Perform Three Data Mining Tasks with Crowdsourcing Process

For data mining studies, because of the complexity of doing feature selection process in tasks by hand, we need to send some of labeling to the workers with crowdsourcing activities. The process of outsourcing data mining tasks to users is often handled by software systems without enough knowledge of the age or geography of the users' residence. Uncertainty about the performance of virtual users in crowdsourcing reduces the accuracy of the received information. In this article, we propose to gather a number of people in a university and apply them for the small gathering tasks by using incentive methods. Increased accuracy in announcing results due to physical presence, high speed of obtaining high precision results at designated time, appropriate education of participants in the activity, and native implementation plan are characteristics of this study. In this study, three classifications are used to classify word embedding as well as the process of motivation to provide standard data by the crowd source. In the first task we use convolutional neural network, for doing classification in six classes: USAGE, TOPIC, COMPARE, MODEL-FEATURE, RESULT and PART-WHOLE. This article extracts the data from the abstract of 400 scientific articles and it is a total of 835 relations. One hundred of these abstracts have been selected by the crowdsourcing. Classification results in this article have been done with a slight improvement in accuracy. In the second task, classification is done by crowdsourcing on the result of a combine word embedding system. Glove and Word2vec are two of the most popular word embedding algorithms. These two algorithms have been used separately in different machine learning applications. In ad innovation was created word embedding with using a combination of glove and word2vec. In this study, we computed the classification results on a combination of vocabulary vectors with using of 450 abstract relation data (100 crowd source datasets with 350 standards). The results of the implementation of the classification algorithm give us performance improvement. The third task was to completing the process of installing the mobile applications. One of the problems with data mining is the lack of standard data. The high cost of data preparation on the one hand and the lack of a suitable population for specialized tasks have led to the design of software for doing these processes. But these methods have no incentive to install the software and often fail due to the lack of crowd workers or more precisely, lack of specialist workers. In another process, we have installed the app into this collection of specialist science people. This smart population has reduced costs and time for doing data mining processes in the future. People can make the move towards the regulation of social activity at a given time and place by the capacity created by ICT to work on a large scale. Creating a social campaign will benefit users on mobile social networks. Scientists can benefit from the capacity created by crowdsourcing in ICT and make movement to regularize social activities at specific time and place. Creating social campaign will help to form new society. The smart population created in this article was an innovation or startup in the field of event organizing that used the attention of people to the day issues as well as the importance of watching competition. This paper uses the population power to perform preparing data mining works.