Palestine Polytechnic University publishes a scientific research in a peer-reviewed journal of its PhD program in Information Technology and Computer Engineering
Palestine Polytechnic University published a scientific research in a peer-reviewed scientific journal of the PhD program in Information Technology and Computer Engineering on "Intelligent Detection of False Information in Arabic Tweets". The paper was published in the "Symmetry" magazine of the Swiss "MDBI".
The student: Thaer Thaher, from the joint Information Technology Engineering PhD program between Palestine Polytechnic University, Al-Quds University and the Arab American University, confirmed that the publication of the scientific paper in the field of uncovering false news came as the fruit of a course called information retrieval, supervised by Dr. Mahmoud Al-Saheb from Palestine Polytechnic University, with the participation of Dr. Hamza Tarabieh from Taif University, and Dr. Hamouda Chantar from Sebha University.
False or fake information on social media platforms is a major challenge that deliberately misleads users, through rumors, propaganda or deceptive information about a person, organization or service. Twitter is one of the most widely used social media platforms, especially in the Arab region, where the number of users is steadily increasing, accompanied by an increase in the rate of misleading or fake news. This drew the researchers' attention to the need to provide a safe environment, free of misleading information, on the Internet.
The paper aims to propose a smart classification model for early detection of false news in Arabic Tweets using NLP(Natural Language Processing) techniques, ML (Machine Learning) models and HHO (Harris Hawks Optimizer), as a “Wrapper-based” feature selection approach.
During work on this research, an “Arab Twitter corpus composed of 1862” previously annotated tweets was utilized by this research to assess the efficiency of the proposed model. The Bag of Words “BoW” model was used using different term-weighting schemes to extract the features. Eight well-known learning algorithms were investigated using with varying combinations of features, including user profile, content-based and word features. The results of the research showed that the "LR" with Term Frequency-Inverse Document Frequency "TF-IDF" model scores the best rank. Moreover, feature selection based on the binary "HHO" algorithm plays a vital role in reducing dimensionality, thereby enhancing the performance of the learning model to detect fake news. The research also showed that the proposed "BHHO-LR" model can produce a better enhancement of 5% compared with previous works on the same dataset..