Predicting Rogue Content and Arabic Spammers on Twitter

Alharbi, Adel R.; Aljaedi, Amer

doi:10.3390/fi11110229

Cited by 13 publications

(10 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…According to [1], modern propaganda operates with many kinds of truth, such as halftruth, limited reality, and truth out of context. In recent times propaganda has been used by terrorist organizations for recruitment [2][3][4][5] and by political parties during elections [6][7][8][9], among many others. Today, abundant online news media has cropped up, some with the intent of spreading propaganda.…”

Section: Discussionmentioning

confidence: 99%

H-Prop and H-Prop-News: Computational Propaganda Datasets in Hindi

Chaudhari

Pawar

Barrón-Cedeño

2022

Data

View full text Add to dashboard Cite

In this digital era, people rely on the internet for their news consumption. As people are free to express their opinions on social media, much information shared on the internet is loaded with propaganda. Propagandist contents are intended to influence public opinion. In the mainstream media or prominent news agencies, the authors’ and news agencies’ own bias may impact in the news contents. Hence, it is required to detect such propaganda spread through news articles. Detection and classification of propagandist text require standard, high-quality, annotated datasets. A few datasets are available for propaganda classification. However, these datasets are mostly in English. Hindi is the most spoken language in India, and efforts are needed to detect its propagandist contents. This research work introduces two new datasets: H-Prop and H-Prop-News, which consist of news articles in Hindi annotated as propaganda or non-propaganda. The H-Prop dataset is generated by translating 28,630 news articles from the QProp dataset. The H-Prop-News dataset contains 5500 news articles collected from 32 prominent Hindi news websites. We experiment with the proposed datasets using four supervised machine learning models combined with different feature vectors and word embeddings. Our experiments achieve 87% accuracy using Logistic Regression with TF-IDF feature vectors. The datasets provide high-quality labeled news articles in Hindi and open new avenues for researchers to explore techniques for analyzing and classifying propaganda in Hindi text.

show abstract

Section: Discussionmentioning

confidence: 99%

H-Prop and H-Prop-News: Computational Propaganda Datasets in Hindi

Chaudhari

Pawar

Barrón-Cedeño

2022

Data

View full text Add to dashboard Cite

show abstract

“…For tokenization, we used the Natural Language Toolkit (NLTK), and then we applied methods MC1 and MC2 working with both multiclass classification and binary classification. We trained and tested on the ASTD Arabic dataset [ 28 ] and also the larger ATDFS dataset [ 59 ].…”

Section: Proposed Methodsmentioning

confidence: 99%

“…For sentiment classification of Arabic text, our models are trained using the Arabic Sentiment Tweets Dataset (ASTD) [ 8 , 28 ] and the Arabic Twitter Data For Sentiment (ATDFS) [ 29 , 59 ]. Tables 10 and 11 show the details of the datasets.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Improving Arabic Sentiment Analysis Using CNN‐Based Architectures and Text Preprocessing

Mustafa

Sutcliffe

Sun

et al. 2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Sentiment analysis is an essential process which is important to many natural language applications. In this paper, we apply two models for Arabic sentiment analysis to the ASTD and ATDFS datasets, in both 2-class and multiclass forms. Model MC1 is a 2-layer CNN with global average pooling, followed by a dense layer. MC2 is a 2-layer CNN with max pooling, followed by a BiGRU and a dense layer. On the difficult ASTD 4-class task, we achieve 73.17%, compared to 65.58% reported by Attia et al., 2018. For the easier 2-class task, we achieve 90.06% with MC1 compared to 85.58% reported by Kwaik et al., 2019. We carry out experiments on various data splits, to match those used by other researchers. We also pay close attention to Arabic preprocessing and include novel steps not reported in other works. In an ablation study, we investigate the effect of two steps in particular, the processing of emoticons and the use of a custom stoplist. On the 4-class task, these can make a difference of up to 4.27% and 5.48%, respectively. On the 2-class task, the maximum improvements are 2.95% and 3.87%.

show abstract

“…Each filter category has more than 50 words. The programmed filters calculate the percentage of the occurrence of the words for each news article, then decide in which category the news belongs [1]. Table 3 shows the category names with its number of observations.…”

Section: Categorisationmentioning

confidence: 99%

Enhancing topic clustering for Arabic security news based on k‐means and topic modelling

2021

Self Cite

View full text Add to dashboard Cite

The internet has become one of the main sources of news spread as it unleashed the information dissemination space, where the news websites express opinions on entities while also reporting on recent or unusual security risks. Recently, many research studies have focused on sentimental reflection on the views and impressions of people utilising natural language processing and analytical linguistics. Therefore, we have collected corpus from popular Arabic websites that publish articles related to recent security issues, and we provide light weight preprocessing techniques where data is term matrix is transformed. We also present an intensive lexical-driven data analysis with visualised data views, as our topic modelling technique can effectively extract significant topics from all the collected text from different websites. Our experiments validate the k-means clustering algorithm with and without the latent Dirichlet allocation topic modelling method, and we adopted various validation techniques to measure the topic clustering internally and externally. As shown in the experiments' results, our proposed combined method has a high round index rate of 87.2%, with a large number of topics and clusters. This is an open access article under the terms of the Creative Commons Attribution-NonCommercial-NoDerivs License, which permits use and distribution in any medium, provided the original work is properly cited, the use is non-commercial and no modifications or adaptations are made.

show abstract

Predicting Rogue Content and Arabic Spammers on Twitter

Cited by 13 publications

References 29 publications

H-Prop and H-Prop-News: Computational Propaganda Datasets in Hindi

H-Prop and H-Prop-News: Computational Propaganda Datasets in Hindi

Improving Arabic Sentiment Analysis Using CNN‐Based Architectures and Text Preprocessing

Enhancing topic clustering for Arabic security news based on k‐means and topic modelling

Contact Info

Product

Resources

About