26 July 2017
15 July 2017
13 July 2017
Fake News Detection
- Fake News Detection Using Deep Learning
- Deep Learning for Stance Detection in News
- A Hybrid Deep Model for Fake News
- A simple but tough-to-beat baseline for the Fake News Challenge stance detection task
- Automatic Detection of Fake News
- Liar Liar Pants on Fire
- Fake News in Social Networks
- Simple Open Stance Classification for Rumour Analysis
- Evaluation Measures for Relevance and Credibility in Ranked Lists
- Fake News Detection on Social Media
- Probabilistic Graphical Models for Credibility Analysis
- The Spread of Fake News by Social Bots
- Everything I Disagree with is #FakeNews
- A Sneak into the Devil's Colony
- I Want to Believe
- Some Like it Hoax
- This Just In
- Fake News Mitigation via Point Process Based Intervention
- Automatic deception detection: Methods for finding fake news
- the_state_of_automated_factchecking
- Stance Detection with BiDirectional Conditional Encoding
- Emergent: A Novel data-set for stance classification
Datasets:
2016-10-facebook-fact-check
kaggle-fake-news
BuzzFeedNews-everything
liar_dataset
politifact-v2apidoc
Fact Checking Sites:
fullfact.org
politifact
opensecrets
snopes
truthorfiction
hoaxslayer
factcheck
Wikipedia
rationalwiki
Reuters Reports:
The Rise of Fact Checking Sites in Europe
Challenges:
Fake News Challenge
Rumor (Pheme)
Sources:
GDELT
Event Registry
SenticNet
ConceptNet
Word Embedding Training Sources:
CommonCrawl
Gigaword
Wikipedia
ConceptNet
SenticNet
Types of Biases:
bias - cognitive - anchoring
|
bias - cognitive - apophenia
|
bias - cognitive - attribution
|
bias - cognitive - confirmation
|
bias - cognitive - framing
|
bias - cognitive - halo effect
|
bias - cognitive - horn effect
|
bias - cognitive - self-serving
|
bias - cognitive - status quo
|
bias - conflict of interest - bribery
|
bias - conflict of interest - favortism
|
bias - conflict of interest - funding
|
bias - conflict of interest - lobbying
|
bias - conflict of interest - regulatory issues
|
bias - conflict of interest - shilling
|
bias - contextual - academic
|
bias - contextual - educational
|
bias - contextual - experimenter
|
bias - contextual - full text on net
|
bias - contextual - media
|
bias - contextual - publication
|
bias - contextual - reporting bias
|
bias - media - advertising
|
bias - media - concision
|
bias - media - corporate
|
bias - media - coverage
|
bias - media - false balance
|
bias - media - gatekeeping
|
bias - media - mainstream
|
bias - media - sensationalism
|
bias - media - statement
|
bias - media - structural
|
bias - prejudice/cultural - classism
|
bias - prejudice/cultural - lookism
|
bias - prejudice/cultural - racism
|
bias - prejudice/cultural - sexism
|
Types of Fake Content:
accounts
|
bias - cognitive
|
bias - conflict of interest
|
bias - contextual
|
bias - extreme bias
|
bias - media
|
bias - prejudice
|
bias - statistics
|
claim - cause/effect
|
claim - definition
|
claim - extreme claim
|
claim - fact
|
claim - policy
|
claim - value
|
clickbait - extremebait
|
clickbait - headlines
|
clickbait - linking
|
conspiracy
|
credibility
|
deception
|
fabricated content
|
false connection
|
false context
|
frequency heuristics
|
gossip
|
groups
|
hate speech
|
hoaxes
|
imposter
|
imprecision
|
influence
|
irony
|
junkscience
|
manipulated content
|
misleading content
|
misuse data
|
parody
|
partisanship
|
plagiarized
|
poll
|
poor journalism
|
proceedwithcaution
|
profit
|
propaganda
|
propagation
|
provoke
|
repressive state
|
reviews
|
rumor
|
sarcasm
|
satire
|
sentiments
|
source
|
spam
|
sponsored content
|
trolling
|
user
|
website
|
Labels:
big data
,
data science
,
deep learning
,
internet
,
linked data
,
machine learning
,
natural language processing
,
news
,
politics
,
semantic web
,
sentiment analysis
,
social networks
,
text analytics
12 July 2017
7 July 2017
6 July 2017
Video Intelligence
Papers:
Case Studies:
Dextro
Clarafai
Google Video Intelligence
Viisights
MIT Creating Videos of the Future
DataSets & Metadata:
Youtube-8M
IPTC
Kaggle Youtube-8M
Youtube-bb
Sports-1M
SUMME
TVSUM
Virat
Computer Vision
UCF101
CCV
- An Improved Algorithm for Video Summarization - A Rank Based Approach
- A Study on Video Summarization Techniques
- Integrating Highlights for More Complete Sports Video Summarization
- Sports Video Summarization using Highlights and Play-Breaks
- Highlights Summarization in Sports Video Based On Replay Detection
- Live Sports Event Detection Based on Broadcast Video and Web-casting Text
- Video Summarization: Techniques and Applications
- Highlight Summarization in Soccer Video based on Goalmouth Detection
- Automatic Summarization of Soccer Highlights Using Audio-visual Descriptors
- Video Summarization with Long Short-term Memory
- Video Summarization using Deep Semantic Features
- A Unified Multi-Faceted Video Summarization System
- Video Summarization via Deep Convolutional Networks
- Video Event Understanding Using Natural Language Descriptions
- Computer Vision and Image Understanding in Big Data
- Efficient Large-Scale Video Classification
- Deep Learning for Video Classification and Captioning
- Deep Learning Methods for Efficient Large Scale Video Labeling
- Large-scale Video Classification with Convolutional Neural Networks
- Sports Videos in the Wild (SVW): A Video Dataset for Sports Analysis
- Browsing Sports Video
Case Studies:
Dextro
Clarafai
Google Video Intelligence
Viisights
MIT Creating Videos of the Future
DataSets & Metadata:
Youtube-8M
IPTC
Kaggle Youtube-8M
Youtube-bb
Sports-1M
SUMME
TVSUM
Virat
Computer Vision
UCF101
CCV
Subscribe to:
Posts
(
Atom
)