User Clickstream Research Articles

Research on intelligent information system of user intelligent behavior data based on computer big data

This paper collects and analyzes users' online behaviors through computer big data technology, uses computer big data intelligent analysis system to analyze users' online shopping behavior, and uses information-based data analysis system to detect consumers' online shopping needs under the e-commerce platform. The main technique used in this paper is the computer browser log mining method. In the user's click stream data, the function keys of Tmall and Taobao webpages are used as data information for classification and collection. This paper uses the Bisecting K-means clustering algorithm to mine the state of interest. Finally, the feature maps of interests and behaviors are summarized. By processing four typical types of e-commerce user demand status, including background management type, continuous search type, product browsing type and information search data, and clustering based on page type, an effective method for dynamically changing demand judgment is obtained. The state of online shoppers is analyzed through data processing, which also proves the effectiveness of the computer intelligent information system.

Real-time user clickstream behavior analysis based on apache storm streaming

This paper presents an approach to analyzing consumers’ e-commerce site usage and browsing motifs through pattern mining and surfing behavior. User-generated clickstream is first stored in a client site browser. We build an ingestion pipeline to capture the high-velocity data stream from a client-side browser through Apache Storm, Kafka, and Cassandra. Given the consumer’s usage pattern, we uncover the user’s browsing intent through n-grams and Collocation methods. An innovative clustering technique is constructed through the Expectation-Maximization algorithm with Gaussian Mixture Model. We discuss a framework for predicting a user’s clicks based on the past click sequences through higher order Markov Chains. We developed our model on top of a big data Lambda Architecture which combines high throughput Hadoop batch setup with low latency real-time framework over a large distributed cluster. Based on this approach, we developed an experimental setup for an optimized Storm topology and enhanced Cassandra database latency to achieve real-time responses. The theoretical claims are corroborated with several evaluations in Microsoft Azure HDInsight Apache Storm deployment and in the Datastax distribution of Cassandra. The paper demonstrates that the proposed techniques help user experience optimization, building recently viewed products list, market-driven analyses, and allocation of website resources.

A product recommendation system for solving the cold start problem

The recommendation of product or service based on application needs different product attributes and user requirements to be analyzed. But if both the kinds of information are unavailable then such kind of issue in the recommendation system is known as the clod start problem.[1] In this presented work, the effort is made in order to understand and resolve the issue of recommendation system. Thus, a four phase recommendation system is introduced in this work. In first phase, the web usage data is preprocessed which is used for further recommendations of products. In next phase, the frequent pattern based recommendation is performed. In third phase, the recommendation is made on the basis of user current search (user click streams) and similar user behaviors available in web access logs. Additionally, the final recommendation is made on the basis of filtering the results obtained in third phase and the cost, brand and social review of the product or service. The implementation of the system is performed on JAVA technology and the results in terms of accuracy, error rate is computed. The results show the prediction is accurate and required less computational resources. Thus, in recommendation system design the model is acceptable for use and future extension of work for solving the issue of cold start problem.

On the Use of Generative Deep Learning Approaches for Generating Hidden Test Scripts

With the advent of web 2.0, web application architectures have been evolved, and their complexity has grown enormously. Due to the complexity, testing of web applications is getting time-consuming and intensive process. In today’s web applications, users can achieve the same goal by performing different actions. To ensure that the entire system is safe and robust, developers try to test all possible user action sequences in the testing phase. Since the space of all the possibilities is enormous, covering all user action sequences can be impossible. To automate the test script generation task and reduce the space of the possible user action sequences, we propose a novel method based on long short-term memory (LSTM) network for generating test scripts from user clickstream data. The experiment results clearly show that generated hidden test sequences are user-like sequences, and the process of generating test scripts with the proposed model is less time-consuming than writing them manually.

