dharani devi

In an organization, employees are the major and important resources and may quit the job unpredictably which may produce immense cost. In general, the employee attitude and their effort are influenced by their personality traits but the job satisfaction may result for an individual observations from an organization based on the environment conditions. Meanwhile, the hiring of new employee may consume time and cost. Similarly, recently hired employee may need to put certain efforts for being productive. The job satisfaction of the employee is one of the factor for leaving out from the organization. The employee attrition prediction and its reasons to leave the organization required to be performed from Human Resource Management (HRM) perspective. This kind of prediction has to be progressed from HRM for analyzing the best and experienced employee's reason for leaving their organization using various data mining technique but the exact prediction is not obtained. This can be analyzed by seeing some experienced and best employee leaving their organization. Therefore, this paper has attempted for developing an ensemble model which assist in providing an accurate prediction of the employee attrition based on the HR analytics dataset. The proposed research work focus in analyzing the job satisfaction mentioned by the employee in the “Employee Attrition” has been considered by predicting the dataset using Weighed Average Mechanism (WAM) in ensemble method with Logistic Regression (LR). Moreover, the performance evaluation of proposed ensemble method attaints the higher accuracy of 98.2% which outperforms the other three existing methods for analyzing the better prediction of job satisfaction from the employees.

In an organization, employees are the major and important resources and may quit the job unpredictably which may produce immense cost. In general, the employee attitude and their effort are influenced by their personality traits but the job satisfaction may result for an individual observations from an organization based on the environment conditions. Meanwhile, the hiring of new employee may consume time and cost. Similarly, recently hired employee may need to put certain efforts for being productive. The job satisfaction of the employee is one of the factor for leaving out from the organization. The employee attrition prediction and its reasons to leave the organization required to be performed from Human Resource Management (HRM) perspective. This kind of prediction has to be progressed from HRM for analyzing the best and experienced employee's reason for leaving their organization using various data mining technique but the exact prediction is not obtained. This can be analyzed by seeing some experienced and best employee leaving their organization. Therefore, this paper has attempted for developing an ensemble model which assist in providing an accurate prediction of the employee attrition based on the HR analytics dataset. The proposed research work focus in analyzing the job satisfaction mentioned by the employee in the “Employee Attrition” has been considered by predicting the dataset using Weighed Average Mechanism (WAM) in ensemble method with Logistic Regression (LR). Moreover, the performance evaluation of proposed ensemble method attaints the higher accuracy of 98.2% which outperforms the other three existing methods for analyzing the better prediction of job satisfaction from the employees.

The Users store vast amounts of sensitive data on a big data and cloud platform. Sharing sensitive data will help enterprises reduce the cost of providing users with personalized services and provide value-added data services. However, secure data sharing is problematic. This paper proposes a framework for secure sensitive data sharing on a big data platform, including secure data delivery, storage, usage, and destruction on a semi-trusted big data sharing platform. We present a proxy re-encryption algorithm based on heterogeneous ciphertext transformation and a user process protection method based on a virtual machine monitor, Twofish and Blowfish which provides support for the realization of system functions. The framework protects the security of users' sensitive data effectively and shares these data safely. At the same time, data owners retain complete control of their own data in a sound environment for modern Internet information security.

Sentiment Analysis (SA) or opinion mining (OM) has recently become the focus of many researchers, beca us analysis of online text is beneficial and demanded for market research , scientific surveys from psychological and sociolo gical perspective, political polls, business intelligence, enhancement of online shopping infrastructures, etc. Nowadays if one wan ts to buy a consumer product one prefer user reviews and discussion in p ublic forums on web about the product. As a result opinion mining has gained importance. This online word-of-mouth represents ne w and measurable source of information with many ap plications, this process of identifying and extracting subjective informatio n from raw data is known as sentiment analysis. Thi s paper presents a survey on sentiment analysis or opinion mining.