GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → yaqingwang → WeFEND-AAAI20

yaqingwang / WeFEND-AAAI20

Licence: other
Dataset for paper "Weak Supervision for Fake News Detection via Reinforcement Learning" published in AAAI'2020.

Programming Languages

Jupyter Notebook
11667 projects

Labels

social-mediadeep-learningweak-supervisiondatasetfake-newsweakly-supervised-learningaaai2020

Projects that are alternatives of or similar to WeFEND-AAAI20

EANN-KDD18
EANN: event-adversarial neural networks for multi-modal fake news detection
Stars: ✭ 171 (+155.22%)
Mutual labels:  social-media, fake-news
ASTRA
Self-training with Weak Supervision (NAACL 2021)
Stars: ✭ 127 (+89.55%)
Mutual labels:  weak-supervision, weakly-supervised-learning
wrench
WRENCH: Weak supeRvision bENCHmark
Stars: ✭ 185 (+176.12%)
Mutual labels:  weak-supervision, weakly-supervised-learning
concept-based-xai
Library implementing state-of-the-art Concept-based and Disentanglement Learning methods for Explainable AI
Stars: ✭ 41 (-38.81%)
Mutual labels:  weak-supervision, weakly-supervised-learning
Learning-From-Rules
Implementation of experiments in paper "Learning from Rules Generalizing Labeled Exemplars" to appear in ICLR2020 (https://openreview.net/forum?id=SkeuexBtDr)
Stars: ✭ 46 (-31.34%)
Mutual labels:  weak-supervision, weakly-supervised-learning
trove
Weakly supervised medical named entity classification
Stars: ✭ 55 (-17.91%)
Mutual labels:  weak-supervision, weakly-supervised-learning
weasel
Weakly Supervised End-to-End Learning (NeurIPS 2021)
Stars: ✭ 117 (+74.63%)
Mutual labels:  weak-supervision, weakly-supervised-learning
knodle
A PyTorch-based open-source framework that provides methods for improving the weakly annotated data and allows researchers to efficiently develop and compare their own methods.
Stars: ✭ 76 (+13.43%)
Mutual labels:  weak-supervision, weakly-supervised-learning
Classification-of-Depression-on-Social-Media-Using-Text-Mining
The first asian machine learning in Jeju Island, South Korea - Project
Stars: ✭ 57 (-14.93%)
Mutual labels:  social-media
DaProfiler
DaProfiler allows you to create a profile on your target based in France only. The particularity of this program is its ability to find the e-mail addresses your target.
Stars: ✭ 58 (-13.43%)
Mutual labels:  social-media
HiGitClass
HiGitClass: Keyword-Driven Hierarchical Classification of GitHub Repositories (ICDM'19)
Stars: ✭ 58 (-13.43%)
Mutual labels:  weakly-supervised-learning
Flutter-Photoarc-app
(Full-stack) Fully functional social media app (Instagram clone) written in flutter and dart with backend node.js and Postgres SQL.
Stars: ✭ 38 (-43.28%)
Mutual labels:  social-media
Wordle2Townscaper
Wordle2Townscaper is meant to convert Wordle tweets into Townscaper houses using yellow and green building blocks.
Stars: ✭ 64 (-4.48%)
Mutual labels:  social-media
gobo
💭 Gobo: Your social media. Your rules.
Stars: ✭ 87 (+29.85%)
Mutual labels:  social-media
ts-serverless
Telar Social Network using OpenFaaS and Kubernetes. Run your own server-less social network. One command from OpenFaaS Cloud to build Social Network.
Stars: ✭ 34 (-49.25%)
Mutual labels:  social-media
Ocelot-Social
Free and open-source social network for active citizenship.
Stars: ✭ 49 (-26.87%)
Mutual labels:  social-media
pH4Social
📣 Social Networking Software built with Laravel PHP framework and Bootstrap.
Stars: ✭ 27 (-59.7%)
Mutual labels:  social-media
ACT AAAI20
code for AAAI 2020 paper "ACT"
Stars: ✭ 105 (+56.72%)
Mutual labels:  aaai2020
tapit-app
App which lets two people share their social media details by simply putting one phone on top of the other ("tapping"). Currently in development by Nikita Mounier.
Stars: ✭ 18 (-73.13%)
Mutual labels:  social-media
crabber
A Twitter clone written in Python + Flask with extended features and a focus on inclusivity.
Stars: ✭ 42 (-37.31%)
Mutual labels:  social-media
View All Similar Projects ➔

WeFEND-AAAI20

Weak Supervision for Fake News Detection via Reinforcement Learning
Yaqing Wang, Weifeng Yang, Fenglong Ma, Jin Xu, Bin Zhong, Qiang Deng, Jing Gao

SUNY Buffalo & WeChat. AAAI, 2020.

Dataset

[2020-07-26] We collected more data and make it public. 


└── data/    
    └── train/
    └── test/
    └── unlabeled data/

Data Statistics

# of data # of fake news
train 10,587
 2,743
test 10,141
1,482
unlabeled news 67,748
-

Data Description

Columns Description
Official Account Name The name of official account, news publisher
Title News Title
News Url The url of news
Image Url The url of cover image
Report Content The reports from reader, split by ##
label label of news, 0 is real and 1 is fake

Main Idea

Challenge:

Due to the dynamic nature of news, annotated samples may become outdated quickly and cannot represent the news articles on newly emerged events. Therefore, how to obtain fresh and high-quality labeled samples is the major challenge in employing deep learning models for fake news detection.

Solution:

We propose a reinforced weakly supervised fake news detection framework, i.e., WeFEND, which can leverage users’ reports as weak supervision source to enlarge the amount of training data for fake news detection.

Experiment

We aim to answer two important questions:

  • Does the distribution of news change with time?
  • why should we use the reports to annotate the fake news?

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].