Strong Regularities in World Wide Web Surfing

Huberman, Bernardo A.; Pirolli, Peter; Pitkow, James E.; Lukose, Rajan M.

doi:10.1126/science.280.5360.95

Cited by 571 publications

(404 citation statements)

References 13 publications

Supporting

Mentioning

388

Contrasting

Unclassified

Order By: Relevance

“…For instance, the hierarchically connected networks are shown [10] to be robust to large failure rates, however, they are vulnerable to removal of a few 'key nodes'. The inhomogeneous structure of connections has been found in metabolic cycles [1], in various social networks [2], including the science citation network [3], and the Internet [4] and the world-wide Web [5][6][7][8].…”

Section: Introductionmentioning

confidence: 99%

“…Understanding the evolution of complex networks [1][2][3][4][5][6][7][8][9][10][11][12][13] remains a challenging problem of modern statistical physics. Modeling the dynamic structure of these networks has significant practical applications, for instance in the design of search and control algorithms and in predicting emergence of new phenomena in information networks [5].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Dynamics of directed graphs: the world-wide Web

Tadić

2001

Physica A: Statistical Mechanics and its Applications

114

139

View full text Add to dashboard Cite

We introduce and simulate a growth model of the world-wide Web based on the dynamics of outgoing links that is motivated by the conduct of the agents in the real Web to update outgoing links (re)directing them towards constantly changing selected nodes. Emergent statistical correlation between the distributions of outgoing and incoming links is a key feature of the dynamics of the Web. The growth phase is characterized by temporal fractal structures which are manifested in the hierarchical organization of links. We obtain quantitative agreement with the recent empirical data in the real Web for the distributions of in-and out-links and for the size of connected component. In a fully grown network of N nodes we study the structure of connected clusters of nodes that are accessible along outgoing links from a randomly selected node. The distributions of size and depth of the connected clusters with a giant component exhibit supercritical behavior. By decreasing the control parameter-average fraction β of updated and added links per time step-towards βc(N ) < 10% the Web can resume a critical structure with no giant component in it. We find a different universality class when the updates of links are not allowed, i.e., for β ≡ 0, corresponding to the network of science citations.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Dynamics of directed graphs: the world-wide Web

Tadić

2001

Physica A: Statistical Mechanics and its Applications

114

139

View full text Add to dashboard Cite

show abstract

“…Studies found that users demonstrated regularities in their surfing patterns [12]. Our characterization results presented in this paper also indicate that users have highly repetitive network-connection patterns.…”

mentioning

confidence: 48%

User-Assisted Host-Based Detection of Outbound Malware Traffic

Xiong

Malhotra

Stefan

et al. 2009

Information and Communications Security

View full text Add to dashboard Cite

Abstract. Conventional network security solutions are performed on networklayer packets using statistical measures. These types of traffic analysis may not catch stealthy attacks carried out by today's malware. We aim to develop a host-based security tool that identifies suspicious outbound network connections through analyzing the user's surfing activities. Specifically, our solution for Web applications predicts user's network connections by analyzing Web content; unpredicted traffic is further investigated with the user's help. We describe our method and implementation as well as the experimental results in evaluating its efficiency and effectiveness. We describe how our studies can be applied to detecting bot infection. In order to assess the workload of our host-based traffic-analysis tool, we also perform a large-scale characterization study on 500 university-users' wireless network traces for 4-month period. We study both the statistical and temporal patterns of individuals' web usage behaviors from collected wireless network traces. Users are classified into different profiles based on their web usage patterns. Our results show that users have regularities in their Web activities and the expected workload of our traffic-analysis solution is low.

show abstract

“…This is stronger than our linkage conjecture, since it implies a positive correlation between V L and V L−1 (analogous to our relevance autocorrelation) for any µ > 0. Huberman et al (1998) find that the distribution of surfing depth (clicks per Web site) derived from the above random walk equation is a very good predictive model of human browsing behavior. Although our conjecture on the value of linkage topology is more modest, it finds strong support in these findings.…”

Section: Other Related Projectsmentioning

confidence: 99%

Untitled

2000

View full text Add to dashboard Cite

Abstract. This paper discusses a novel distributed adaptive algorithm and representation used to construct populations of adaptive Web agents. These InfoSpiders browse networked information environments on-line in search of pages relevant to the user, by traversing hyperlinks in an autonomous and intelligent fashion. Each agent adapts to the spatial and temporal regularities of its local context thanks to a combination of machine learning techniques inspired by ecological models: evolutionary adaptation with local selection, reinforcement learning and selective query expansion by internalization of environmental signals, and optional relevance feedback. We evaluate the feasibility and performance of these methods in three domains: a general class of artificial graph environments, a controlled subset of the Web, and (preliminarly) the full Web. Our results suggest that InfoSpiders could take advantage of the starting points provided by search engines, based on global word statistics, and then use linkage topology to guide their search on-line. We show how this approach can complement the current state of the art, especially with respect to the scalability challenge.

show abstract

Strong Regularities in World Wide Web Surfing

Cited by 571 publications

References 13 publications

Dynamics of directed graphs: the world-wide Web

Dynamics of directed graphs: the world-wide Web

User-Assisted Host-Based Detection of Outbound Malware Traffic

Untitled

Contact Info

Product

Resources

About