With the rapid development of the World Wide Web, electronic word-of-mouth interaction has made consumers active participants. Nowadays, a large number of reviews posted by the consumers on the Web provide valuable information to other consumers. Such information is highly essential for decision making and hence popular among the internet users. This information is very valuable not only for prospective consumers to make decisions but also for businesses in predicting the success and sustainability. In this paper, a Gini Index based feature selection method with Support Vector Machine (SVM) classifier is proposed for sentiment classification for large movie review data set. The results show that our Gini Index method has better classification performance in terms of reduced error rate and accuracy.
The web has become an indispensable global platform that glues together daily communication, sharing, trading, collaboration and service delivery. Web users often store and manage critical information that attracts cybercriminals who misuse the web and the internet to exploit vulnerabilities for illegitimate benefits. Malicious web pages are transpiring threatening issue over the internet because of the notoriety and their capability to influence. Detecting and analyzing them is very costly because of their qualities and intricacies. The complexities of attacks are increasing day by day because the attackers are using blended approaches of various existing attacking techniques. In this paper, a model DeMalFier (Detection of Malicious Web Pages using an Effective ClassiFier) has been developed to apply supervised learning approaches to identify malicious web pages relevant to malware distribution, phishing, drive-by-download and injection by extracting the content of web pages, URL-based features and features based on host information. Experimental evaluation of DeMalFier model achieved 99.90/0 accuracy recommending the impact of our approach for real-life deployment.
Nowadays, enormous reviews are posted online by the consumers which provide related and required knowledge to the similar consumers. Such information is very much crucial for decision making and hence trendy among the web users. This information is very essential not only for potential consumers to make decisions but also for forecasting success and sustainability in commercial businesses. Online reviews on medicinal drugs are important for patients, medical representatives and medical industries. Reviewing medicinal drugs is challenging as sentiment analysis provides very little opportunity to discuss it. Collecting the reviews for uterine fibroid medicines from websites and analysing is a challenging process. An efficient Uterine Fibroid Medicinal Drugs Review Analysis (UFMDRA) model is developed with a decision tree algorithm which is trained and tested for different split ratios to obtain 100% accuracy. Experimental analysis results show that the proposed model has better classification performance in terms of accuracy compared to other classifiers.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.