Combining Similarity Features and Deep Representation Learning for Stance Detection in the Context of Checking Fake News

Abstract

Fake news are nowadays an issue of pressing concern, given their recent rise as a potential threat to high-quality journalism and well-informed public discourse. The Fake News Challenge (FNC-1) was organized in early 2017 to encourage the development of machine learning-based classification systems for stance detection (i.e., for identifying whether a particular news article agrees, disagrees, discusses, or is unrelated to a particular news headline), thus helping in the detection and analysis of possible instances of fake news. This article presents a novel approach to tackle this stance detection problem, based on the combination of string similarity features with a deep neural network architecture that leverages ideas previously advanced in the context of learning efficient text representations, document classification, and natural language inference. Specifically, we use bi-directional Recurrent Neural Networks (RNNs), together with max-pooling over the temporal/sequential dimension and neural attention, for representing (i) the headline, (ii) the first two sentences of the news article, and (iii) the entire news article. These representations are then combined/compared, complemented with similarity features inspired on other FNC-1 approaches, and passed to a final layer that predicts the stance of the article towards the headline. We also explore the use of external sources of information, specifically large datasets of sentence pairs originally proposed for training and evaluating natural language inference methods, in order to pre-train specific components of the neural network architecture (e.g., the RNNs used for encoding sentences). The obtained results attest to the effectiveness of the proposed ideas and show that our model, particularly when considering pre-training and the combination of neural representations together with similarity features, slightly outperforms the previous state-of-the-art. 39:2 • Borges et al.is increasingly harder to know for sure what to trust, with the absorption of fake news by the masses having increasingly harmful consequences [48]. Automatically dealing with fake news has drawn considerable attention in several research communities [24,26,34,36,40,41,45]. However, the task of evaluating the veracity of news articles is still very demanding and complex, even for trained specialists and much more for automated systems.A useful first step towards identifying fake news articles relates to understanding what other news agencies, in a given moment, are reporting about the same topic. This sub-task is often referred to as stance detection, and automating this process might be useful in developing automated assistants to help in fact checking. In particular, an automatic approach to stance detection would allow, for example, someone to insert an allegation or a news title, and recover related articles that either agree, disagree, or discuss that title. Then, the human checker would use her own judgment to assess the situation.Based on the aforementioned general ideas, a Fake Ne...

Fake News Stance Detection Using Deep Learning Architecture (CNN-LSTM)

“…In [12], a deep learning method is used for addressing the stance detection problem from the FNC-1 task. It incorporates bi-directional RNNs together with max-pooling and neural attention mechanisms to build representations from headlines and from the body of news articles and combine these representations with external similarity features.…”

“…As manual fact checking is a very tedious task, automat- VOLUME 4, 2016 ically identification of fake news has drawn considerable attention in the Natural Language Processing (NLP) community to help alleviate the burdensome and time-consuming human activity of fact checking [10], [11]. Despite that, the task of evaluating the authenticity of news remains very complex even for automated systems [12]. Identifying fake news articles by understanding what other news organizations are reporting about the same topic could be a valuable first step.…”

«Deepfakes»: el pròxim repte en la detecció de notícies falses

“…En los últimos años, las noticias falsas se han convertido en un tema que amenaza el discurso público, la sociedad humana y la democracia (Borges, Martins y Calado, 2019;Mackenzie y Bhatt, 2018;Qayyum et al, 2019). En un escenario donde el caos reina en gran parte del ecosistema de información del que dependen las sociedades (Lin, 2019), la información falsa se propaga rápidamente a través de las redes sociales, donde puede impactar a millones de usuarios (Figueira y Oliveira, 2017).…”

“…Este aumento en la popularidad del vídeo destaca la necesidad de herramientas para confirmar la autenticidad del contenido de los medios y las noticias, ya que las nuevas tecnologías permiten manipulaciones convincentes de vídeos o audios (Anderson, 2018). Dada la facilidad para obtener y difundir información errónea a través de las plataformas de redes sociales, tanto en forma de publicación como en los comentarios (Atasanova et al, 2019), cada vez es más difícil saber en qué confiar, lo que genera consecuencias perjudiciales para la toma de decisiones informadas (Borges et al, 2019;Britt et al, 2019). De hecho, hoy vivimos en lo que algunos autores identifican como un escenario de posverdad, que se caracteriza por la desinformación digital, el sesgo mediático (Hamborg et al, 2018), la generación de información falsa y la distorsión deliberada de la realidad, para manipular creencias y emociones e influir en la opinión pública y en actitudes sociales (Anderson, 2018;Qayyum et al, 2019).…”

Deepfake Forensics, an AI-synthesized Detection with Deep Convolutional Generative Adversarial Networks

“…The deepfake technology can realize the tampering, forgery and automatic generation of images, sounds and videos, and produce highly realistic and difficult to distinguish effects. Fake information has become a serious threat to the public news, democracy and human society [1]. The most popular product of deepfake is AI face changing technology, such as Face2Face.…”