---
type: source
id: kramer-2026-aggregation-human-ai
title: 'Improving human performance in deepfake detection: limits of aggregation and human–AI collaboration'
authors:
- Robin S. S. Kramer
- Victoria P. M. Lister
year: 2026
venue: 'Cognitive Research: Principles and Implications'
volume: null
pages: null
doi: 10.1186/s41235-026-00758-2
peer_review: peer-reviewed-journal
evidence_tier: B
design: 'Four experiments, real-vs-deepfake video judgements. Exp1: response aggregation across the sample. Exp2: confidence ratings, metacognitive sensitivity, confidence-weighted fusion of participant pairs. Exp3-4: decisions before and after simulated algorithmic guidance, varying guidance accuracy and deepfake prevalence'
modality:
- video
stimuli: YouTube clips and their corresponding deepfakes (generator not in abstract)
n_participants: null
n_note: not in abstract
topics:
- human-detection
- crowds
- aggregation
- metacognition
- human-ai-teaming
summary: Individuals detected deepfake videos above chance but modestly; whole-sample aggregation helped, but confidence did not discriminate correct from incorrect trials, confidence-weighted pairing reduced accuracy, and gains from accurate AI guidance were offset by following incorrect advice.
results:
- metric: Individual accuracy
  value: above chance but modest and error-prone
  note: no values in abstract
  source_location: abstract
- metric: Aggregation across full sample (Exp1)
  value: reliable accuracy gains
  note: wisdom of the crowd
  source_location: abstract
- metric: Metacognitive sensitivity (Exp2)
  value: no evidence
  note: confidence modestly higher for correct decisions but did not reliably discriminate at trial level
  source_location: abstract
- metric: Confidence-weighted fusion of pairs (Exp2)
  value: reduced accuracy
  note: ''
  source_location: abstract
- metric: Simulated AI guidance (Exp3-4)
  value: helped when highly accurate; offset by following incorrect advice
  note: reliance unaffected by deepfake prevalence
  source_location: abstract
moderators:
- Guidance accuracy
- Aggregation method
limitations:
- Values not checked against full text
- Simulated, not real, algorithmic guidance
verification:
  status: verified-abstract
  confidence: medium
  checked: 2026-10-18
  via: OpenAlex abstract record for doi:10.1186/s41235-026-00758-2
url: null
pmid: null
pmcid: null
arxiv_id: null
openalex_id: null
oa_url: null
cited_in:
- MR-0001
updated: '2026-10-18'
---

# Improving human performance in deepfake detection: limits of aggregation and human–AI collaboration

> **Source record** `kramer-2026-aggregation-human-ai` · 2026 · Cognitive Research: Principles and Implications  
> **Evidence tier:** B (peer-reviewed-journal) · **Verification:** verified-abstract (compiler confidence: medium)  
> **Bottom line:** Individuals detected deepfake videos above chance but modestly; whole-sample aggregation helped, but confidence did not discriminate correct from incorrect trials, confidence-weighted pairing reduced accuracy, and gains from accurate AI guidance were offset by following incorrect advice.

## Citation {#citation}

Robin S. S. Kramer, Victoria P. M. Lister (2026). Improving human performance in deepfake detection: limits of aggregation and human–AI collaboration. *Cognitive Research: Principles and Implications*. https://doi.org/10.1186/s41235-026-00758-2

Verification entry (identifiers, resolvers, claims with source locations): [/data/citations.json#kramer-2026-aggregation-human-ai](/data/citations.json#kramer-2026-aggregation-human-ai)

## Study design {#design}

| Field | Value |
|---|---|
| Design | Four experiments, real-vs-deepfake video judgements. Exp1: response aggregation across the sample. Exp2: confidence ratings, metacognitive sensitivity, confidence-weighted fusion of participant pairs. Exp3-4: decisions before and after simulated algorithmic guidance, varying guidance accuracy and deepfake prevalence |
| Modality | video |
| Stimuli | YouTube clips and their corresponding deepfakes (generator not in abstract) |
| Participants (N) | not recorded |
| N detail | not in abstract |
| Topics | human-detection, crowds, aggregation, metacognition, human-ai-teaming |

## Results {#results}

| Metric | Value | Note |
|---|---|---|
| Individual accuracy | above chance but modest and error-prone | no values in abstract |
| Aggregation across full sample (Exp1) | reliable accuracy gains | wisdom of the crowd |
| Metacognitive sensitivity (Exp2) | no evidence | confidence modestly higher for correct decisions but did not reliably discriminate at trial level |
| Confidence-weighted fusion of pairs (Exp2) | reduced accuracy |  |
| Simulated AI guidance (Exp3-4) | helped when highly accurate; offset by following incorrect advice | reliance unaffected by deepfake prevalence |

## Moderators {#moderators}

- Guidance accuracy
- Aggregation method

## Limitations {#limitations}

- Values not checked against full text
- Simulated, not real, algorithmic guidance

## Cited in {#cited-in}

- [MR-0001](/metareports/human-detection-accuracy.md): Human Detection of Deepfakes: Accuracy, Bias, Confidence, and Training

## Verification {#verification}

| Field | Value |
|---|---|
| Status | `verified-abstract` |
| Compiler confidence | medium |
| Checked on | 2026-10-18 |
| Via | OpenAlex abstract record for doi:10.1186/s41235-026-00758-2 |

Values on this page have not all been checked against the full text. Confirm them against the primary source before high-stakes use.