An experimental system for measuring the credibility of news content in Twitter

Al‐Khalifa, Hend S.; Al-Eidan, Rasha M. BinSultan

doi:10.1108/17440081111141772

Cited by 58 publications

(36 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Credibility assessment has been studied from another point of view based on similarity. Al-Khalifa et al [21] developed a model to measure credibility of Twitter messages and assign the credibility level (high, low and moderate) to each tweet. The proposed model is based on the similarity between Twitter messages and authorized news sources like Aljazeera.net.…”

Section: Related Workmentioning

confidence: 99%

Credibility Detection in Twitter Using Word N-gram Analysis and Supervised Machine Learning Techniques

Hassan¹,

Gomaa²,

Khoriba³

et al. 2020

IJIES

View full text Add to dashboard Cite

With the evolution of social media platforms, the Internet is used as a source for obtaining news about current events. Recently, Twitter has become one of the most popular social media platforms that allows public users to share the news. The platform is growing rapidly especially among young people who may be influenced by the information from anonymous sources. Therefore, predicting the credibility of news in Twitter becomes a necessity especially in the case of emergencies. This paper introduces a classification model based on supervised machine learning techniques and word-based N-gram analysis to classify Twitter messages automatically into credible and not credible. Five different supervised classification techniques are applied and compared namely: Linear Support Vector Machines (LSVM), Logistic Regression (LR), Random Forests (RF), Naïve Bayes (NB) and K-Nearest Neighbors (KNN). The research investigates two feature representations (TF and TF-IDF) and different word N-gram ranges. For model training and testing, 10-fold cross validation is performed on two datasets in different languages (English and Arabic). The best performance is achieved using a combination of both unigrams and bigrams, LSVM as a classifier and TF-IDF as a feature extraction technique. The proposed model achieves 84.9% Accuracy, 86.6% Precision, 91.9% Recall, and 89% F-Measure on the English dataset. Regarding the Arabic dataset, the model achieves 73.2% Accuracy, 76.4% Precision, 80.7% Recall, and 78.5% F-Measure. The obtained results indicate that word N-gram features are more relevant for the credibility prediction compared with content and source-based features, also compared with character N-gram features. Experiments also show that the proposed model achieved an improvement when compared to two models existing in the literature.

show abstract

Section: Related Workmentioning

confidence: 99%

Credibility Detection in Twitter Using Word N-gram Analysis and Supervised Machine Learning Techniques

Hassan¹,

Gomaa²,

Khoriba³

et al. 2020

IJIES

View full text Add to dashboard Cite

show abstract

“…However, when sharing, the conversion to structured data and the similarity of the information do not ensure its veracity; therefore, its use for research is compromised by this vulnerability [20] [21]. There are works focused on measuring the level of credibility of the information applied on specific data sources, such as Twitter [3] [22]- [28], but nonexistent for others, as Facebook.…”

Section: Information Sources On Internetmentioning

confidence: 99%

“…In [22] the Twitter API is used to implement an algorithm that combines text search on a specific topic with social aspects of the account (followers), to measure the tweet credibility. In [3], in addition to considering the text content, characteristics associated with the user account are evaluated, such as its verified quality and its Twittergrader.com 3 (text, user, and social credibility). In [24], authors mix characteristics associated with the message (text and sentiment analysis), the users (registration age), the social impact (number of followers, number of following, number of tweets the user has authored in the past, retweets), and a particular topic.…”

Section: B Credibility Analysis On Twittermentioning

confidence: 99%

See 1 more Smart Citation

Credibility Analysis for Available Information Sources on the Web: A Review and a Contribution

Dongo

Cardinale

Aguilera

2019

2019 4th International Conference on System Reliability and Safety (ICSRS)

View full text Add to dashboard Cite

In this paper, we present a study about the most popular information sources available on the Web (e.g., Google, Facebook, Twitter) and the available methods to verify their publications. We propose a generic credibility analysis model for social information sources, which is instantiated for Twitter. We show a proof of concepts through the development of World White Web, a Google Chrome extension application that implements the model to analyze tweets in real time, using web scraping. Our study demonstrates the feasibility and suitability of creating efficient methods to analyze the credibility of publication on social networks and points out the challenges and open problems that should be overcome in future solutions in this area.

show abstract

“…Morris et al [16] researched the credibility of Microblog information through two experiments. Al-Khalifa and AlEidan [17] also designed a system to calculate the credibility of Twitter messages.…”

Section: Introductionmentioning

confidence: 99%

Rumor Identification with Maximum Entropy in MicroNet

Liu

2017

Complexity

View full text Add to dashboard Cite

The widely used applications of Microblog, WeChat, and other social networking platforms (that we call MicroNet) shorten the period of information dissemination and expand the range of information dissemination, which allows rumors to cause greater harm and have more influence. A hot topic in the information dissemination field is how to identify and block rumors. Based on the maximum entropy model, this paper constructs the recognition mechanism of rumor information in the micronetwork environment. First, based on the information entropy theory, we obtained the characteristics of rumor information using the maximum entropy model. Next, we optimized the original classifier training set and the feature function to divide the information into rumors and nonrumors. Finally, the experimental simulation results show that the rumor identification results using this method are better than the original classifier and other related classification methods.

show abstract

An experimental system for measuring the credibility of news content in Twitter

Cited by 58 publications

References 24 publications

Credibility Detection in Twitter Using Word N-gram Analysis and Supervised Machine Learning Techniques

Credibility Detection in Twitter Using Word N-gram Analysis and Supervised Machine Learning Techniques

Credibility Analysis for Available Information Sources on the Web: A Review and a Contribution

Rumor Identification with Maximum Entropy in MicroNet

Contact Info

Product

Resources

About