Predicting Web Users' Next Access Based on Log Data

Sen, Rituparna; Hansen, Mark

doi:10.1198/1061860031275

Cited by 36 publications

(32 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Cadez et.al. [8] as well as Sen and Hansen [28] also proposed the use of mixed Markov models. A different approach is that of Acharyya and Ghosh [1], who use concepts, to describe the web site.…”

Section: Related Workmentioning

confidence: 99%

“…There exist only a few approaches where the authors claim that these techniques are not accurate enough and define different priors. Sen and Hansen [28] use Dirichlet priors, whereas Borges and Levene [5] define a hybrid formula which combines the two options (taking into consideration the frequency of visits to a page as the first page, or the total number of visits to the page). For this purpose, they define the variable α, which ranges from 0 (for page requests as first page) to 1 (for total page requests).…”

Section: Related Workmentioning

confidence: 99%

“…Moreover, such complex models often require inordinate amounts of training data, and the increase in the number of states may even have worse prediction accuracy and can significantly limit their applicability for applications requiring fast predictions, such as web personalization [11]. There have also been proposed some mixture models that combine Markov models of different orders [8,11,22,28]. Such models, however, require much more resources in terms of preprocessing and training.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Web path recommendations based on page ranking and Markov models

Eirinaki

Vazirgiannis

Kapogiannis

2005

Proceedings of the 7th Annual ACM International Workshop on Web Information and Data Management

View full text Add to dashboard Cite

Markov models have been widely used for modelling users' navigational behaviour in the Web graph, using the transitional probabilities between web pages, as recorded in the web logs. The recorded users' navigation is used to extract popular web paths and predict current users' next steps. Such purely usage-based probabilistic models, however, present certain shortcomings. Since the prediction of users' navigational behaviour is based solely on the usage data, structural properties of the Web graph are ignored. Thus important -in terms of pagerank authority score -paths may be underrated. In this paper we present a hybrid probabilistic predictive model extending the properties of Markov models by incorporating link analysis methods. More specifically, we propose the use of a PageRank-style algorithm for assigning prior probabilities to the web pages based on their importance in the web site's graph. We prove, through experimentation, that this approach results in more objective and representative predictions than the ones produced from the pure usage-based approaches.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Web path recommendations based on page ranking and Markov models

Eirinaki

Vazirgiannis

Kapogiannis

2005

Proceedings of the 7th Annual ACM International Workshop on Web Information and Data Management

View full text Add to dashboard Cite

show abstract

“…The investigation of the hyperlinked relationships between web pages is known as external structure mining [19], while the analysis of relationships of information within web pages is known as internal structure mining. The extraction of URL that is important to decision maker's purpose is known as URL mining [20].…”

Section: Introductionmentioning

confidence: 99%

Web Log based Analysis of User's Browsing Behavior

Ladekar¹,

Pawar²,

Raikar³

et al. 2015

IJCA

View full text Add to dashboard Cite

In The increasing craze of internet has geared a number of modern firms for using web technology in their day to day lives. A remarkable ability to analyze web log data is provided to them by the web mining technology, that are putatively full of information, but frequently lacking with meaningful information. This signifies the need to the development of an inference mechanism which is advanced and that draws out richer implication from mining's output. This paper presents a web mining algorithm that aims at amending the interpretations of the draft's output of association rule mining. This algorithm is being tremendously used in web mining. The results obtained prove robustness of the algorithm proposed in this paper.

show abstract

“…While Markov models are highly regarded as Web usage mining methods M. Deshpande et al, [14] , J. Zhu et al, [32], J. Pitkow et al [39], R.R. Sarukkai, [38] ,R. Sen et al, [23] ; I. Cadez et al, [35] combining Markov models with sequence-based clustering has rarely been attempted, with the exception of Yang et al, [28] in which Markov chain's transition matrix-based representation and K-means algorithm are used to cluster user sessions for better Web caching and pre-fetching. As shown in Table 1, while sequence-based clustering is consistently highly regarded for use in Web usage mining, a systematic evaluation of these methods was rarely addressed.…”

Section: Introductionmentioning

confidence: 99%