Improving search ranking of geospatial data based on deep learning using user behavior data

Finding geospatial data has been a big challenge regarding the data size and heterogeneity across various domains. Previous work has explored using machine learning to improve geospatial data search ranking, but it usually relies on training data labelled by subject matter experts, which makes it laborious and costly to apply to scenarios in which data relevancy to a query can change over time. When a user interacts with a search engine, plenteous information is recorded in the log file, which is essentially free, sustainable and up-to-the-minute. In this research, we propose a deep learning-based search ranking framework that can expeditiously update the ranking model through capturing real-time user clickstream data. The contributions of the proposed framework consist of 1) a log parser that can ingest and parse Web logs that record users’ behavior in a real-time manner; 2) a set of hypotheses of modelling the relative relevance of data; and 3) a deep learning based ranking model which can be updated dynamically with the increment of user behavior data. Quantitative comparison with a few other machine learning algorithms suggests substantial improvement.

Exploring Smartphone Users’ Social Information Behavior

AAs the popularity of social network services (SNS) grows, users’ online behavior is increasingly being affected by SNS browsing. Now, mobile device serve as a tool for social connection, provides an increasingly important communication channel in facilitating social connections. SNSs that are adequate for mobile devices have been developed. To clarify web user social information behavior, this study used social network sites to analyze smartphone user online behavior by collecting user clickstream data over a period of 3 months. The influence of SNS browsing on types of external sites visited—namely news, shopping, searches, forums, videos, and blogs—is examined. This study used a site-centric approach, wherein user data was examined by using association rules and the Jaccard Index to explore the relationship between SNS and other online activities. We collaborates with InsightXplorer to recruit smart phone users, collected 580 samples from the consumers who use the smartphone. First, user-centric approach will be conducted for correlation analysis to quantify the association between SNSs and other categories, and then use the results as the standard to conduct fixed effect model by exploring the duration of gender, age and weekdays/weekend at 24hrs. Second, site-centric approach will conduct correspondence analysis and association rules by using users' session to gather all categories in the graph and explore the relationship between the SNSs and the other categories. The result shows that Taiwanese smartphone users use Facebook (both Web and App) as a news-seeking, topic-seeking, video-seeking and word-of-mouth–seeking platform. That means Facebook will become a portal. When people want to find something interesting, the first thing is to open Facebook and searching their timeline. Finally, based on the findings, this study to provide a stepping stone for marketers and researchers to understand web users’ social information behavior. Keywords: Smartphone, Social information behavior, Web usage mining, Clickstream data, Mobile commerce To cite this document: Chiang, I.-P., Lin, C.-Y., & Wu, Y.-J. (2019). Exploring smartphone users’ social information behavior. Contemporary Management Research, 15(1), 53-67. https://doi.org/10.7903/cmr.18461

A comprehensive methodology for discovering semantic relationships among geospatial vocabularies using oceanographic data discovery as an example

ABSTRACTIt is challenging to find relevant data for research and development purposes in the geospatial big data era. One long-standing problem in data discovery is locating, assimilating and utilizing the semantic context for a given query. Most research in the geospatial domain has approached this problem in one of two ways: building a domain-specific ontology manually or discovering automatically, semantic relationships using metadata and machine learning techniques. The former relies on rich expert knowledge but is static, costly and labor intensive, whereas the second is automatic and prone to noise. An emerging trend in information science takes advantage of large-scale user search histories, which are dynamic but subject to user- and crawler-generated noise. Leveraging the benefits of these three approaches and avoiding their weaknesses, a novel methodology is proposed to (1) discover vocabulary-based semantic relationships from user search histories and clickstreams, (2) refine the similarity calculation methods from existing ontologies and (3) integrate the results of ontology, metadata, user search history and clickstream analysis to better determine their semantic relationships. An accuracy assessment by domain experts for the similarity values indicates an 83% overall accuracy for the top 10 related terms over randomly selected sample queries. This research functions as an example for building vocabulary-based semantic relationships for different geographical domains to improve various aspects of data discovery, including the accuracy of the vocabulary relationships of commonly used search terms.

