| Abstrakt: |
Artificial intelligence is involved in all aspects of life and with the development of social media, the methods used in sending spam have evolved and it becomes difficult to detect and control it manually. Therefore, due to the need to use artificial intelligence in language processing and the detection of propaganda messages by classifying posts and tweets that carry a disturbing message on Twitter in this study, We propose a new system to detect spam in Twitter for the Arabic language, based on the trend of hashtags, using artificial intelligence algorithms and extracting properties. It contains three data collection stages, image and text characteristics extraction, and classification stage based on combination of CNN algorithm and SVM algorithm. In addition to this search, annoying text and images, in addition to combining two classification algorithms. The classification accuracy is 98% and the results indicate the best compared to the rest of the models when tested after the testing process on four samples of the data collected from Twitter [ABSTRACT FROM AUTHOR] |
