User Model of Personalized Search Engine for Product Design Based on Machine Learning

2011 ◽  
Vol 460-461 ◽  
pp. 747-753
Author(s):  
Ying Shi Kang ◽  
Hai Ning Wang
Keyword(s):  
Machine Learning ◽  
Product Design ◽  
Search Engine ◽  
Interaction Design ◽  
Hot Spot ◽  
Rapid Development ◽  
Web Design ◽  
Internet Technology ◽  
Web Pages ◽  
Personalized Search

With the rapid development of internet technology, focusing on the product design of individual users, emphasizing the interaction design for Web and improving the user experience have become an inevitable trend of Web design, and also the hot spot of the design of personalized search engine. This paper proposed an optimized algorithm for building user models for product design websites. In order to show the design dimensions of Web pages presented by a browser, a concept of freshness is presented in this algorithm. By analyzing the user behavior of browsing Web pages, the model was updated using methods of machine learning. At last, the performance and effectiveness of this algorithm was analyzed and estimated through the simulation experiment.

Creative Drawings as Intuitive Probes for Evaluating Interface Preferences

2013 ◽  
Vol 311 ◽  
pp. 360-365
Author(s):  
Tsen Yao Chang
Keyword(s):  
Product Design ◽  
Interaction Design ◽  
Design Research ◽  
Web Design ◽  
User Participation ◽  
Emotional Reactions ◽  
Emotional Engagement ◽  
Web Interface ◽  
Visual Aesthetics ◽  
Usability Tests

Achieving a balance between visual aesthetics and usability to enhance user experience has enjoyed an increasing popularity in Web design. This study combines creative drawings as intuitive probes to investigate users’ emotional reactions and needs. The basic purpose of these creative exercises is to inspire design researchers and practitioners into applying a strategy in practicable design research to probe real user experiences and create an enjoyable and effective user environment. Emotional engagement with design is vital in design research. Unfortunately, laboratory usability tests often involve complex technical and mechanical tools that discourage user participation, thus limiting the opportunity to receive feedback. The research exercise in this study includes a series of intuitive practices that engaged the participants as target users to sketch an imagined garden layout, a library landscape layout, and a personal home page. We hypothesized from their drawings that a connection exists among the users’ sketches, Web interface preferences, and a classification of personality types. Significant results were obtained: (1) Creative drawing is an effective tool in understanding the personality of a user; (2) Three graphic practices establish emotional connections with the users’ Web interface preferences and product design; and (3) User personality categorization reveals preferences in Web interface and product design. This study focused on the effect of visual aesthetics and user-friendly methods on usability assessments in response to the increasing emotional conciliation of human-computer interaction design. These findings are beneficial in keeping abreast with the developments in design creativity and the qualitative contributions of design inspiration.

Design and Construction of Distributed JavaScript Parsing System

2014 ◽  
Vol 6 (4) ◽  
pp. 1-14
Author(s):  
Bo Shen ◽  
Wei Huang ◽  
Xiaodi Li
Keyword(s):  
Search Engine ◽  
Distributed System ◽  
Task Scheduling ◽  
Information Acquisition ◽  
Scheduling Algorithm ◽  
Rapid Development ◽  
Internet Technology ◽  
The Internet ◽  
Computing Technology ◽  
Task Scheduling Algorithm

With the rapid development of the Internet technology, JS (short for JavaScript), as one of the representative of script languages, which is very powerful, is becoming more and more popular to the developers and users. But JS programming is more complex than usual static technology. In the field of search engine and information acquisition, it's very difficult to get the information hidden in script code. In this paper, the authors design a distributed system for parsing the JS code embedded in HTML file and retrieving the underling information. the authors describe how to extract JS codes from HTML file and parse them. Also, they introduce a task scheduling algorithm for the JS parsing system by employing Hadoop distributed computing technology. The experimental results indicate that the proposed algorithm and system can achieve a reasonable task scheduling efficiency and parse JS codes rapidly.

Research and Implementation on Personalized Search Engine

2011 ◽  
Vol 467-469 ◽  
pp. 129-133 ◽  
Author(s):  
Qing Wei Zeng ◽  
Jie Jiang
Keyword(s):  
Information System ◽  
Search Engine ◽  
Search Engines ◽  
Rapid Development ◽  
User Feedback ◽  
Personalized Search ◽  
Feedback Information ◽  
General Search

With the rapid development of Internet, how to find useful information rapidly is becoming more and more important. General search engines somewhat satisfy users’ search needs. However, they do not consider users’ interests or background. Search engine will be more personal, intelligent and professional. It is necessary that personalized search engines come to reality. This paper designed and realized personalized search engines system by learning user feedback information. System can be able to optimize searching results and return the results that user is most interested in, also can tell users about other users’ interested modes, in order to make users share searching results with each other and improve the efficiency of searching.

