期刊名称：International Journal of Innovative Research in Computer and Communication Engineering
印刷版ISSN：2320-9798
电子版ISSN：2320-9801
出版年度：2017
卷号：5
期号：4
页码：7550
DOI：10.15680/IJIRCCE.2017.05040186
出版社：S&S Publications
摘要：Classification is a data mining technique in which the various kinds of data are classified into the predefinedcategories. In this paper, we attempt to devise techniques to classify the users news feeds or posts taken fromFacebook, into various categories using Naive Bayes classification algorithm. The posts are classified into fivedifferent categories. After the classification of posts into one of the specified categories sentiments of the posts is to beidentified and categorized. Sentiment Analysis is done on the classified post to determine the opinion of that post. Heresentiments of the post are identified and classified into positive, negative or neutral category. For this purpose, SupportVector Machine(SVM) algorithm is used.In the next part a way to implement Facebook Watchdog application, which aims to detect the explicit images and toavoid them from being uploaded on the server, is given. Explicit images are detected using an Adult Image DetectionAlgorithm.
关键词：Facebook news feed; Text classification; Sentiment analysis; Watchdog;Naive Bayes; SVM
