Web User Profiling on Proxy Logs and Its Evaluation in Personalization

Fujimoto, Hiroshi; Etoh, Minoru; Kinno, Akira; Akinaga, Yoshikazu

doi:10.1007/978-3-642-20291-9_13

Cited by 11 publications

(6 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Web‐usage mining can be used to extract knowledge from observed actions. A wide variety of techniques, such as case‐based reasoning (Godoy, Schiaffino, & Amandi, ), Bayesian networks (Garcia, Amandi, Schiaffino, & Campo, ), association rules (Schiaffino & Amandi, ), genetic algorithms (Yannibelli, Godoy, & Amandi, ), neural networks (Villaverde, Godoy, & Amandi, ), and topic modeling (Fujimoto, Etoh, Kinno, & Akinaga, ), and so on, have been used to this end. These techniques have been applied to many areas, but, to our knowledge, they have not been applied to detecting navigation problems in a website aimed at users with disabilities.…”

Section: Related Work and Discussionmentioning

confidence: 99%

Web mining for navigation problem detection and diagnosis in Discapnet: A website aimed at disabled people

Arbelaitz

Lojo

Muguerza

et al. 2015

Asso for Info Science & Tech

View full text Add to dashboard Cite

The dramatic increase in the amount of information stored on the web makes it more important to familiarize people with disabilities and elderly people with digital devices and applications and to adapt websites to enable their use by these users. Discapnet is a website mainly aimed at visually disabled people, and navigation is a challenging task for its users. In this context, system evaluation and problem detection become crucial aspects for enhancing user experience and may contribute greatly to diminishing the existing technological gap. This study proposes a system based on webmining techniques that collects in-use information while the user is accessing the web (thus, being a noninvasive system). The proposed system models users in the wild and discovers navigation problems appearing in Discapnet and can also be used for problem detection when new users are navigating the site. The system was tested and its efficiency demonstrated in an experiment involving navigation under supervision, in which 82.6% of a set of disabled people were automatically labeled as having problems with the website.

show abstract

Section: Related Work and Discussionmentioning

confidence: 99%

Web mining for navigation problem detection and diagnosis in Discapnet: A website aimed at disabled people

Arbelaitz

Lojo

Muguerza

et al. 2015

Asso for Info Science & Tech

View full text Add to dashboard Cite

show abstract

“…Back in 1999, Mobasher et al (1999) conducted research to analyze the user's interaction and recommend URL for creating adaptive websites. More recently, Fujimoto et al (2011) proposed the construction of user profiles based on server logs and Sen et al (2016) proposed an approach for predicting the next visited page using the history of past visits contained in logs. Khonsha and Sadreddini (2011) developed a framework that mines user logs and the content of the website for supporting the Web personalization by predicting the next pages that the user will visit.…”

Section: Adaptive Web Applicationsmentioning

confidence: 99%

An approach to support the construction of adaptive Web applications

Vasconcelos

Baldochi

Santos

2020

IJWIS

View full text Add to dashboard Cite

Purpose This paper aims to presents Real-time Usage Mining (RUM), an approach that exploits the rich information provided by client logs to support the construction of adaptive Web applications. The main goal of RUM is to provide useful information about the behavior of users that are currently browsing a Web application. By consuming this information, the application is able to adapt its user interface in real-time to enhance the user experience. RUM provides two types of services as follows: support for the detection of struggling users; and user profiling based on the detection of behavior patterns. Design/methodology/approach RUM leverages the previous study on usability evaluation to provide a service that evaluates the usability of tasks performed by users while they browse applications. This evaluation is based on a metric that allows the detection of struggling users, making it possible to identify these users as soon as few logs from their interaction are processed. RUM also exploits log mining techniques to detect usage patterns, which are then associated with user profiles previously defined by the application specialist. After associating usage patterns to user profiles, RUM is able to classify users as they browse applications, allowing the application developer to tailor the user interface according to the users’ needs and preferences. Findings The proposed approach was exploited to improve user experience in real-world Web applications. Experiments showed that RUM was effective to provide support for struggling users to complete tasks. Moreover, it was also effective to detect usage patterns and associate them with user profiles. Originality/value Although the literature reports studies that explore client logs to support both the detection of struggling users and the user profiling based on usage patterns, no existing solutions provide support for detecting users from specific profiles or struggling users, in real-time, while they are browsing Web applications. RUM also provides a toolkit that allows the approach to be easily deployed in any Web application.

show abstract

“…Latent Dirichlet Allocation (LDA) is also another type of topic model that is used commonly to cluster users for many applications. [5] gives an example where web users are clustered, assuming the users are the documents and the visited websites are the words. Furthermore, [14] gives an application of LDA for online advertising (but on a small, sampled set of users).…”

Section: Previous Workmentioning

confidence: 99%

User Clustering in Online Advertising via Topic Models

Geyik,

Dasdan,

Lee

2015

Preprint

View full text Add to dashboard Cite

In the domain of online advertising, our aim is to serve the best ad to a user who visits a certain webpage, to maximize the chance of a desired action to be performed by this user after seeing the ad. While it is possible to generate a different prediction model for each user to tell if he/she will act on a given ad, the prediction result typically will be quite unreliable with huge variance, since the desired actions are extremely sparse, and the set of users is huge (hundreds of millions) and extremely volatile, i.e., a lot of new users are introduced everyday, or are no longer valid. In this paper we aim to improve the accuracy in finding users who will perform the desired action, by assigning each user to a cluster, where the number of clusters is much smaller than the number of users (in the order of hundreds). Each user will fall into the same cluster with another user if their event history are similar. For this purpose, we modify the probabilistic latent semantic analysis (pLSA) model by assuming the independence of the user and the cluster id, given the history of events. This assumption helps us to identify a cluster of a new user without re-clustering all the users. We present the details of the algorithm we employed as well as the distributed implementation on Hadoop, and some initial results on the clusters that were generated by the algorithm.

show abstract

Web User Profiling on Proxy Logs and Its Evaluation in Personalization

Cited by 11 publications

References 15 publications

Web mining for navigation problem detection and diagnosis in Discapnet: A website aimed at disabled people

Web mining for navigation problem detection and diagnosis in Discapnet: A website aimed at disabled people

An approach to support the construction of adaptive Web applications

User Clustering in Online Advertising via Topic Models

Contact Info

Product

Resources

About