The professional web sites design helps attracting and navigating the Internet shopper efficiently . Moreover, it is a key success for modern business in the decade such as Amazon.com. Although there are various influencing factors for the professional web design such as graphic, image, color and layout , , we only focus on visual layout and presentation in this paper.
Good visual layout and presentation are two important factors which help attracting the Internet shoppers to browse the products and perhaps make some purchases on e-commerce web sites.
Traditionally, web design depends on manual investigation by human. Each web design depends on their experience and individual style. We cannot focus on unity style easily. Besides, this clue, very few researches have been proposed to investigate good e-commerce web site design and make comparison with the other automatically. We are encountering with limitation of web site design improvement if we have to rely on the human judgment. We consider page segmentation ,  which can analyze the web site design, but most research has been studied on product extraction .
In this paper, we propose a method for analyzing page layout for assessing e-commerce web-site design. In order to discover the influencing factors, we need to divide the web page into individual blocks. Firstly, we divide each page into five blocks: top, bottom, left, right and center respectively. Secondly, we identify each e-commerce block to locate features such as navigation, product index and customer service.
Finally, we consider e-commerce format and navigation menu style such as highlight, popup, text modification, row, and column appearance. In addition, we also consider the image alignment layout and text density. Then, we extract features to present the blocks and manually label their functions. After this preprocessing step, we need to label our data set according to block feature so that it can be used as the training set for classification algorithm. The accuracy result from the model will be used for our evaluation. We can select the appropriate model for implementing our system in the future. We attempt to find the most influencing factors among spatial, location and presentation feature sets through our experimental study.
Our contributions in this paper include:
1) to discover the significant features based on visual and presentation factors, which influence the e-commerce web design,
2) to propose a framework for accessing the web page visual layout, and
3) to perform empirical verification and effectiveness of visual and presentation features.