Keywords : Newspaper
Engineering and Technology Journal,
2020, Volume 38, Issue 2B, Pages 74-84
Due to the increasing electronic publishing sites for printed and certified newspapers, the reader faced the problem of reaching his goal by accessing these sites, which led to the neglect of a large section of important publications. The provision of an automated measure to verify the positive and negative articles based on the analysis of readers' comments on the articles is a necessity to see the important articles that are compatible with the corpus generated by us for inference. The project achieved the previous target and achieved a success rate. The Bag-of-Words Model (BoW) was used to obtain the repetition of the block of words to build the corpus. The proposed system is evaluated based on four metrics (Accuracy= 93%, Precision= 94%, Recall= 94% and F-measure= 94%). The effectiveness results obtain by this system was (Accuracy, Precision and Recall and F-measure).