Search

Copyright of Application Research of Computers / Jisuanji Yingyong Yanjiu is the property of Application Research of Computers Edition and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Application Research of Computers / Jisuanji Yingyong Yanjiu is the property of Application Research of Computers Edition and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Consumers’ online shopping reviews are consumers’ feedback to online shopping. Mining valuable knowledge from massive online shopping reviews will not only provide safeguard for businesses to carry out precision marketing and personalized recommendation services, but also is good for consumers to make purchase decisions. Besides, management departments can use it to establish regulatory strategy. This paper reviewed the clothing online shopping comments on China’s large integrated electronic business platform as the object of study, making a participle of the comments, screening high frequency words, analyzing of co-occurrence relationship between the high frequency words in order to structure co-occurrence network of high frequency word. The analysis result shows a number of structural features for the network comments hot words and a few nodes in the comment network play a dominant role in the operation of the network. On the other hand, this paper also provides the study suggestion on the interaction effects of the structure characteristics for the high frequency word co-occurrence network on the sales volume. [ABSTRACT FROM AUTHOR]

Copyright of Application Research of Computers / Jisuanji Yingyong Yanjiu is the property of Application Research of Computers Edition and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Retailers are facing with a variety of product information, how to help retailers access to effective commodity sales strategy effectively and accurately is an urgent problem. Based on complex network theory, this paper constructed a complex weighted network model of retail product association. Beginning with the relationship of retail product purchase in the consumer purchase record, retail products wrere nodes and the relationship of different product purchase wrere directed edge, and product sales volume wrere weights. And then, it calculated the node strength. Finally, it used the sales bill data from the K-commerce sites and supermarket to verify the algorithm. This study provided a reference basis for bundling sales, discount promotions and display layout strategies for E-commerce websites or large retailers. [ABSTRACT FROM AUTHOR]

The traditional CF algorithm has the problem of cold start,data sparseness and low operation efficiency. This paper chose Slope One algorithm which was more efficient and accurate than traditional CF algorithm for research and analyses its advantages ,principle and process. It pointed out shortcomings of Slope one algorithm that it did not take user interest changes and user similarity into account. This paper put forward improved scheme of Slope one algorithm based on user interest forgetting function and user nearest neighbors. The experimental test on MovieLens dataset proves the feasibility and better time performance of improved scheme. [ABSTRACT FROM AUTHOR]