Search

Web Navigation Prediction is a popular area of research as users on the web are continuously growing. Capturing users’ behavior provides insights about the user demands, accessibility patterns, and inconsistencies in the website design. Several navigation models have been developed in the past. Most of the models rely upon fixed threshold mechanism for prediction, which is inadequate as they require multiple computational steps which not necessarily give the best possible value. To combat this issue, we propose two models based on dynamic thresholds: All-Kth Modified Markov Model based on Geometric threshold (KMMMG) and (b) All-Kth Modified Markov Model based on Branching Factor Threshold (KMMMBF). Our experiments show that longer navigations are rare and are highly co-related. However, smaller navigations are more and are less co-related. Dynamic threshold models produce more optimum predictions as compare to fixed threshold models. KMMMBF performs the best and achieves the highest prediction accuracy, 78.53%, 91.32%, and 61.37% on CTI, MSWEB, and BMS dataset, respectively.

With the commoditization of private data, data trading in consideration of user privacy protection has become a fascinating research topic. The trading for private web browsing histories brings huge economic value to data consumers when leveraged by targeted advertising. And the online pricing of these private data further helps achieve more realistic data trading. In this paper, we study the trading and pricing of multiple correlated queries on private web browsing history data at the same time. We propose CTRADE , which is a novel online data CommodiTization fRamework for trAding multiple correlateD queriEs over private data. CTRADE first devises a modified matrix mechanism to perturb query answers. It especially quantifies privacy loss under the relaxation of classical differential privacy and a newly devised mechanism with relaxed matrix sensitivity, and further compensates data owners for their diverse privacy losses in a satisfying manner. CTRADE then proposes an ellipsoid-based query pricing mechanism according to a given linear market value model, which exploits the features of the ellipsoid to explore and exploit the close-optimal dynamic price at each round. In particular, the proposed mechanism produces a low cumulative regret, which is quadratic in the dimension of the feature vector and logarithmic in the number of total rounds. Through real-data based experiments, our analysis and evaluation results demonstrate that CTRADE balances total error and privacy preferences well within acceptable running time, indeed produces a convergent cumulative regret with more rounds, and also achieves all desired economic properties of budget balance, individual rationality, and truthfulness.

The increasing importance of online distribution channels is paralleled by a rising interest in gaining insights into the customer journey and browsing behavior. We evaluate several machine learning methods (latent Dirichlet allocation, correlated topic model, structural topic model, replicated softmax model) with respect to their ability to reproduce the browsing behavior of households across websites. In addition, we compare these machine learning methods to a related classical technique, singular value decomposition. In our study, the replicated softmax model outperforms latent Dirichlet allocation, but the correlated topic model attains the overall best performance. Compared to singular value decomposition both the correlated topic model and the replicated softmax model lead to a more efficient compression of web browsing data. On the other hand, singular value decomposition surpasses latent Dirichlet allocation. We interpret results of the correlated topic model and the replicated softmax model by determining combinations of topics or hidden variables that are heterogeneous with respect to visited websites. We show that decision makers should not rely on bivariate measures of site visits, as these do not agree with measures of interdependences between sites that can be inferred from the correlated topic model or the replicated softmax model. We investigate how well topics or hidden variables measured by these methods predict yearly household expenditures. The correlated topic model leads to the best predictive performance, followed by the replicated softmax model. We also discuss how the replicated softmax model can be used to support online marketing decisions of websites.

To enable targeted ads, companies profile Internet users, automatically inferring potential interests and demographics. While current profiling centers on users' web browsing data, smartphones and other devices with rich sensing capabilities portend profiling techniques that draw on methods from ubiquitous computing. Unfortunately, even existing profiling and ad-targeting practices remain opaque to users, engendering distrust, resignation, and privacy concerns. We hypothesized that making profiling visible at the time and place it occurs might help users better understand and engage with automatically constructed profiles. To this end, we built a technology probe that surfaces the incremental construction of user profiles from both web browsing and activities in the physical world. The probe explores transparency and control of profile construction in real time. We conducted a two-week field deployment of this probe with 25 participants. We found that increasing the visibility of profiling helped participants anticipate how certain actions can trigger specific ads. Participants' desired engagement with their profile differed in part based on their overall attitudes toward ads. Furthermore, participants expected algorithms would automatically determine when an inference was inaccurate, no longer relevant, or off-limits. Current techniques typically do not do this. Overall, our findings suggest that leveraging opportunistic moments within pervasive computing to engage users with their own inferred profiles can create more trustworthy and positive experiences with targeted ads.

