Web Recommender Systems Research Articles

A Collaborative Web Recommendation System Based on Fuzzy Association Rule Mining Techniques

Currently the use of web recommendation techniques is growing worldwide with aim of providing the custom-made required data to end users. Most of the web users complain about finding useful information on web sites. Web recommender systems predict the information needs of users and provide them with recommendations to facilitate their navigation. Recommender systems have been extensively explored in web mining. The web recommendation systems are split into two main categories such as collaborative recommendation system and content based recommendation system. However, the quality of recommendations and the user satisfaction with such systems are still not optimal. In adaptive association recommender systems based on web mining techniques have strengths and weaknesses. One of these weaknesses is lack of consideration of an appropriate measure to calculate the user’s interest degree of pages. Applying Fuzzy Association Rule Mining (FARM) algorithm to a recommender system leads to calculate user’s interest of pages more accurately. Consequently generated recommendations will be more desirable when compared to other association rule mining techniques.

Recommendation of Web Pages using Weighted K-Means Clustering

Web Recommendation Systems are implemented by using collaborative filtering approach. It is a specific type of information filtering system that aims to predict the user browsing activity and then recommend to the user web pages items that are likely to be of interest. In this paper, a new recommendation system is proposed by using Weighted KMeans clustering approach to predict the user’s navigational behavior. The proposed recommendation system based on Weighted K-Means clustering performs well when compared to K-Means algorithm. The performance of the comparative analysis is presented through experimental results.

Recommendations of Personal Web Pages Based on User Navigational Patterns

In this paper, we propose a web recommendation system where user navigational patterns can be extracted from web logs. First, the recommendation system discovers user concepts from web logs step-by-step, and then extracts the navigation patterns among these concepts. These navigational patterns are then used to generate recommendation web pages by matching the navigation behavior of a user personal knowledge base. The pages in a recommendation list are ranked according to their hub scores which are computed based on page connectivity information. The experimental results show that the web pages recommended by our system are of better quality and acceptable for humans from various domains, based on human evaluators ranking as well as quality-value-based performance measures.

Web Recommender System for Private Universities’ Admission in Iraq: UHD Case Study

Admission recommender system provides a way to finding suitable course in universities that best fit students' merits and interests. Iraqi universities are using a complex admission process which is not supporting recommender systems, and it is only based on the candidates' Grade Point Average (GPA). In addition, applicants don't have enough information on available courses and their available majors. In this paper, we prepare a new admission recommender system that is developed by using a hybrid method of Neural Network (NN), Decision Tree (DT), and Our Proposed Algorithm (OPA). We using DT to classify the applicant to 10 groups, each group has special properties, but NN used to apply the applicant to the available courses that can apply, our algorithm mixed with NN to finding best course. Our algorithm considers GPA, test score, candidates' interest and their desire jobs as decision parameters. The aim of this paper to solve the complex systems that used more than one criteria to apply more than one courses. The result of the system is better and more reliable outcome comparing to other available admission systems; furthermore our system can find a suitable course for each applicant.

A Review on Web Recommendation System

In Web world, there is immense of information available on the internet but user is not capable to find relevant information in short period of time. Therefore, a system called recommendation system developed to assist user in their browsing activities. It analyzes users need and provides relevant information in shorter span. In this work, various recommendation systems reviewed to analyze their problems and solutions. In order to improve the recommendation quality, a new web recommendation system is introduced. This system uses knn and genetic algorithm during web usage mining process to analyze static web access log.

User Action Interpretation for Online Content Optimization

Web portal services have become an important medium to deliver digital content and service, such as news, advertisements, and so on, to Web users in a timely fashion. To attract more users to various content modules on the Web portal, it is necessary to design a recommender system that can effectively achieve online content optimization by automatically estimating content items' attractiveness and relevance to users' interests. User interaction plays a vital role in building effective content optimization, as both implicit user feedbacks and explicit user ratings on the recommended items form the basis for designing and learning recommendation models. However, user actions on real-world Web portal services are likely to represent many implicit signals about users' interests and content attractiveness, which need more accurate interpretation to be fully leveraged in the recommendation models. To address this challenge, we investigate a couple of critical aspects of the online learning framework for personalized content optimization on Web portal services, and, in this paper, we propose deeper user action interpretation to enhance those critical aspects. In particular, we first propose an approach to leverage historical user activity to build behavior-driven user segmentation; then, we introduce an approach for interpreting users' actions from the factors of both user engagement and position bias to achieve unbiased estimation of content attractiveness. Our experiments on the large-scale data from a commercial Web recommender system demonstrate that recommendation models with our user action interpretation can reach significant improvement in terms of online content optimization over the baseline method. The effectiveness of our user action interpretation is also proved by the online test results on real user traffic.