Analysis on Prediction Results and Curve Fitting of Search Engine Based on Boolean Model

2014 ◽  
Vol 556-562 ◽  
pp. 3872-3876
Author(s):  
Xin Guo
Keyword(s):  
Search Engine ◽  
Moving Average ◽  
Rapid Development ◽  
Boolean Model ◽  
Internet Technology ◽  
Human Society ◽  
Search Engine Marketing ◽  
Marketing Mode ◽  
Autoregressive Moving Average Model ◽  
Vertical Search

Since twenty-first Century, internet technology has the rapid development, the human society entered the era of network economy. Suddenly rising e-commerce occupies half of the country's retail enterprises. How to improve the efficiency of commodity marketing under the environment of e-commerce is one of the hot problems in modern enterprises. In the paper we firstly present marketing strategy under the environment of e-commerce, analyze the basic principle of search engine marketing, analyze the relationship between basic principles under the search engine marketing framework. Combining with Boolean model, we put forward the vertical search engine oriented marketing model under e-commerce environment. In order to verify the practicability of the model based on fitting simulation of autoregressive moving average model, the results show that the marketing mode u is practical, and with scientific decision-making ability.

Improving the performance of precision poverty alleviation based on big data mining and machine learning

2020 ◽  
pp. 1-12
Author(s):  
Lejie Wang
Keyword(s):  
Machine Learning ◽  
Economic Growth ◽  
Big Data ◽  
Low Income ◽  
Large Scale ◽  
Rapid Development ◽  
Machine Learning Algorithms ◽  
Internet Technology ◽  
Rapid Economic Growth ◽  
Causes Of Poverty

Since the reform began in our country, with the rapid economic growth in recent years, the income level has grown extremely unequal, and it is difficult for the low-income poor to benefit from the rapid economic growth. The most important prerequisite for the fight against poverty is the accurate identification of the causes of poverty. To date, our country has not reached the level of maturity required to accurately study the causes of poverty in various households. However, with the rapid development of Internet technology and big data technology in recent years, the application of large-scale data technology and data extraction algorithms to poverty reduction can identify truly poor households faster and more accurately. Compared with traditional machine learning algorithms, there are no machine storage and technical constraints, can use a large amount of data and rely on multiple data samples.

scholarly journals Issues in adapting web content to be displayed on devices with various screen shapes using a JavaScript built screen shape simulator

2020 ◽  
Vol 4 (1) ◽  
Author(s):  
Tanja Krunić
Keyword(s):  
Rapid Development ◽  
Web Design ◽  
Smart Devices ◽  
Web Pages ◽  
Web Content ◽  
Outdoor Advertising ◽  
Web Standards ◽  
Testing Tool ◽  
Responsive Web Design ◽  
Indoor And Outdoor

This paper is devoted to an upcoming issue in web design: Styling web content to be displayed correctly on devices with various screen shapes. This issue is a consequence of the rapid development of LED displays with a wide variety of screen shapes. Many of them can be connected to a computer which means that one can display web content on them. Such displays are used as indoor and outdoor advertising panels, which makes them very important for business. Also, various smart devices are developing rapidly and they are often web browsing enabled. They come with various screen shapes, which is an imperative of modern design. Hence the need to style web pages in such a way that their content is displayed correctly on all those devices. By now, responsive web design has a solution only for styling web pages to be displayed on rectangular screens with various dimensions by using media queries and flexible grids. The W3C organization is currently working on media queries for round shaped displays, but all new suggested CSS rules are still in the working draft. It is obviously that the development of LED displays is running faster than the development of web standards. For these reasons, a responsive web design testing tool with a various screen shape simulator is built in JavaScript and is available on GitHub. Its main features are described herein. An example of styling a web site for various screen shapes using that testing tool is given in this paper in order to highlight the problems that arise during that process.