Being on endpoints, Content Providers can easily evaluate end users’ Web browsing quality of experience (Web QoE) by accessing in-browser computed application-level metrics. Because of end-to-end traffic encryption, it is becoming considerably harder for Internet Service Providers (ISPs) to evaluate the Web QoE of their customers, which is important for management purposes. In this paper, we propose data-driven machine learning techniques and exact flow-level algorithmic methods to infer well-known application-level Web performance metrics (such as SpeedIndex and Page Load Time) from raw encrypted streams of network traffic. We prove the efficiency of our approach taking as input a unique dataset of more than 200,000 experiments, targeting a large set of popular pages (Alexa top-500), from probes from several ISPs networks, with different browsers (Chrome, Firefox) and viewport combinations. Results show that our data-driven models are not only accurate for several Web performance metrics, but also feature the ability to generalize to previously unseen conditions. Furthermore, we discuss how our extremely lightweight flow-level method has a provable accuracy on a specific metric, and is thus of particular appeal from a deployment viewpoint.

With more than seven billion people actively using the Internet, the number of cyber attacks has increased, and personal data breaches have become a concern among the general public. The COVID-19 pandemic has only increased the use of online platforms and services for work and leisure activities, which opens the door to more scams, viruses, and other cyber security breaches. Guided by SEO techniques and research regarding dangerous website and domain patterns, we have designed and implemented a visual system that tracks suspicious links on an active webpage and marks them in order to alert users to proceed with caution. Our AI utilizes linear regression to best detect trends in URL parsing, comparing them with registered unsafe links to see if they pose similar threats. The results reveal that AI isn’t entirely accurate since some trends are hard to decipher; however, it can reliably flag certain redirects and out-of-domain links that would otherwise remain hidden to users.

Nowadays, a lot of data mining applications, such as web traffic analysis and content popularity prediction, leverage users’ web browsing trajectories to improve their performance. However, the disclosure of web browsing trajectory is the most prominent issue. A novel privacy model, named Differential Privacy, is used to rigorously protect user’s privacy. Some works have applied this privacy model to spatial-temporal streams. However, these works either protect the users’ activities in different places separately or protect their activities in all places jointly. The former one cannot protect trajectories that traverse multiple places; while the latter ignores the differences among places and suffers the degradation of data utility (i.e., data accuracy). In this paper, we propose a w , n -differential privacy to protect any spatial-temporal sequence occurring in w successive timestamps and n -range places. To achieve better data utility, we propose two implementation algorithms, named Spatial-Temporal Budget Distribution (STBD) and Spatial-Temporal RescueDP (STR). Theoretical analysis and experimental results show that these two algorithms can achieve a balance between data utility and trajectory privacy guarantee.

Webpages have become increasingly complex in recent years, with longer loading times to match. This paper uses tailored edge computing to address this issue. As is customary, A grip server interacts with cloud web servers in edge computing. In A footing server, on the other hand, is a personalised edge computing system. referred to as a foothold The Server in the Middle (ESM) collaborates with other servers. users' cell phones This research focuses on two strategies based on personalised edge computing: edge aided caching and edge aided reprioritizing. Edge-assisted caching decreases the time it takes for a page to load. Because an ESM saves the cached data on mobile devices, So far, we've got components. Edge helps in the reprioritization of forces on the internet. browser to show visual components earlier and lowers the amount of white space Time spent in front of a screen.In addition, the ESM uses HTTP/2 rather than HTTP/1.1. This decreases the number of interactions between a mobile device and, as a result, the ESM, allowing advanced functionalities to be used. such as priority and server push Edge-assisted caching has been implemented. built in a high-end PC for Google's web browser Chrome for Android is a mobile web browser. Edge aided in an experiment, according to the results. The time it took for a popular website to load was cut in half because to caching. 59 percent in a network that is extremely congested. Another experiment found that edge-assisted reprioritization cut the white screen time of a webpage with a lot of photo photos by 21%. edge computing, reprioritization, mobile device, index terms browsing the web, caching

