期刊名称：International Journal of Advanced Computer Science and Applications(IJACSA)
印刷版ISSN：2158-107X
电子版ISSN：2156-5570
出版年度：2021
卷号：12
期号：1
页码：398-409
DOI：10.14569/IJACSA.2021.0120148
出版社：Science and Information Society (SAI)
摘要：In recent years, the use of social media and the amount of exchangeable data have increased considerably. The increase in exchangeable data makes data mining, analysis and visualization of relevant information a challenging task. This research work assesses, categorizes, and analyzes Arabic entities on social media selected by users at certain time intervals. To accomplish this aim, the authors built a highly efficient classification model to classify entities according to three categories: person, location, and organization. The developed model captures an entity and specific time, collects all the posts on tweeter that refer to the entity at this specific time, and then classifies, visualize the entity through three methods. It first starts with classifying the entity through a corpus model that depends on customized corpus. If the entity is not classified through that model, it will be send to an indicators model which uses the pre-indicators or post-indicators for classing. Finally, the entity is passed to a gazetteer model which searches for the entity in three gazetteers (person, location, and organization), and accordingly determines the number of times the entity reference is repeated. This work allows scholars and researchers in different fields to visualize the frequency of entities referenced by a community. It also compares how references to entities change over time. The experimental results show that accuracy of the developed model in classifying the tweets is nearly 90%.
关键词：Machine learning; classification; visualization; Arabic entities; social media
