User Requirements Analysis Based On Text Data Mining Technology

With the rapid development of mobile Internet technology,the wide application of E-commerce and the popularity of intelligent mobile equipment and so on,a large amount of data are produced in the Internet every day.Meanwhile,these data involve a mess of unstructured data,such as text data and multimedia data,etc.However,how to acquire potential and valuable information by making full use of unstructured data analysis is the problem demanding prompt solution.First and foremost,this paper started with the theory of user requirements analysis,analyzing source of user requirements and its five characteristics which consist of dynamics,complexity,hiding property,affective reaction and fuzzification.It combined cyber-expressions of user requirements and characteristics of text mining technology,thus discovering several advantages of text mining technology in the field of user requirements analysis,which included reliability,rapidity,low cost,durative and real-time.Based on specific process of text mining,namely,data acquisition,data processing and data visualization,it also put forward that user requirements analysis can be divided into requirements acquisition,requirements identification and requirements expression,thus reaching hierarchical structure model of user requirements analysis.Then with cooperation and studies of text mining technology as well as hierarchical structure mode of user requirements analysis,it considered that the acquisition of user requirements information facing online comments could be realized by crawler technology,and super vector machine and keyword extraction could be better used to identify and express user requirements information,thus put forward double-spiral structure of user requirements analysis.Last but not least,this paper recounts the specific flow of user requirements analysis based on text mining technology from an empirical analysis of HUAWEI Mate9.