The Mobile intermittent wireless connectivity limits the evolution of the mobile landscape, such that this progress coupled with the ubiquitous nature of the Internet and the web services. The web service Reliability achieves the low overhead communication and retrieves the appropriate state response from the web service consumption. This paper discusses and analyzes the most recent approaches that achieve the reliability of web services consumed by mobile devices. Achieving the reliable web service consumption istended to two approaches: Middleware approach and Mobile Agent(MA) approach. Both of them focus on ensuring the request execution under the communication limitations and services temporary unavailability., 2015 IEEE Seventh International Conference on Intelligent Computing and Information Systems (ICICIS). IEEE, 2015. arXiv admin note: substantial text overlap with arXiv:2207.12404, arXiv:2207.11608

Purpose The Web has become an indispensable medium used by people across the world for education, information, entertainment, social interaction as well as for various daily activities involving shopping and employment-related tasks. It is therefore becoming increasingly essential that the Web must be accessible to all people to provide equal access and equal opportunity. This is specifically more important for people with various kind of disabilities. Several initiatives such as development of Web accessibility guidelines, tools and technologies have been undertaken to make the Web usable for people with different disabilities. However, only a handful of them are aimed at people with Severe Speech and Motor Impairment (SSMI). This paper aims to present a Web browsing interface for people with severe speech and motor impairment. Design/methodology/approach The browser allows easy dissemination of information through World Wide Web for people with SSMI. The browser is augmented with both automatic as well as manual scanning mechanisms through which a motor disorder person can access the browser graphical user interface (GUI). Further, the browser provides an intelligent content scanning mechanism through which the Web contents can be accessed with less time and cognitive effort. Along with the desktop version, WebSanyog is successfully ported on Android-based tablets to make the system portable. Findings The system has been exhaustively field tested by people with SSMI. The browser has been deployed at the Indian Institute of Cerebral Palsy (IICP), Kolkata. The performance of the browser has been measured in terms of three parameters: The Task execution time (TET); Error rates analysis (ER); and Overall usability score by the subject. The evaluation results suggests that the proposed Web browsing interface is effective in terms of task execution time, cognitive effort and overall user satisfaction. Originality/value The browser GUI is integrated with an automatic scanning mechanism as an alternate way to access and navigate through Web pages, instead of using keyboard and mouse. The browser provides novel content access mechanisms that makes navigating through Web page contents like links, images and embedded videos easier and faster. To facilitate text entry, the browser provides two different options, namely, the predictive virtual scanning keyboard and a novel icon-based query entry scheme that allows generating search queries through the selection of multiple icons.

Low vision care and rehabilitation is often limited by access to assistive devices, especially in low-resourced countries, due to their high cost and unavailability. Smartphones have the potential to serve as an alternative assistive device for people living with severe visual impairment and blindness (SVIB). This study aims to investigate the use of smartphones among people living with SVIB. The study was a cross-sectional study of 166 people living with SVIB in a low resourced setting. The participants were recruited from two tertiary institutions and four eye care facilities. A questionnaire was administered to all respondents and for those who could not read prints they were read out to them and their responses recorded. The majority of respondents (n = 88, 53.1%) either had no phone or used a basic phone. The prevalence of smartphone usage among people living with SVIB was found to be 46.90% (n = 78). Most respondents use their smartphones to interact on social media [n = 75 (96%)] and web browsing [n = 69,92%]. The most frequently demanded [n = 22 (44%)] smartphone functionality by the respondents was the image and color description feature. Most participants were unaware that 90% of their functionality demands already existed and were compatible with current smartphones. A significant number of people living with SVIB in this study used smartphones; however, most users are unaware of its full functionality and assistive capabilities.

Current information recommendation systems obtain users’ preferences from Web browsing histories and activities such as purchase of products, and efficiently provide the users with their preferable information. In such a case, however, the same or similar information is always recommended, which is called filter bubble and it decreases the users’ satisfaction to the systems. If information recommendation systems could provide users with something surprising and useful as output information, the user’s satisfaction to the systems would drastically increase. Therefore, “serendipity” is paid attention to in this research. In this paper, a new information recommendation system using a concept-based information retrieval is proposed to provide the users with serendipitous information. In this system, concepts which describe features or roles of items are input instead of the items themselves, and information which can meet the concepts are output as candidates of serendipitous information. The serendipitous information is extracted from the output information using the criteria which are the indexes of serendipity defined in this research. Through the evaluation experiment, it is revealed that the proposed system achieves the accuracy of 70% for the serendipitous information determination and the accuracy of 100% for the information retrieval, which are satisfactory for this research purpose.