Big Data Characterization of Learner Behaviour in a Highly Technical MOOC Engineering Course

MOOCs attract a large number of users with unknown diversity in terms of motivation, ability, and goals. To understand more about learners in a MOOC, the authors explored clusters of user clickstream patterns in a highly technical MOOC, Nanophotonic Modelling through the algorithm k-means++. Five clusters of user behaviour emerged: Fully Engaged, Consistent Viewers, One-Week Engaged, Two-Week Engaged, and Sporadic users. Assessment behaviours and scores are then examined within each cluster, and found different between clusters. Nonparametric statistical test, Kruskal-Wallis yielded a significant difference between user behaviour in each cluster. To make accurate inferences about what occurs in a MOOC, a first step is to understand the patterns of user behaviour. The latent characteristics that contribute to user behaviour must be explored in future research. Keywords: MOOCs, Learning Analytics, Assessment

User clusters, click streams and barriers on Germany`s public reporting portal Weisse Liste.de

User clusters, click streams and barriers on Germany`s public reporting portal Weisse Liste.de

Profiling Online Social Behaviors for Compromised Account Detection

Account compromization is a serious threat to users of online social networks (OSNs). While relentless spammers exploit the established trust relationships between account owners and their friends to efficiently spread malicious spam, timely detection of compromised accounts is quite challenging due to the well established trust relationship between the service providers, account owners, and their friends. In this paper, we study the social behaviors of OSN users, i.e., their usage of OSN services, and the application of which in detecting the compromised accounts. In particular, we propose a set of social behavioral features that can effectively characterize the user social activities on OSNs. We validate the efficacy of these behavioral features by collecting and analyzing real user clickstreams to an OSN website. Based on our measurement study, we devise individual user’s social behavioral profile by combining its respective behavioral feature metrics. A social behavioral profile accurately reflects a user’s OSN activity patterns. While an authentic owner conforms to its account’s social behavioral profile involuntarily, it is hard and costly for impostors to feign. We evaluate the capability of the social behavioral profiles in distinguishing different OSN users, and our experimental results show the social behavioral profiles can accurately differentiate individual OSN users and detect compromised accounts.

Exploring latent browsing graph for question answering recommendation

In this paper, we develop a framework of Question Answering Pages (referred to as QA pages) recommendation. Our proposed framework consists of the two modules: the off-line module to determine the importance of QA pages and the on-line module for on-line QA page recommendation. In the off-line module, we claim that the importance of QA pages could be discovered from user click streams. If the QA pages are of higher importance, many users will click and spend their time on these QA pages. Moreover, the relevant relationships among QA pages are captured by the browsing behavior on these QA pages. As such, we exploit user click streams to model the browsing behavior among QA pages as QA browsing graph structures. The importance of QA pages is derived from our proposed QA browsing graph structures. However, we observe that the QA browsing graph is sparse and that most of the QA pages do not link to other QA pages. This is referred to as a sparsity problem. To overcome this problem, we utilize the latent browsing relations among QA pages to build a QA Latent Browsing Graph. In light of QA latent browsing graph, the importance score of QA pages (referred to as Latent Browsing Rank) and the relevance score of QA pages (referred to as Latent Browsing Recommendation Rank) are proposed. These scores demonstrate the use of a QA latent browsing graph not only to determine the importance of QA pages but also to recommend QA pages. We conducted extensive empirical experiments on Yahoo! Asia Knowledge Plus to evaluate our proposed framework.

Characterizing the file hosting ecosystem: A view from the edge

We present a comprehensive, longitudinal characterization study of the file hosting ecosystem using HTTP traces collected from a large campus network over a one-year period. We performed detailed multi-level analysis of the usage behavior, infrastructure properties, content characteristics, and user-perceived performance of the top five services in terms of traffic volume, namely RapidShare, Megaupload, zSHARE, MediaFire, and Hotfile. We carefully devised methods to identify user clickstreams in the HTTP traces, including the identification of free and premium user instances, as well as the identification of content that is split into multiple pieces and downloaded using multiple transactions. Throughout this characterization, we compare and contrast these services with each other as well as with peer-to-peer file sharing and other media sharing services.

