An Unsupervised Approach for Customer Need Assessment in E-commerce: A Case Study of Japanese Customer Reviews

2021 ◽  
Author(s):  
Mate Kovacs ◽  
Daniil Buryakov ◽  
Victor Kryssanov
2020 ◽  
Vol 12 (3) ◽  
pp. 9
Author(s):  
Kinga Szabó ◽  
Gauri Shankar Gupta

Rapid growth of sharing economy in the last two decades is the outcome of a paradigm shift in global capitalism and societal values. Based on digital identity and the Trust and Reputation Index, IT platforms have brought together strangers who under new social construct, share under-utilized capacities and assets with those who need them. Radius of trust which was initially confined to family and friends; now encompasses strangers who speak no common language and who live oceans apart. Hungary is no exception to this global shift. Sharing economy in Hungary has registered healthy growth specially in the areas of transportation and accommodation. Oszkár, a long-distance car-sharing company presents a good example of this paradigm shift in societal values and sharing with strangers. This platform has recorded impressive growth of over 67% between 2015-2018 with very positive customer reviews. Moreover, this represents an environmentally-friendly sustainable practice which successfully reduces carbon foot-print and traffic congestion.


Author(s):  
Rogaina Rogaina ◽  
Tikawati Tikawati

This study aims to examine and analyse the effect of ease of shopping, online customer reviews and perceptions of maslahah on online shopping decisions among UINSI and UMKT Samarinda students. The type of research used is field research. The sample in this study was 198 people who had shopped online. The method of collecting data is a questionnaire is distributed online using Google form. Data analysis used multiple regression analysis. The results showed that of the three variables of ease of shopping, online customer review and perception of maslahah simultaneously affect online shopping decisions. From the calculation of SPSS 23. For the Ftest, it is known that Fcount = 187.146 > Ftable 2.65 with a significance of 0.000 < 0.5. Partially, it is known that the ease of shopping, online customer reviews and the perception of maslahah have a significant effect of online shopping decisions. In addition to the Ftest and t-test, the R2 test is known to have an R square value of 0.743 which means the magnitude of the independent variable 74.3%.


2021 ◽  
Vol 10 (9) ◽  
pp. 318
Author(s):  
Jennifer Johnson Jorgensen ◽  
Katelyn Sorensen

Consumers have been advocating for a variety of causes, and in turn, retailers are expressing their political opinions through social-media posts in hopes of aligning with their customers’ views. This study looks at a single case in which customers reacted to a retailer’s political opinion posted on a social media account. Data was collected at the time of the retailer’s political post and up to three years afterward. Content analysis was employed to identify themes from the customer reviews posted, and four themes were identified. Of significance, this study found that customers of a retail store typically merge feelings on the retailer’s product and political post or the retailer’s service and the political post within their social media responses. Thus, a majority of customers in this case were not exclusively focused on battling the political post on social media. Also, a shift in customers’ opinions of the retailer shifted positively over time.


2020 ◽  
pp. 1-10
Author(s):  
Junegak Joung ◽  
Harrison M. Kim

Abstract Identifying product attributes from the perspective of a customer is essential to measure the satisfaction, importance, and Kano category of each product attribute for product design. This paper proposes automated keyword filtering to identify product attributes from online customer reviews based on latent Dirichlet allocation. The preprocessing for latent Dirichlet allocation is important because it affects the results of topic modeling; however, previous research performed latent Dirichlet allocation either without removing noise keywords or by manually eliminating them. The proposed method improves the preprocessing for latent Dirichlet allocation by conducting automated filtering to remove the noise keywords that are not related to the product. A case study of Android smartphones is performed to validate the proposed method. The performance of the latent Dirichlet allocation by the proposed method is compared to that of a previous method, and according to the latent Dirichlet allocation results, the former exhibits a higher performance than the latter.


CONVERTER ◽  
2021 ◽  
pp. 382-392
Author(s):  
Hang Liu, Zan Ren, Yingjie Li

With the development and popularization of smart products, the technological differences of products are decreasing, and the phenomenon of product homogeneity is becoming more and more obvious. It is necessary for the smart product manufacturing firms have the capability to analyze customer requirement deeply and adapt to the dynamically changing market quickly. Therefore, the traditional technology-oriented product development model is no longer suitable for manufacturers to obtain a competitive advantage. Based on this, this paper proposed a method to evaluate the importance of customer demands based on online comments and quantitative Kano model. First, the Python crawler tool is used to obtain online customer reviews of relevant products and the word segmentation processing is performed to obtain the product features and frequency that customers are mainly concerned about, and then the initial importance of demand can be calculated. Furthermore, use the quantitative Kano model to determine the customer satisfaction and revise the initial importance of the requirements to obtain a more reasonable ranking of the importance of user needs. Finally, a case study is carried out with the smart bracelet as an example to verify the effectiveness and feasibility of the model proposed in this paper.


Sign in / Sign up

Export Citation Format

Share Document