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

Abstract

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.

Defining facets of social distancing during the COVID-19 pandemic: Twitter analysis

“…We examined frequent word pairs (bigrams) for each facet to qualitatively validate that tweets were related to the facet they were assigned to as has been done in other Twitter-based studies as they offer more insight into the sentiment of tweets than examining unigrams on their own [18] , [19] , [20] . A representative sample is shown in Appendix B.…”

A Framework for Spam Detection in Twitter Based on Recommendation System

“…In this section, we compare the performance of the proposed model with three models existing in the literature. The first model was introduced by Noha Hassan et al [42] who introduces a classification model based on supervised machine learning techniques and word-based N-gram analysis to automatically classify Twitter messages into credible and non-credible. The results in Table 5 show that this model has an accuracy of 84.9%.…”

“…in Facebook also , Fong et al [35] have taken into consideration the analysis of the avatar on a profile, sex, age, and the name. Noha et al [42], 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. 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.…”

Influence of Pre-Processing Strategies on the Performance of ML Classifiers Exploiting TF-IDF and BOW Features

“…Using a Kaggle data collection, the authors investigated to label each of the tweets as positive, negative or neutral sentiment. A classification algorithm focused on supervised ML techniques and word-based N-gram processing to automatically divide Twitter messages into credible and not credible ones introduced by (Hassan et al, 2020). Five different supervised ML classification techniques were applied and the research examines two interpretations of features (TF and TF-IDF) and separate sets of N-gram terms.…”