Experimental Study Of Feature Weighting Techniques For URL Based Webpage Classification

Rajalakshmi, R.; Xaviar, Sanju

doi:10.1016/j.procs.2017.09.128

Cited by 15 publications

(5 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Rajalakshmi and Xavier [1] described Web page classification using URL based features. They have used classification steps namely preprocessing, feature weighting methods (n-Gram, Term Frequency and Mutual Information), training (70%) and testing samples (30%) of WebKB dataset.…”

Section: Literature Overviewmentioning

confidence: 99%

Research of Novel Web Page Classifiers and Feature Selection Methods

2019

IJITEE

View full text Add to dashboard Cite

The World revolves around the web technology at present. Every year, the Web information are exponentially growing and this information are huge and complex. The web users are difficult to classify and extract useful information from the web, because the Webinformation are noisy, redundant and irrelevant and also misclassified.Many researchers don’t have strongknowledge about the process of web page classification, techniques and methods previously used. The objective of this survey is to convey an outline of the modern techniques of Web page classification. In this survey, the recent papers in this area are selected and explored.Thus this study will help the researchers to obtain the required knowledge about the current trends in web page classification

show abstract

Section: Literature Overviewmentioning

confidence: 99%

Research of Novel Web Page Classifiers and Feature Selection Methods

2019

IJITEE

View full text Add to dashboard Cite

show abstract

“…Using statistically relevant tokens as features, we classified the URLs in a multiclass scenario. The number of token features present in each statistical dictionary SDC k for all 13 Naive Bayes algorithm, the exact token matches with the SDC k are assigned with the term goodness of the corresponding tokens as the weights ignoring the partial matches. Table 5 shows the results of this experiment.…”

Section: Experiments To Ascertain the Importance Of Feature Selectionmentioning

confidence: 99%

“…Some URLs may not contain any related information about a web page, and hence pose more challenges for classification (eg, http://www.clker.com/). URL classification problem has been studied by various researchers, [6][7][8][9][10][11][12][13][14][15] and various methods have been suggested in the literature. The issues in these existing methods are discussed below.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Naive Bayes approach for URL classification with supervised feature selection and rejection framework

Rajalakshmi

Aravindan²

2018

Computational Intelligence

Self Cite

View full text Add to dashboard Cite

Web page classification has become a challenging task due to the exponential growth of the World Wide Web. Uniform Resource Locator (URL)‐based web page classification systems play an important role, but high accuracy may not be achievable as URL contains minimal information. Nevertheless, URL‐based classifiers along with rejection framework can be used as a first‐level filter in a multistage classifier, and a costlier feature extraction from contents may be done in later stages. However, noisy and irrelevant features present in URL demand feature selection methods for URL classification. Therefore, we propose a supervised feature selection method by which relevant URL features are identified using statistical methods. We propose a new feature weighting method for a Naive Bayes classifier by embedding the term goodness obtained from the feature selection method. We also propose a rejection framework to the Naive Bayes classifier by using posterior probability for determining the confidence score. The proposed method is evaluated on the Open Directory Project and WebKB data sets. Experimental results show that our method can be an effective first‐level filter. McNemar tests confirm that our approach significantly improves the performance.

show abstract

“…Zhao et al [9] used the Naive Bayes algorithm and SVM to classify RESTful services by extracting features from web page content and document structure information. Rajalakshmi and Xaviar [16] conducted an experimental study on URL-based web page classification feature-weighting techniques and used SVM to perform web page classification. Altay et al [17] used context-sensitive and keyword density to extract features and used SVM, maximum entropy, and Extreme learning machine for malicious web page detection.…”

Section: Related Workmentioning

confidence: 99%

Feature Selection and Recognition Methods for Discovering Physiological and Bioinformatics RESTful Services

et al. 2018

View full text Add to dashboard Cite

Many physiology and bioinformatics research institutions and websites have opened their own data analysis services and other related Web services. It is therefore very important to be able to quickly and effectively select and extract features from the Web service pages to learn about and use these services. This facilitates the automatic discovery and recognition of Representational State Transfer or RESTful services. However, this task is still challenging. Following the description feature pattern of a RESTful service, the authors proposed a Feature Pattern Search and Replace (FPSR) method. First, they applied a regular expression to perform a matching lookup. Then, a custom string was used to substitute the relevant feature pattern to avoid the segmentation of its feature pattern and the loss of its feature information during the segmentation process. Experimental results showed in the visualization that FPSR obtained a clearer and more obvious boundary with fewer overlaps than the test without using FPSR, thereby enabling a higher accuracy rate. Therefore, FPSR allowed the authors to extract RESTful service page feature information and achieve better classification results.

show abstract

Experimental Study Of Feature Weighting Techniques For URL Based Webpage Classification

Cited by 15 publications

References 13 publications

Research of Novel Web Page Classifiers and Feature Selection Methods

Research of Novel Web Page Classifiers and Feature Selection Methods

A Naive Bayes approach for URL classification with supervised feature selection and rejection framework

Feature Selection and Recognition Methods for Discovering Physiological and Bioinformatics RESTful Services

Contact Info

Product

Resources

About