Retrieval of Web Pages on Real-World Events related to Physical Objects

2012 ◽  
Vol 2 (1) ◽  
pp. 65-80 ◽  
Author(s):  
Takeshi Okadome ◽  
Hajime Funai ◽  
Sho Ito ◽  
Junya Nakajima ◽  
Koh Kakusho
Keyword(s):  
Machine Learning ◽  
Search Engine ◽  
Real World ◽  
Machine Learning Techniques ◽  
Web Pages ◽  
Learning Techniques ◽  
Physical Objects

The method proposed in this paper searches for web pages using an event-related query consisting of a noun, verb, and genre term. It re-ranks web pages retrieved using a standard search engine on the basis of scores calculated from an expression consisting of weighted factors such as the frequency of query words. For the genres that are characterized by their genre terms, the method optimizes the weights of the expression. Furthermore, the method attempts to improve the scores provided of relevant pages by using machine learning techniques. In addition, some evaluations are provided to show the effectiveness of the method.

scholarly journals Using Machine Learning for Web Page Classification in Search Engine Optimization

2021 ◽  
Vol 13 (1) ◽  
pp. 9
Author(s):  
Goran Matošević ◽  
Jasminka Dobša ◽  
Dunja Mladenić
Keyword(s):  
Machine Learning ◽  
Search Engine ◽  
Search Engines ◽  
Machine Learning Algorithms ◽  
Practical Significance ◽  
Web Pages ◽  
Web Page ◽  
Data Set ◽  
Search Engine Optimization ◽  
Novel Approach

This paper presents a novel approach of using machine learning algorithms based on experts’ knowledge to classify web pages into three predefined classes according to the degree of content adjustment to the search engine optimization (SEO) recommendations. In this study, classifiers were built and trained to classify an unknown sample (web page) into one of the three predefined classes and to identify important factors that affect the degree of page adjustment. The data in the training set are manually labeled by domain experts. The experimental results show that machine learning can be used for predicting the degree of adjustment of web pages to the SEO recommendations—classifier accuracy ranges from 54.59% to 69.67%, which is higher than the baseline accuracy of classification of samples in the majority class (48.83%). Practical significance of the proposed approach is in providing the core for building software agents and expert systems to automatically detect web pages, or parts of web pages, that need improvement to comply with the SEO guidelines and, therefore, potentially gain higher rankings by search engines. Also, the results of this study contribute to the field of detecting optimal values of ranking factors that search engines use to rank web pages. Experiments in this paper suggest that important factors to be taken into consideration when preparing a web page are page title, meta description, H1 tag (heading), and body text—which is aligned with the findings of previous research. Another result of this research is a new data set of manually labeled web pages that can be used in further research.

scholarly journals MACHINE LEARNING BASED SEARCH ENGINE WITH CRAWLING, INDEXING AND RANKING

2021 ◽  
Vol 10 (7) ◽  
pp. 76-83
Author(s):  
Anuradha T ◽  
Tayyaba Nousheen
Keyword(s):  
Machine Learning ◽  
World Wide Web ◽  
Search Engine ◽  
Search Engines ◽  
World Wide ◽  
Accurate Result ◽  
Web Pages ◽  
The Web

The web is the heap and huge collection of wellspring of data. The Search Engine are used for retrieving the information from World Wide Web (WWW). Search Engines are helpful for searching user keywords and provide the accurate result in fraction of seconds. This paper proposed Machine Learning based search engine which will give more relevant user searches in the form of web pages. To display the user entered query search engine plays a major role of basic interface. Every site comprises of the heaps of site pages that are being made and sent on the server.

scholarly journals Machine Learning as a New Search Engine Interface: An Overview

2014 ◽  
Vol 2 (2) ◽  
pp. 103-112 ◽  
Author(s):  
Taposh Kumar Neogy ◽  
Harish Paruchuri
Keyword(s):  
Machine Learning ◽  
Search Engine ◽  
Search Engines ◽  
New World ◽  
Human Factor ◽  
Experimental Results ◽  
The Internet ◽  
Web Pages ◽  
Web Page ◽  
Real People

The essence of a web page is an inherently predisposed issue, one that is built on behaviors, interests, and intelligence. There are relatively a ton of reasons web pages are critical to the new world, as the matter cannot be overemphasized. The meteoric growth of the internet is one of the most potent factors making it hard for search engines to provide actionable results. With classified directories, search engines store web pages. To store these pages, some of the engines rely on the expertise of real people. Most of them are enabled and classified using automated means but the human factor is dominant in their success. From experimental results, we can deduce that the most effective and critical way to automate web pages for search engines is via the integration of machine learning.  

Sign in / Sign up

Export Citation Format

Share Document