A Neoteric Web Recommender System based on Approach of Mining Frequent Sequential Pattern from Customized Web Log Preprocessing

A Neoteric Web Recommender System based on Approach of Mining Frequent Sequential Pattern from Customized Web Log Preprocessing

An Efficient Web Recommendation System using Collaborative Filtering and Pattern Discovery Algorithms

Information is overloaded in the Internet due to the unstable growth of information and it makes information search as complicate process. Web recommendation systems assist the users to get the exact information and facilitate the information search easier. Web recommendation is one of the techniques of web personalization, which recommends web pages to the user based on the previous browsing history. It is done either content based approach or collaborative filtering approach. In this paper web usage mining is considered as the major source for web recommendation in association with Collaborative filtering approach, association rule mining and Markov model to recommend the web pages to the user.

A fuzzy co-clustering approach for hybrid recommender systems

Many efforts have been done to tackle the problem of information abundance in the World Wide Web. Growth in the number of web users and the necessity of making the information available on the web, make web recommender systems very critical and popul

A Hybrid Web Recommendation System Based on the Improved Association Rule Mining Algorithm

As the growing interest of web recommendation systems those are applied to deliver customized data for their users, we started working on this system. Generally the recommendation systems are divided into two major categories such as collaborative recommendation system and content based recommendation system. In case of collaborative recommendation systems, these try to seek out users who share same tastes that of given user as well as recommends the websites according to the liking given user. Whereas the content based recommendation systems tries to recommend web sites similar to those web sites the user has liked. In the recent research we found that the efficient technique based on association rule mining algorithm is proposed in order to solve the problem of web page recommendation. Major problem of the same is that the web pages are given equal importance. Here the importance of pages changes according to the frequency of visiting the web page as well as amount of time user spends on that page. Also recommendation of newly added web pages or the pages that are not yet visited by users is not included in the recommendation set. To overcome this problem, we have used the web usage log in the adaptive association rule based web mining where the association rules were applied to personalization. This algorithm was purely based on the Apriori data mining algorithm in order to generate the association rules. However this method also suffers from some unavoidable drawbacks. In this paper we are presenting and investigating the new approach based on weighted Association Rule Mining Algorithm and text mining. This is improved algorithm which adds semantic knowledge to the results, has more efficiency and hence gives better quality and performances as compared to existing approaches.

Generation of web recommendations using implicit user feedback and normalised mutual information

The knowledge base of a traditional web recommender system is constructed from web logs, reflecting past user preferences which may change over time. In this paper, an algorithm, based on implicit user feedback on top N recommendations and normalised mutual information, is proposed for collaborative personalised web recommender system. The proposed algorithm updates the knowledge base taking into account the changing user preferences, in order to generate better recommendations in future. The proposed approach and collaborative personalised web recommender systems without feedback are compared. Significant improvements are observed in precision, recall and F1 measure for proposed approach.

Comparing the Effect of Matrix Factorization Techniquesin Reducing the Time Complexity for Traversing the Big Data of Recommendation Systems

 Abstract—In this fast trending technological era, data is growing very fast all around the globe. Today by analyzing large data sets, one can spot business trends, detect environmental changes, predict forthcoming social agendas and combat crime. This so-called Big Data analytics is challenging and dependent on time complexity. Amidst all this, we also know that space is becoming lesser day by day. In a time when computer imaging and web browsing demand the use of many different data, it is very important for us to be able to store all the types in reasonably sized matrices. A database is like a matrix but due to the growing data it will have a never ending addition of rows. To tackle this situation, we have tried to compare some matrix compression techniques that will help in efficient and fast working of analytic web recommendation systems and will decrease the effort of information retrieval from large data sets.

Investigation of sequential pattern mining techniques for web recommendation

Increased application of sequence mining in web recommender systems (WRS) requires a better understanding of the performance and a clear identification of the strengths and weaknesses of existing algorithms. Among the commonly used sequence mining methods, the tree-based approach, such as pre-order linked WAP-tree mining algorithm (PLWAP-Mine) and conditional sequence mining algorithm (CS-Mine), has demonstrated high performance in web mining applications. However, its advantages over other mining methods are not well explained and understood in the context of WRS. This paper firstly reviews the existing sequence mining algorithms, and then studies the performance of two outstanding algorithms, i.e., the PLWAP-Mine and CS-Mine algorithms, with respect to their sensitivity to the dataset variability, and their practicality for web recommendation. The results show that CS-Mine performs faster than PLWAP-Mine, but the frequent patterns generated by PLWAP-Mine are more effective than CS-Mine when applied in web recommendations. These results are useful to WRS developers for the selection of appropriate sequence mining algorithms.

Evaluation of a web recommender system in electronic and mobile tourism

Recommender systems are software frameworks that employ a specific type of information filtering technique, aiming at recommending information items or social elements that are likely to be of interest to the user. Herein, we present the evaluation results of the recently prototyped tourism recommender system (TRS). We followed a formal evaluation process to validate the usability of two versions of the TRS by users in realistic environments; the first is a typical web recommender system (wTRS), while the second is a system that enables tourist content recommendations addressed to mobile users (mTRS). The usability evaluation tests have been undertaken at the municipality of Mytilene, Greece.

