Search results

Over the past few years, e‐commerce has become increasingly popular in China. Recent research has shown that it is widely accepted that customer satisfaction and loyalty for online purchases is lower than that for shopping in more traditional ways. How to maintain and increase the satisfaction and loyalty of online customers is a challenging issue for online retailers. The purpose of this paper is to try to understand what affects customer satisfaction and loyalty.

A new conceptual model of customer satisfaction and loyalty in online purchases is developed, where four dimensions of e‐service quality – efficiency, requirement fulfillment, system accessibility, and privacy – are the four predictors from Parasuraman's E‐S‐QUAL. A partial least square estimation algorithm was then applied to analyze data from a sample of 164 online buyers from a range of backgrounds. Goods purchased include furniture, books, clothes, software, and digital products.

The results indicate that efficiency and fulfillment have positive effects on customer satisfaction, and fulfillment and privacy have positive effects on customer loyalty. However, the remaining factors have no significant effect on either customer satisfaction or customer loyalty. In addition, customer loyalty is positively affected by customer satisfaction.

The paper finds that the service quality must be analyzed from different aspects only to find that the requirement fulfillment has relatively great effect on customers' satisfaction and loyalty, the system accessibility has no effect on both, the efficiency has positive effect on customers' satisfaction and the privacy has positive effect on customers' loyalty. As these results are inconsistent with previous research achievements to some extent, this paper tends to provide some explanation.

Problem-solving” is the most crucial key insight of scientific research. This study focuses on constructing the “problem-solving” knowledge graph of scientific domains by extracting four entity relation types: problem-solving, problem hierarchy, solution hierarchy and association.

This paper presents a low-cost method for identifying these relationships in scientific papers based on word analogy. The problem-solving and hierarchical relations are represented as offset vectors of the head and tail entities and then classified by referencing a small set of predefined entity relations.

This paper presents an experiment with artificial intelligence papers from the Web of Science and achieved good performance. The F1 scores of entity relation types problem hierarchy, problem-solving and solution hierarchy, which were 0.823, 0.815 and 0.748, respectively. This paper used computer vision as an example to demonstrate the application of the extracted relations in constructing domain knowledge graphs and revealing historical research trends.

This paper uses an approach that is highly efficient and has a good generalization ability. Instead of relying on a large-scale manually annotated corpus, it only requires a small set of entity relations that can be easily extracted from external knowledge resources.