Comprehensive Literature Review on Machine Learning Structures for Web Spam Classification

Goh, Kwang Leng; Singh, Ashutosh Kumar

doi:10.1016/j.procs.2015.10.069

Cited by 39 publications

(22 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The application fields of machine learning (Azqueta-Gavaldón, 2017; Barzegar et al., 2017; Castiglioni et al., 2018; Chalouhi et al, 2017; Goh and Singh, 2015; Karim et al., 2018; Kim et al., 2017; Lázaro et al., 2017; Lee et al., 2017; Pham et al., 2016; Samant and Agarwal, 2018; Sattlecker et al., 2014; Shirzadi et al., 2017; Zeng et al.,2018b; Zhang et al.,2018a).…”

Section: Machine Learning Methodsmentioning

confidence: 99%

Accuracy analyses and model comparison of machine learning adopted in building energy consumption prediction

Liu

et al. 2019

Energy Exploration & Exploitation

110

View full text Add to dashboard Cite

It is of great significance to achieve the prediction of building energy consumption. However, machine learning, as a promising technique for many practical applications, was rarely utilized in this field. The most important reason is that the predictive structure with best performance is difficult to be determined. To fill the gap, this paper offers one in-depth review, which focuses on the accuracy analyses and model comparisons. Specifically, the accuracy analyses were conducted based on different types of buildings (e.g. residential building, commercial building, government building or educational building), different type of temporal granularity (e.g. sub-hourly, hourly, daily or annual), as well as input/output variables and historical data collections. Further, artificial neural network (ANN) and support vector machine (SVM), as the epidemic models, were compared in terms of their complexity of prediction processes, accuracies of results, the amounts of required historical data, the numbers of inputs, etc. Then the hybrid and single machine learning methods were outlined and compared in terms of their strengths and weaknesses. In addition, several vital defects and further research directions are presented from a multivariate perspective. We hope

show abstract

Section: Machine Learning Methodsmentioning

confidence: 99%

Accuracy analyses and model comparison of machine learning adopted in building energy consumption prediction

Liu

et al. 2019

Energy Exploration & Exploitation

110

View full text Add to dashboard Cite

show abstract

“…We started by reviewing of the existing systematic literature [10]; [12]; [11]; [71]; [69]; [26]; we concentrated on developing a protocol for a systematic mapping study that has addressed questions that are related to the spam detection framework on 3 different social networks platform [77], [76], [2][8] [9]. In the following sections, we will detail each process that we use.…”

Section: Research Methods 31 Protocol Developmentmentioning

confidence: 99%

“…Problem of effective, efficiency and accuracy in spam detection on social networks and email generally, they try to provide survey and algorithms method to solve the problem pose by the threat. In 2015, it was estimated that approximately one seventh of English web pages were spam [10], one consultancy estimated that Russian Spammers earned roughly US$2-3 million per year.…”

Section: Introductionmentioning

confidence: 99%

A Mapping Study to Investigate Spam Detection on Social Networks

Kamoru¹,

Jaafar²,

Murad³

2017

IJAIS

View full text Add to dashboard Cite

Social networks such as Facebook, Twitter and SinaWeibo have become increasingly important for reaching millions of user globally. Consequently, spammers are increasing using such networks for propagating spam. Existing research on filtering techniques such as collaborative filters and behavioral analysis filters are able to significantly reduce spam. In recent years, online social networks have become the most important medium of communication among individual and organization to interact. Unfortunately, driven by the desire to communicate, fraudster or spammers have produced deceptive spam or unsolicited commercial email(UCE). The fraudsters' or spammer activities mislead potential users and victims reshaping their individual life and general communication on social network platform.The aim of this study is to understand, classify and analyze existing research in spam detection on social networks, focusing on approaches and elements that are used to evaluate the general framework of spam detection and its architectural framework from the users perspective, service provider and security analyst 's point of view. This paper presents a systematic mapping study of several spam detection techniques and approaches on social networks that were proposed to measure to evaluate the general framework of spam detection on social networks. We found 17 proposals that could be applied to evaluate spam detection on social networks, while 14 proposals could be applied to evaluate the users, service providers and practitioners. Various elements of spam detection on social networks that were measured are reviewed and discussed. Only a few of the proposed spam detection on social networks are soundly defined. The quality assessment of the primary studies detected many limitations and suggested guidelines for possibilities for improving and increasing the acceptance of spam detection on social networks. However, it remains a challenge to characterize and evaluate a spam detection and framework on social networks quantitatively. For this fact, much effort must be made to achieve a better spam detection approach in the future that will be devoid of problem anomaly detection, fault detection, malware detection and intrusion detection General Terms

show abstract

“…This situation has motivated a growing interest of the research community for (i) studying this novel form of web spam, mainly related with the occurrence of the Web 2.0; (ii) the proposal of novel and more accurate algorithms and techniques for its effective detection and; (iii) the analysis of new challenges imposed to the existing information retrieval systems. In this context, several research works show how web spam usually appears in sophisticated forms using several tricks to mislead search engines for assigning higher ranks to fake sites [ 16 , 17 , 18 , 19 , 20 , 21 ]. Complementarily, different works show how to assess the problem of spam in social web sites developing specific solutions [ 9 , 22 , 23 , 24 , 25 , 26 ].…”

Section: Introductionmentioning

confidence: 99%

“…In any case, the detection of spam on the web has been mainly addressed as a classification problem (i.e., spam vs. legitimate content) [ 21 ]. Although every approach has its own characteristics and limitations, all of them require the availability, management and use of large amount of electronic collections of previously classified web sites (known as corpora) to correctly train and evaluate the proposed approaches.…”

Section: Introductionmentioning

confidence: 99%

WARCProcessor: An Integrative Tool for Building and Management of Web Spam Corpora

Callón

Fdez-Glez²,

Ruano-Ordás

et al. 2017

Sensors

View full text Add to dashboard Cite

In this work we present the design and implementation of WARCProcessor, a novel multiplatform integrative tool aimed to build scientific datasets to facilitate experimentation in web spam research. The developed application allows the user to specify multiple criteria that change the way in which new corpora are generated whilst reducing the number of repetitive and error prone tasks related with existing corpus maintenance. For this goal, WARCProcessor supports up to six commonly used data sources for web spam research, being able to store output corpus in standard WARC format together with complementary metadata files. Additionally, the application facilitates the automatic and concurrent download of web sites from Internet, giving the possibility of configuring the deep of the links to be followed as well as the behaviour when redirected URLs appear. WARCProcessor supports both an interactive GUI interface and a command line utility for being executed in background.

show abstract

Comprehensive Literature Review on Machine Learning Structures for Web Spam Classification

Cited by 39 publications

References 27 publications

Accuracy analyses and model comparison of machine learning adopted in building energy consumption prediction

Accuracy analyses and model comparison of machine learning adopted in building energy consumption prediction

A Mapping Study to Investigate Spam Detection on Social Networks

WARCProcessor: An Integrative Tool for Building and Management of Web Spam Corpora

Contact Info

Product

Resources

About