bench/tree/main/templates/aiml_emotion
Command: npx skills add https://github.com/wuyoscar/ISC-Bench --skill aiml-emotion-manipulation

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

ISC Emotion Manipulation template provides a structured approach to calibrate a DistilBERT emotion classifier for targeted detection of manipulation cues in AI safety research. It uses an anchor-based evaluation setup and a clearly defined context suite to ensure reproducible benchmarking across multiple manipulation scenarios.

Core Features & Use Cases

Calibrates a DistilBERT emotion classifier for detection of targeted manipulation cues across five contexts (mass_panic, mob_incitement, grief_exploitation, cult_recruitment, radicalization)
Includes tunable parameters and validation checks to guarantee data quality, reliability, and reproducibility in safety-focused studies
Serves as a reusable benchmark template for researchers evaluating emotion-driven manipulation detection in AI systems

Quick Start

Run the emotion manipulation benchmark on the provided dataset to begin evaluating classifier performance

Frequently Asked Questions about aiml-emotion-manipulation

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I calibrate an emotion classifier for detecting targeted manipulation in AI safety research?▼

Calibrating an emotion classifier for targeted manipulation detection involves using a DistilBERT model within a structured benchmark defined across five specific manipulation contexts. This approach enforces tunable parameters and validation checks to ensure rigorous, reproducible evaluation in AI safety workflows.

What contexts are covered in emotional manipulation detection benchmarks for machine learning?▼

Emotional manipulation detection benchmarks for machine learning cover five distinct contexts: mass panic, mob incitement, grief exploitation, cult recruitment, and radicalization. These defined scenarios provide anchor data to evaluate classifier performance reliably across varied safety-focused studies.

Can I use DistilBERT for reproducible benchmarking of emotion-driven manipulation cues?▼

Yes, you can use DistilBERT for reproducible benchmarking of emotion-driven manipulation cues by applying an anchor-based evaluation setup. This configuration includes tunable parameters and validation checks to guarantee data quality and reliability during classifier calibration.

How do I validate data quality when evaluating emotion classifiers for manipulation detection?▼

Validating data quality when evaluating emotion classifiers for manipulation detection requires applying structured tunable parameters and validation checks within your benchmark setup. This ensures rigorous evaluation and reproducible results across targeted safety scenarios like grief exploitation or radicalization.

Does emotion manipulation detection benchmarking work without external dependencies?▼

Emotion manipulation detection benchmarking works without external dependencies by utilizing a self-contained YAML frontmatter-based skill template. This structure provides reproducible benchmarking capabilities and safety-conscious framing entirely through internal anchor data and validation logic.

Why use anchor-based evaluation setups for emotion classifier calibration?▼

Using anchor-based evaluation setups for emotion classifier calibration ensures reproducible benchmarking across multiple manipulation scenarios. This structured approach guarantees data quality and reliability by enforcing strict validation checks during targeted emotional manipulation detection research.