Study on collaborative filtering recommendation algorithm based on web user clustering

Collaborative filtering recommend is the most widely used and the most successful recommendation algorithm. However, because the online effective amount of information on the number and types of goods is growing rapidly, to recommend system proposed a serious challenge, the collaborative filtering recommend exists in the cold start and sparse matrix, real-time problems need to be solved urgently. In order to solve the problem, this paper based on the collaborative filtering algorithm proposed Web recommend system based on user clustering, analysis of the Web recommendation system implementation process, and finally, experiment design and analysis. The results show that the proposed collaborative filtering recommendation based on user clustering method and the traditional collaborative filtering method is compared, and can efficiently improve recommendation quality, and better meet the needs of users.

Finding superior skyline points for multidimensional recommendation applications

In a typical Web recommendation system, objects are often described by many attributes. It also needs to serve many users with a diversified range of preferences. In other words, it must be capable to efficiently support high dimensional preference queries that allow the user to explore the data space effectively without imposing specific preference weightings for each dimension. The skyline query, which can produce a set of objects guaranteed to contain all top ranked objects for any linear attribute preference combination, has been proposed to support this type of recommendation applications. However, it suffers from the problem known as `dimensionality curse' as the size of skyline query result set can grow exponentially with the number of dimensions. Therefore, when the dimensionality is high, a large percentage of objects can become skyline points. This problem makes such a recommendation system less usable for users. In this paper, we propose a stronger type of skyline query, called core skyline query, that adopts a new quality measure called vertical dominance to return only an interesting subset of the traditional skyline points. An efficient query processing method is proposed to find core skyline points using a novel indexing structure called Linked Multiple B'-trees (LMB). Our approach can find such superior skyline points progressively without the need of computing the entire set of skyline points first.

An efficient web recommendation system based on modified IncSpan algorithm

Web recommendation systems are used to assist the user to access the most appropriate web pages that can satisfy their needs. This paper provides the web recommendation system which is based on incremental database. The incremental database contains the new navigational sequences from the user and this incremental database can be added with the existing sequence database. We have proposed a novel algorithm, called modified IncSpan, for the effectual mining of the sequential patterns from the incremental database. Finally, the performance of the proposed recommendation system is evaluated with precision, applicability and hit ratio.

Social Voting Techniques: A Comparison of the Methods Used for Explicit Feedback in Recommendation Systems

Web recommendation systems usually brings a content list to users based on previous ratings made by them to other similar contents through some social voting mean. This paper aims to present a comparison of the main explicit rating methods used by web recommendation systems. The goal of this survey is to determine which of the studied methods fits better to user preferences when they rate a content on the web; based on the obtained results, a recommendation system can be implemented using an explicit feedback method to achieve this goal.

Efficient personalization and Recommendation Methods for Web Mining

With the fast development of World Wide Web, Web-based applications and services should allow user to get the right personalized information quickly and effectively. Collaborative Filtering acts a very important role in web service personalization and Recommender System. Most of the research efforts in web personalization correspond to the evolution of extensive research in web usage mining, i.e. the exploitation of the navigational patterns of the web site’s visitors. When a personalization system relies solely on usage-based results, however, valuable information conceptually related to what is finally recommended may be missed. Moreover, the structural properties of the web site are often disregarded. In this thesis, we propose novel techniques that use the content semantics and the structural properties of a web site in order to improve the effectiveness of web personalization. In the first part of our work we present standing for Semantic Web Personalization, a personalization system that integrates usage data with content semantics, expressed in ontology terms, in order to compute semantically enhanced navigational patterns and effectively generate useful recommendations. To the best of our knowledge, our proposed technique is the only semantic web personalization system that may be used by non-semantic web sites. In the second part of our work, we present a novel approach for enhancing the quality of recommendations based on the underlying structure of a web site. We introduce UPR (Usage-based PageRank), a PageRank-style algorithm that relies on the recorded usage data and link analysis techniques. Our experimental results show more efficient than existing works. Key words: Web personalization, Semantic web and Recommender systems.

Mining and tracking evolving web user trends from large web server logs

AbstractRecently, online organizations became interested in tracking users' behavior on their websites to better understand and satisfy their needs. In response to this need, web usage mining tools were developed to help them use web logs to discover usage patterns or profiles. However, since website usage logs are being continuously generated, in some cases, amounting to a dynamic data stream, most existing tools are still not able to handle their changing nature or growing size. This paper proposes a scalable framework that is capable of tracking the changing nature of user behavior on a website, and represent it in a set of evolving usage profiles. These profiles can offer the best usage representation of user activity at any given time, and they can be used as an input to higher‐level applications such as a web recommendation system. Our specific aim is to make the hierarchical unsupervised niche clustering (HUNC) algorithm more scalable, and to add integrated profile tracking and cluster‐based validation to it. Our experiments on real web log data confirm the validity of our approach for large data sets that previously could not be handled in one shot. Copyright © 2010 Wiley Periodicals, Inc. Statistical Analysis and Data Mining 3: 106‐125, 2010