Towards automatically filtering fake news in Portuguese

Silva, Renato Moraes; Santos, Roney L. S.; Almeida, Tiago A.; Pardo, Thiago Alexandre Salgueiro

doi:10.1016/j.eswa.2020.113199

Cited by 97 publications

(107 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We review some of the recent methods (Mourão et al, 2018;Kim et al, 2019;Elnagar, Al-Debsi & Einea, 2020;Shan et al, 2020;Silva et al, 2020) to represent and classify news documents in other languages such as English, Portuguese and so on. Mourão et al (2018) proposed a novel method, called Net-Class, to represent and classify the news documents in English language.…”

Section: Non-nepali News Document Representation Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Vector representation based on a supervised codebook for Nepali documents classification

Sitaula

Basnet²,

Aryal

2021

PeerJ Computer Science

View full text Add to dashboard Cite

Document representation with outlier tokens exacerbates the classification performance due to the uncertain orientation of such tokens. Most existing document representation methods in different languages including Nepali mostly ignore the strategies to filter them out from documents before learning their representations. In this article, we propose a novel document representation method based on a supervised codebook to represent the Nepali documents, where our codebook contains only semantic tokens without outliers. Our codebook is domain-specific as it is based on tokens in a given corpus that have higher similarities with the class labels in the corpus. Our method adopts a simple yet prominent representation method for each word, called probability-based word embedding. To show the efficacy of our method, we evaluate its performance in the document classification task using Support Vector Machine and validate against widely used document representation methods such as Bag of Words, Latent Dirichlet allocation, Long Short-Term Memory, Word2Vec, Bidirectional Encoder Representations from Transformers and so on, using four Nepali text datasets (we denote them shortly as A1, A2, A3 and A4). The experimental results show that our method produces state-of-the-art classification performance (77.46% accuracy on A1, 67.53% accuracy on A2, 80.54% accuracy on A3 and 89.58% accuracy on A4) compared to the widely used existing document representation methods. It yields the best classification accuracy on three datasets (A1, A2 and A3) and a comparable accuracy on the fourth dataset (A4). Furthermore, we introduce the largest Nepali document dataset (A4), called NepaliLinguistic dataset, to the linguistic community.

show abstract

Section: Non-nepali News Document Representation Methodsmentioning

confidence: 99%

“…Shan et al (2020) proposed an incremental learning strategy based on a deep learning approach to represent and classify English news documents. Silva et al (2020) performed Portuguese news documents classification to capture fake news. They used BoW to represent the documents in their work.…”

Section: Non-nepali News Document Representation Methodsmentioning

confidence: 99%

Vector representation based on a supervised codebook for Nepali documents classification

Sitaula

Basnet²,

Aryal

2021

PeerJ Computer Science

View full text Add to dashboard Cite

show abstract

“…A benchmarking study for fake news detection concludes that SVM with linguisticbased word embedding features enables us to classify fake news with high accuracy (Gravanis et al, 2019). A study about Portuguese fake news detection reveals that random forest outperforms the other five machine learning models (Silva et al, 2020). AdaBoost achieves the best performance on a small corpus than the other six models to separate fake news from legitimate news .…”

Section: Related Workmentioning

confidence: 99%

“…After the U.S. presidential elections in 2015, few popular social media applications like Twitter, Facebook, and Google started to pay attention to design machine learning and natural language processing (NLP) based mechanisms to detect and combat fake news. The remarkable development of supervised machine learning models paved the way for designing expert systems to identify fake news for English, Portuguese (Monteiro et al, 2018;Silva et al, 2020), Spanish (Posadas-Durán et al, 2019), Indonesian (Al-Ash et al, 2019), German, Latin, and Slavic languages (Faustini & Covões, 2020). A major problem of machine learning models is that different models perform differently on the same corpus.…”

Section: Introductionmentioning

confidence: 99%

“…Ensemble learning methods have shown good performance in various applications, including solar irradiance prediction (Lee et al, 2020), slope stability analysis (Pham et al, 2021), natural language processing (Sangamnerkar et al, 2020), malware detection (Gupta & Rani, 2020), traffic incident detection (Xiao, 2019). In the past, several studies explored machine learning models for fake news detection task in a few languages like Portuguese (Monteiro et al, 2018;Silva et al, 2020), Spanish (Posadas-Durán et al, 2019;Abonizio et al, 2020), Urdu , Arabic (Alkhair et al, 2019), Slavic (Faustini & Covões, 2020;Kapusta & Obonya, 2020), and English (Kaur, Kumar & Kumaraguru, 2020;Ozbay & Alatas, 2020). As compared to machine learning, a few efforts have been made to explore ensemble learning for fake news detection like Indonesian (Al-Ash & Wibowo, 2018;Al-Ash et al, 2019), English (Kaur, Kumar & Kumaraguru, 2020;Sangamnerkar et al, 2020).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Supervised ensemble learning methods towards automatically filtering Urdu fake news within social media

Akhter

Zheng

Afzal

et al. 2021

PeerJ Computer Science

View full text Add to dashboard Cite

The popularity of the internet, smartphones, and social networks has contributed to the proliferation of misleading information like fake news and fake reviews on news blogs, online newspapers, and e-commerce applications. Fake news has a worldwide impact and potential to change political scenarios, deceive people into increasing product sales, defaming politicians or celebrities, and misguiding visitors to stop visiting a place or country. Therefore, it is vital to find automatic methods to detect fake news online. In several past studies, the focus was the English language, but the resource-poor languages have been completely ignored because of the scarcity of labeled corpus. In this study, we investigate this issue in the Urdu language. Our contribution is threefold. First, we design an annotated corpus of Urdu news articles for the fake news detection tasks. Second, we explore three individual machine learning models to detect fake news. Third, we use five ensemble learning methods to ensemble the base-predictors’ predictions to improve the fake news detection system’s overall performance. Our experiment results on two Urdu news corpora show the superiority of ensemble models over individual machine learning models. Three performance metrics balanced accuracy, the area under the curve, and mean absolute error used to find that Ensemble Selection and Vote models outperform the other machine learning and ensemble learning models.

show abstract

Fake news detection in the Hindi language using multi‐modality via transfer and ensemble learning

Garg,

Sharma

2024

Internet Technology Letters

View full text Add to dashboard Cite

Fake news classification emerged as an exciting topic for machine learning and artificial intelligence researchers. Most of the existing literature on fake news detection is based on the English language. Hence, it needs more usability. Fake news detection in low‐resource scare languages is still challenging due to the absence of large annotated datasets and tools. In this work, we propose a large‐scale Indian news dataset for the Hindi language. This dataset is constructed by scraping different reliable fact‐checking websites. The LDA approach is adopted to assign the category to news statements. Various machine‐learning and transfer learning approaches are applied to verify the authenticity of the dataset. Ensemble learning is also applied based on the low false‐positive rate of machine‐learning classifiers. A multi‐modal approach is adopted by combining LSTM with VGG‐16 and VGG‐19 classifiers. LSTM is used for textual features, while VGG‐16 and VGG‐19 are applied for image analysis. Our proposed dataset has achieved satisfactory performance.

show abstract

Towards automatically filtering fake news in Portuguese

Cited by 97 publications

References 21 publications

Vector representation based on a supervised codebook for Nepali documents classification

Vector representation based on a supervised codebook for Nepali documents classification

Supervised ensemble learning methods towards automatically filtering Urdu fake news within social media

Fake news detection in the Hindi language using multi‐modality via transfer and ensemble learning

Contact Info

Product

Resources

About