miscellaneous-6

Deception Detection

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in deception-detection-12

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find deception-detection-12 models and implementations

manideep2510/siamese-BERT-fake-news…

2 papers 135

Datasets

Mafiascum

The Mafia Dataset

Subtasks

Deception Detection In Videos

Most implemented papers

The Mafiascum Dataset: A Large Text Corpus for Deception Detection

Bob de Ruiter, George Kachergis•Sun Nov 18 2018

This work introduces the Mafiascum dataset, a collection of over 700 games of Mafia, in which players are randomly assigned either deceptive or non-deceptive roles and then interact via forum postings to construct a set of hand-picked linguistic features based on prior deception research.

19

Content

0

Paper Graph

Explain, Edit, and Understand: Rethinking User Study Design for Evaluating Model Explanations

Graham Neubig, Zachary Chase Lipton, Siddhant Arora, William W. Cohen, N. Sadeh, Danish Pruthi•Thu Dec 16 2021

A crowdsourcing study where participants interact with deception detection models that have been trained to distinguish between genuine and fake hotel reviews, it is observed that for a linear bag-of-words model, participants with access to the feature coefficients during training are able to cause a larger reduction in model confidence in the testing phase when compared to the no-explanation control.

44 0

Paper Graph

Can lies be faked? Comparing low-stakes and high-stakes deception video datasets from a Machine Learning perspective

M. Camara, Adriana Postal, T. Maul, Gustavo Paetzold•Tue Nov 22 2022

In the authors' experiments, a network trained in low-stakes lies had better accuracy classifying high-stakes deception thanLow-stakes, although using low- stakes lies as an augmentation strategy for the high- stakes dataset decreased its accuracy.

9 0

Paper Graph

Audio-Visual Deception Detection: DOLOS Dataset and Parameter-Efficient Crossmodal Learning

A. Kot, Zitong Yu, Xiaobao Guo, Nithish Muthuchamy Selvaraj, A. Kong, Bingquan Shen•Wed Mar 08 2023

This work introduces DOLOS 1, the largest gameshow deception detection dataset with rich deceptive conversations, and proposes Parameter-Efficient Crossmodal Learning (PECL), where a Uniform Temporal Adapter (UT-Adapter) explores temporal attention in transformer-based architectures, and a crossmodal fusion module, Plug-in Audio-Visual Fusion (PAVF), combines crossmodal information from audio-visual features.

23 0

Paper Graph

UNIDECOR: A Unified Deception Corpus for Cross-Corpus Deception Detection

Roman Klinger, Aswathy Velutharambath•Sun Jun 04 2023

This paper surveys available English deception datasets which include domains like social media reviews, court testimonials, opinion statements on specific topics, and deceptive dialogues from online strategy games to conduct correlation analysis of linguistic cues of deception across datasets and perform cross-corpus modeling experiments which show that a cross-domain generalization is challenging to achieve.

5 0

Paper Graph

Spatiotemporal Pyramidal CNN with Depth-Wise Separable Convolution for Eye Blinking Detection in the Wild

Lan Anh Thi Nguy, Nguyen Bach, Thanh Tu Thi Nguyen, Kamioka Eiji, Tan Phan-Xuan•Mon Jun 19 2023

Using Depth-wise Separable Convolution rather than conventional convolution layers inside each branch is considered in this paper as a feasible solution to how the eye blinking detection model can learn efficiently from different resolutions of eye pictures in diverse conditions.

1 0

Paper Graph

Adding a benchmark result helps the community track progress.