Detecting Incongruity Between News Headline and Body Text via a Deep Hierarchical Encoder (2018-11-17T00:00:00.000000Z)

TL;DR

This research introduces million-scale pairs of news headline and body text dataset with incongruity label, which can uniquely be utilized for detecting news stories with misleading headlines.

Abstract

Some news headlines mislead readers with overrated or false information, and identifying them in advance will better assist readers in choosing proper news stories to consume. This research introduces million-scale pairs of news headline and body text dataset with incongruity label, which can uniquely be utilized for detecting news stories with misleading headlines. On this dataset, we develop two neural networks with hierarchical architectures that model a complex textual representation of news articles and measure the incongruity between the headline and the body text. We also present a data augmentation method that dramatically reduces the text input size a model handles by independently investigating each paragraph of news stories, which further boosts the performance. Our experiments and qualitative evaluations demonstrate that the proposed methods outperform existing approaches and efficiently detect news stories with misleading headlines in the real world.

Authors

Joongbo Shin

3 papers

Seunghyun Yoon

5 papers

Kyomin Jung

5 papers

TL;DR

Abstract

Authors

References38 items

Sampling the News Producers: A Large News and Feature Data Set for the Study of the Complex Media Landscape

Learning to Rank Question-Answer Pairs Using Hierarchical Recurrent Encoder with Latent Topic Clustering

Incongruent Headlines: Yet Another Way to Mislead Your Readers

A simple but tough-to-beat baseline for the Fake News Challenge stance detection task

Learning to Identify Ambiguous and Misleading News Headlines

Diving Deep into Clickbaits: Who Use Them to What Extents in Which Topics with What Effects?

Bilateral Multi-Perspective Matching for Natural Language Sentences

Rumor Detection over Varying Time Windows

Social Media and Fake News in the 2016 Election

Stop Clickbait: Detecting and preventing clickbaits in online news media

Emergent: a novel data-set for stance classification

Social Clicks: What and Who Gets Read on Twitter?

XGBoost: A Scalable Tree Boosting System

Misleading Online Content: Recognizing Clickbait as "False News"

The Ubuntu Dialogue Corpus: A Large Dataset for Research in Unstructured Multi-Turn Dialogue Systems

Breaking the News: First Impressions Matter on Online News

Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks

Adam: A Method for Stochastic Optimization

Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling

The effects of subtle misinformation in news headlines.

Convolutional Neural Networks for Sentence Classification

Exact solutions to the nonlinear dynamics of learning in deep linear neural networks

Prominent Features of Rumor Propagation in Online Social Media

Distributed Representations of Words and Phrases and their Compositionality

On the difficulty of training recurrent neural networks

Introduction to "This is Watson"

Understanding the difficulty of training deep feedforward neural networks

Long Short-Term Memory

Learning long-term dependencies with gradient descent is difficult

Towards Automatic Identiﬁcation of Fake News: Headline-Article Stance Detection with LSTM Attention Models

and Vlachos

Fake News Challenge

Click bait: Forward-reference as lure in online news headlines

Dropout: a simple way to prevent neural networks from overfitting

and Bengio

Twitter Sentiment Classiﬁcation using Distant Supervision

and Schmidhuber

were the same with RDE. Hierarchical Recurrent Encoder (HRE) The dimension of the word-embedding vector was set to be 300, which was pre-trained

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names