New versions of PageRank employing alternative Web document models

Thelwall, Mike; Vaughan, Liwen

doi:10.1108/00012530410516840

Cited by 7 publications

(3 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, given the lack of a universal best choice of ADM, another option would be to use several. Thelwall and Vaughan (2004) introduced several new versions of the PageRank algorithm using ADMs, but with inconclusive results. The new approach seemed to work well for sets, which included pages from other web sites but did not work well in ranking pages from the same site.…”

Section: Discussionmentioning

confidence: 99%

A longitudinal analysis of alternative document models

Payne

Thelwall

2009

Aslib Proceedings

Self Cite

View full text Add to dashboard Cite

PurposeAlternative document models (ADMs) were created with the purpose of reducing the extent to which anomalies occur in counts of web links at the page level, and have been used extensively within webometrics as an alternative to using the web page as the basic unit of analysis. This paper seels tp carry out a longitudinal study of ADMs in an attempt to ascertain which model gives the most consistent results when applied to the UK, Australia and New Zealand academic web spaces over the last six years.Design/methodology/approachInformation science software (SocSciBot Tools, socscibot.wlv.ac.uk) was used to process hyperlink structure text files for UK, Australian and New Zealand universities and produced standard Page, Directory, Domain and Site ADMs using both inlinks and outlinks. Spearman bivariate correlation analysis was then undertaken to determine the level of correlation between these eight ADMs and a measure of site size for each university.FindingsThe findings show that the Domain ADM gives the most consistent results. However, the Directory ADM also gives more reliable results than are evident when using the standard Page model. Aggregating at the site (or university) level appears to provide less reliable results than using the page as the standard unit of measure, and this finding holds true over all three academic webs and for each time period examined over the last six years.Research limitations/implicationsThe use of Spearman's correlation coefficient is considered to be unreliable when used with very small sample sizes and, with only eight universities, the New Zealand academic web space may not be sufficiently large to give truly accurate statistical results.Originality/valueWhile previous specific studies have shown that more accurate results can be obtained through the use of the Domain or Directory ADM, the paper has shown that these results are consistent over time and across different countries' academic web spaces.

show abstract

Section: Discussionmentioning

confidence: 99%

A longitudinal analysis of alternative document models

Payne

Thelwall

2009

Aslib Proceedings

Self Cite

View full text Add to dashboard Cite

show abstract

“…PageRank is founded on the concepts used in academic citation analysis research, but extends the idea for the internet by “not counting links from all pages equally and normalizing the number of links on a page” (Brin & Page, 1998). PageRank has been used to assess importance in a variety of settings, such as academic (Kothainayaki & Gopalakrishnan, ; Thelwall & Vaughan, ). When we started the study in 2015, PageRank data were publicly available through Google Toolbar.…”

Section: Literature Reviewmentioning

confidence: 99%

A webometric analysis of the online vaccination debate

Ninkov

Vaughan

2017

Asso for Info Science & Tech

Self Cite

View full text Add to dashboard Cite

Webometrics research methods can be effectively used to measure and analyze information on the web. One topic discussed vehemently online that could benefit from this type of analysis is vaccines. We carried out a study analyzing the web presence of both sides of this debate. We collected a variety of webometric data and analyzed the data both quantitatively and qualitatively. The study found far more anti‐ than pro‐vaccine web domains. The anti and pro sides had similar web visibility as measured by the number of links coming from general websites and Tweets. However, the links to the pro domains were of higher quality measured by PageRank scores. The result from the qualitative content analysis confirmed this finding. The analysis of site ages revealed that the battle between the two sides had a long history and is still ongoing. The web scene was polarized with either pro or anti views and little neutral ground. The study suggests ways that professional information can be promoted more effectively on the web. The study demonstrates that webometrics analysis is effective in studying online information dissemination. This kind of analysis can be used to study not only health information but other information as well.

show abstract

“…Crawling mechanisms based on the site paradigm, rather than the traditional page-based one, were enumerated in [34]. In [11], the potential spam properties of a HostRank algorithm were observed, and in [35], the ranking quality of several site-levelstyle PageRank variations was studied. In contrast to page aggregations, other researchers [36] have considered disaggregating Web pages into smaller units for providing ranking over individual components of Web pages.…”

Section: Related Workmentioning

confidence: 99%

A Parameterized Approach to Spam-Resilient Link Analysis of the Web

Caverlee

Webb

Liu

et al. 2009

IEEE Trans. Parallel Distrib. Syst.

View full text Add to dashboard Cite

Abstract-Link-based analysis of the Web provides the basis for many important applications-like Web search, Web-based data mining, and Web page categorization-that bring order to the massive amount of distributed Web content. Due to the overwhelming reliance on these important applications, there is a rise in efforts to manipulate (or spam) the link structure of the Web. In this manuscript, we present a parameterized framework for link analysis of the Web that promotes spam resilience through a source-centric view of the Web. We provide a rigorous study of the set of critical parameters that can impact source-centric link analysis and propose the novel notion of influence throttling for countering the influence of link-based manipulation. Through formal analysis and a large-scale experimental study, we show how different parameter settings may impact the time complexity, stability, and spam resilience of Web link analysis. Concretely, we find that the source-centric model supports more effective and robust rankings in comparison with existing Web algorithms such as PageRank.Index Terms-Internet search, information search and retrieval, information storage and retrieval, information technology and systems, distributed systems, systems and software, Web search, general, Web-based services, online information services.

show abstract

New versions of PageRank employing alternative Web document models

Cited by 7 publications

References 27 publications

A longitudinal analysis of alternative document models

A longitudinal analysis of alternative document models

A webometric analysis of the online vaccination debate

A Parameterized Approach to Spam-Resilient Link Analysis of the Web

Contact Info

Product

Resources

About