A Genetic Programming Framework for Topic Discovery from Online Digital Library

Various topic extraction techniques for digital libraries have been proposed over the past decade. Generally the topic extraction system requires a large number of features and complicated lexical analysis. While these features and analysis are effective to represent the statistical characteristics of the document, they didn't capture the high level semantics. In this paper, we present a new approach for topic extraction. Our approach combines user's click stream data with traditional lexical analysis. From our point of view, the user's click stream directly reflects human understanding of the high-level semantics in the document. Furthermore, a simple, yet effective, piecewise linear model for topic evolution is proposed. We apply genetic algorithm to estimate the model and extract topics. Experiments on the set of US congress digital library documents demonstrate that our approach achieves better accuracy for the topic extraction than traditional methods.

Identifying web navigation behaviour and patterns automatically from clickstream data

A user's clickstream, such as that which is found in server-side logs, can be a rich source of data concerning the ways in which a user navigates a site, but the volume and level of detail found in these logs makes it difficult to identify and categorise specific navigational patterns. In this paper, we describe the three-step automatic pattern discovery (APD) method, a tool that utilises sequential mining to extract a user's navigation route based on two levels of basic navigational elements. This paper contains descriptions of two studies in which the APD was used; the first makes use of APD to analyse the usage of an educational website; the second describes how APD was used to improve the design of a technical support website in a university department.

Personalised online sales using web usage data mining

Practically every major company with a retail operation has its own web site and online sales facilities. This paper describes a toolset that exploits web usage data mining techniques to identify customer Internet browsing patterns. These patterns are then used to underpin a personalised product recommendation system for online sales. Within the architecture, a Kohonen neural network or self-organizing map (SOM) has been trained for use both offline, to discover user group profiles, and in real-time to examine active user click stream data, make a match to a specific user group, and recommend a unique set of product browsing options appropriate to an individual user. Our work demonstrates that this approach can overcome the scalability problem that is common among these types of system. Our results also show that a personalised recommender system powered by the SOM predictive model is able to produce consistent recommendations.

Supporting global user profiles through trusted authorities

Personalization generally refers to making a Web site more responsive to the unique and individual needs of each user. We argue that for personalization to work effectively, detailed and interoperable user profiles should be globally available for authorized sites, and these profiles should dynamically reflect the changes in user interests.Creating user profiles from user click-stream data seems to be an effective way of generating detailed and dynamic user profiles. However a user profile generated in this way is available only on the computer where the user accesses his browser, and is inaccessable when the same user works on a different computer. On the other hand, the integration of Internet with telecommunication networks have made it possible for the users to connect to Web with a variety of mobile devices as well as desk tops. This requires that user profiles should be available to any desktop or mobile device on the Internet that users choose to work with.In this paper, we address these problems through the concept of "Trusted Authority". A user agent at the client side that captures the user click stream, dynamically generates a navigational history 'log' file in Extensible Markup Language (XML). This log files is then used to produce the 'user profiles' in Resource Description Framework (RDF). User's right to privacy is provided through the Platform for Privacy Preferences (P3P) standard. User profiles are uploaded to the trusted authority and served next time the user connects to the Web.The trusted authority concept, serving as a namespace qualifier, provides globally unique userid/password identification for users. Furthermore user profiles dynamically reflect the changes in their interests since the data generated while they are surfing the Web contribute to their profile. Also since the user profiles are defined in RDF, they are interoperable and available to any type of authorized device on the Internet.

LARGE-SCALE MINING, DISCOVERY AND VISUALIZATION OF WWW USER CLICKPATHS

Analysis of user clickstreams on the World Wide Web is made challenging by the volume of data and the difficulty of visualizing millions of different navigation paths. We present a method for identifying user clickpaths which scales well on large amounts of data, and provides an intuitive and insightful visual representation of user activity. Our technique borrows from the data mining literature on association rules and the computer graphics literature on graph layout optimization. The method is demonstrated with data from two commercial sources and paints a fascinating picture of web activity.