Creating Task-Generic Features for Fake News Detection

Social media platforms has become widely popular among netizens to share views and news. This can be attributed to easy affordability of digital devices, low cost Internet and free subscription to social media platforms. Individuals find social media platforms quite appealing where they can find like-minded people to exchange views and news. Studies have shown that a less credible person is more likely to propagate fake news in order to fulfill their objectives of any form - seeking attention, gaining financial benefits or influencing political views. Hence, fake news detection on social media has become one of the most envisaged research topics in recent times. Fake news detection on social media can be done through various methods based on sources, transmission, styles, and knowledge. The major contribution of this survey paper is to provide a comparative study of major computational methods for fake news detection on social media. The objective of this study is to help researchers carry further research using the details and the research gaps presented in the paper.

show abstract

“…al [127] and Olivieri et. al [107] that address this issue. However, still more reliable and effective works are required in this area.…”

Section: Major Research Findingsmentioning

confidence: 99%

A Comparative Study of Computational Fake News Detection on Social Media

Manish

Jawed

Alam

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…They have applied this method to three publicly available data sets. In another work, the task-generic features have applied to tackle the detection of fake news [38]. Using the crowd signal for the problem and employing it in novel detective algorithm that performs Bayesian inference and jointly learns lagging accuracy of users over time is what [57] contributed to the ield.…”

Section: Key Contributions and Organization Of The Papermentioning

confidence: 99%

Albanian Fake News Detection

Canhasi¹,

Shijaku²,

Berisha³

2022

ACM Trans. Asian Low-Resour. Lang. Inf. Process.

View full text Add to dashboard Cite

Recent years have witnessed the vast increase of the phenomenon known as the fake news. Among the main reasons for this increase are the continuous growth of internet and social media usage and the real-time information dissemination opportunity offered by them. Deceiving, misleading content, such as the fake news, especially the one made by and for social media users, is becoming eminently hazardous. Hence, the fake news detection problem has become an important research topic. Despite the recent advances in fake news detection, the lack of fake news corpora for the under-resourced languages are compromising the development and the evaluation of existing approaches on these languages. To fill this huge gap, in this paper we investigate the issue of fake news detection for the Albanian language. In it, we present a new public data set of labeled true and fake news in Albanian, and perform an extensive analysis of machine learning methods for fake news detection. We performed a comprehensive feature engineering and feature selection experiments. In doing so, we explored the Albanian language related feature categories such as the lexical, syntactic, lying-detection, and psycho-linguistic features. Each article was also modeled in four different ways: with the traditional bag-of-words (BoW) and with three distributed text representations using the state-of-the-art Word2Vec, FastText and BERT methods. Additionally, we investigated the best combination of features and various types of classification methods. The conducted experiments and obtained results from evaluations are finally used to draw some conclusions. They shed light on the potentiality of the methods and the challenges that the Albanian fake news detection presents.

show abstract

“…Such an achievement also validates the quality of our dataset in this early stage, although the test and training datasets derive from the same source, which may cause some noise. In addition, the exploration of other features, such as sentiment-related features, the text similarity features extracted by querying Google [13], and the paralinguistic features using LIWC [15], could provide a better understanding of the detection of satirical articles based on a French-language dataset.…”

Section: B Evaluationmentioning

confidence: 99%

Detection of Satiric News on Social Media: Analysis of the Phenomenon with a French Dataset

Liu¹,

Shabani²,

Balet³

et al. 2019

2019 28th International Conference on Computer Communication and Networks (ICCCN)

Self Cite

View full text Add to dashboard Cite

The topic of deceptive and satiric news has drawn attention from both the public and the academic community, as such misinformation has the potential to have extremely adverse effects on individuals and society. Detecting false and satiric news automatically is a challenging problem in deception detection, and it has tremendous real-word political and social influences. In this paper, we contribute a useful French satiric dataset to the research community and provide a satiric news detection system using machine learning to automate classifications significantly. In addition, we present the preliminary results of our research designed to discriminate real news from satiric stories, and thus ultimately reduce false and satiric news distribution.

show abstract

Creating Task-Generic Features for Fake News Detection

Cited by 24 publications

References 26 publications

A Comparative Study of Computational Fake News Detection on Social Media

A Comparative Study of Computational Fake News Detection on Social Media

Albanian Fake News Detection

Detection of Satiric News on Social Media: Analysis of the Phenomenon with a French Dataset

Contact Info

Product

Resources

About