Filipino and english clickbait detection using a long short term memory recurrent neural network

Philogene Kyle Dimpas; Royce Vincent Po; Mary Jane Sabellano

doi:10.1109/IALP.2017.8300597

Filipino and english clickbait detection using a long short term memory recurrent neural network

Closed

Philogene Kyle Dimpas, Royce Vincent Po, Mary Jane Sabellano

2017 Proceedings of the 2017 International Conference on Asian Language Processing, IALP 2017 Vol. 2018-January Conference paper Cited by 14

Abstract

The Filipinos are very active users on social media which makes them the perfect candidate to gain revenue from posts, blogs, and news from their clicks. These contents usually use tempting headlines to drag users into clicking on them. Especially in the Philippines where fake news is rampant, spreading false news with the use of clickbait headlines can cause a lot of damage and confusion in the country. This research has gathered Filipino and English Headlines (English because it is one of the official languages of the Philippines) and determines if it is clickbait. A neural network architecture based on a Bidirectional Long Short Term Memory (BiLSTM) was used. The model uses Word2Vec to provide word representation and embedding from the corpora. The experimental results showed a 91.5% accuracy using the model. © 2017 IEEE.

Affiliations

University of San Carlos, Talamban Cebu City, Philippines

View full text (DOI) →

Research at a Glance

Research at a Glance

Topics & SDG Alignment

Collaboration

Author Profile (Selected)

References Overview

Journal & Source

Metadata & Integrity