Clickbait Detection Using Deep Recurrent Neural Network

Razaque, Abdul; Alotaibi, Bandar; Alotaibi, Munif; Hussain, Shujaat; Alotaibi, Aziz; Jotsov, Vladimir

doi:10.3390/app12010504

Cited by 15 publications

(4 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The audiences are able to tell which titles and cover pictures are professionally designed. Also, there are already multiple technical ways to detect clickbaits and similar styles of phrasing nowadays, which makes it almost impossible for the clickbaits to stay unrecognized [6]. This condition also helps the current form of phrasing, which is to make the title cover picture seem like an ordinary daily life post.…”

Section: Discussionmentioning

confidence: 99%

Research on Clickbait Effect of Phrasing in Media Contents Titles

2023

LNEP

View full text Add to dashboard Cite

The research is about how the phrasing in the media contents title and cover picture, including word choices, ways of speaking, and forms of expression in pictures, affects the audiences willingness to click and read; it also aims at analyzing the timeliness of certain styles of phrasing, such as whether the traditional and old phrasing styles will be less effective with time moving forward. Upon the purposes, the research includes a survey and an interview after it. The survey includes basic questions to test how do the participants react to certain ways of phrasing; the interview provides as a clarification to the purpose and the function of each question in the survey, then asks the participants to declare their feeling during the survey and how do they subjectively feel about the usage of phrasing in media titles and cover pictures. Following the research and analysis, the following conclusion is reached: using phrasing in media titles and covers is effective in increasing audiences' willingness to click and read; traditional phrasing becomes less effective, and new forms of phrasing prove to be more effective.

show abstract

Section: Discussionmentioning

confidence: 99%

Research on Clickbait Effect of Phrasing in Media Contents Titles

2023

LNEP

View full text Add to dashboard Cite

show abstract

“…Naeem et al (2020) considered 16,000 headlines for clickbait and non-clickbait headlines and got an accuracy of 0.97 for LSTM with 300 dimensional word2vec embedding and 0.88 for part of speech analysis module (POSAM). Razaque et al (2022) proposed a deep recurrent neural network (RNN) using source rating analysis that examined 1800 legal websites with an accuracy of 0.9983. Ma et al (2022) created 6,000 clickbait and 6,000 non-clickbait from Chinese news websites, and using CNN-LSTM with title embedding, content embedding, and adding 18 manual features, obtained an accuracy of 98.42%.…”

Section: Related Workmentioning

confidence: 99%

Identification of clickbait news articles using SBERT and correlation matrix

Supriya,

Singh,

Kumar

2023

Preprint

View full text Add to dashboard Cite

Clickbait refers to the practice of using attention-grabbing or misleading headlines to attract readers to click on particular headlines or pieces of content. This technique often involves exaggerating claims or adding false information to attract traffic. In general, clickbait headlines are less similar to detailed articles associated with that headline compared to the standard news post. In our proposed system, we have exploited that to create features from headlines and its paragraph by using SBERT. Since the size of the paragraph is quite large compared to the headlines, we have selected a few sentences from the paragraph using a dissimilarity matrix. The extracted features from the headlines, target title and selected sentences of the paragraph are concatenated and classified using machine learning (ML) classifiers. The proposed model was tested extensively on two real-world datasets, and the results showed that it performed better than the current state-of-the-art models. The experimental results, the support vector machine (SVM) classifier with the concatenated embedding of six dissimilar sentences from paragraph exhibited the best performance with an accuracy of 0.84, weighted precision of 0.83, weighted recall of 0.84, and weighted F1-score of 0.82 surpassing the state-of-the-art model by 0.088 in terms of F1-score.

show abstract

“…Razaque et al proposed a RNN model to determine if a link (URL) in a clickbait message is malicious or harmless [42]. Another RNN model by the same authors determines if the content pointed to by a link (e.g., an article or a social media post) is malicious or harmless [43].…”

Section: B Existing Work On Clickbait Detectionmentioning

confidence: 99%

An Attention-Based Neural Network Using Human Semantic Knowledge and Its Application to Clickbait Detection

Feng

Nguyen

2022

IEEE Open J. Comput. Soc.

View full text Add to dashboard Cite

Clickbait is a commonly used social engineering technique to carry out phishing attacks, illegitimate marketing, and dissemination of disinformation. As a result, clickbait detection has become a popular research topic in recent years due to the prevalence of clickbait on the web and social media. In this article, we propose a novel attention-based neural network for the task of clickbait detection. To the best of our knowledge, our work is the first that incorporates human semantic knowledge into an artificial neural network, and uses linguistic knowledge graphs to guide attention mechanisms for the clickbait detection task. Extensive experimental results show that the proposed model outperforms existing state-of-the-art clickbait classifiers, even when training data is limited. The proposed model also performs better or comparably to powerful pre-trained models, namely, BERT, RoBERTa, and XLNet, while being much more lightweight. Furthermore, we conducted experiments to demonstrate that the use of human semantic knowledge can significantly enhance the performance of pre-trained models in the semi-supervised domain such as BERT, RoBERTa, and XLNet.

show abstract

Clickbait Detection Using Deep Recurrent Neural Network

Cited by 15 publications

References 22 publications

Research on Clickbait Effect of Phrasing in Media Contents Titles

Research on Clickbait Effect of Phrasing in Media Contents Titles

Identification of clickbait news articles using SBERT and correlation matrix

An Attention-Based Neural Network Using Human Semantic Knowledge and Its Application to Clickbait Detection

Contact Info

Product

Resources

About