Analytics provides insight to people based on the analytics of past usage by using techniques such as statistics, data mining, machine learning and artificial intelligence. Lack of monitoring system of browsing causes low engagements that reduce the growth of certain businesses caused by unnecessary browsing for students learning time. This paper presents an analysis on browsing behavior that classifies browsed words followed their ethical word-groups browsing. An Analytic platform is created as a monitoring system of browsing behavior. Data mining, indexing and classification method are used in this research as data is the essential key of creating a predictive model and four types of ethical groups have been filtered based on the browsing behaviors. The browsed words are categorized into four types of browsing called queries, applications, social media, Campus-related sites. The research method uses software tools and data mining process on the browsing data and analytics is presented on the development of the dashboard mainly using the R programming language. Few unethical words using the indexing method are generated in analytic graphs based on the type of browsing versus time. Data collected from the browsing behaviors of students’analysis taken from browsing database of personal computer and laboratory computer in the campus network. The result shows that othercategories are the highest categories which reached79.6% for personals' computer browsing compared to72.4% browsing at the laboratory computers. It is identified that about 21% of the browsing behavior was filtered during the data mined processed. The other category is still on the research portfolio where these libraries must be filtered in detail to identify whether they are learning or non-learning activities. This research is significant in that helps to increase the effectiveness of suggestions applications, optimize the internet usage by blocking unnecessary words or webpages, and even campus guide systems by monitoring the surrounding browsing behavior of the students’ usages of the campus network computer labs.

The pervasive penetration of mobile smart devices has significantly enriched Internet applications and undoubtedly reshaped the way that users access Internet services. Different from traditional desktop applications, mobile Internet applications require users to input via touch screens and view outputs on the displays with considerably limited size. The significant conflict between the limited-size of touch screens and the richness of online media contents widely exists in dynamic-viewport mobile applications, a class of mobile Internet applications that download contents beyond the user's viewing region (referred to as viewport ). As dynamic-viewport mobile applications usually use HTTP for content downloading, to improve their quality of experience (QoE) and cost efficiency, in this paper, we present a Mobile-Friendly HTTP middleware (MF-HTTP), which can interpret user touch screen inputs and optimize the HTTP downloading of media objects for such applications. We first demystify screen scrolling in mobile operating systems and precisely break down the viewport moving process. We identify the key influential factors for media object downloading and develop an optimal download scheme. Towards building a practical middleware, we further discuss and address the implementation issues in detail. We implement a MF-HTTP prototype based on Android platforms and evaluate the performance of MF-HTTP by conducting concrete case studies on two representative dynamic-viewport mobile applications, namely, web browsing and 360-degree video streaming.

Network traffic analysis has been increasingly used in various applications to either protect or threaten people, information, and systems. Website fingerprinting is a passive traffic analysis attack which threatens web navigation privacy. It is a set of techniques used to discover patterns from a sequence of network packets generated while a user accesses different websites. Internet users (such as online activists or journalists) may wish to hide their identity and online activity to protect their privacy. Typically, an anonymity network is utilized for this purpose. These anonymity networks such as Tor (The Onion Router) provide layers of data encryption which poses a challenge to the traffic analysis techniques. Although various defenses have been proposed to counteract this passive attack, they have been penetrated by new attacks that proved the ineffectiveness and/or impracticality of such defenses. In this work, we introduce a novel defense algorithm to counteract the website fingerprinting attacks. The proposed defense obfuscates original website traffic patterns through the use of double sampling and mathematical optimization techniques to deform packet sequences and destroy traffic flow dependency characteristics used by attackers to identify websites. We evaluate our defense against state-of-the-art studies and show its effectiveness with minimal overhead and zero-delay transmission to the real traffic.

The problem of finding relevant data while searching the internet represents a big challenge for web users due to the enormous amounts of available information on the web. These difficulties are related to the well-known problem of information overload. In this work, we propose an online web assistant called OWNA. We developed a fully integrated framework for making recommendations in real-time based on web usage mining techniques. Our work starts with preparing raw data, then extracting useful information that helps build a knowledge base as well as assigns a specific weight for certain factors. The experiments show the advantages of the proposed model against alternative approaches.

We measure the data sent to their back-end servers by five browsers: Google Chrome, Mozilla Firefox, Apple Safari, Brave Browser and Microsoft Edge, during normal web browsing on both desktop and mobile devices. Our aim is to assess the privacy risks associated with this data exchange between a browser and its back-end servers. With regard to shared services, all of the browsers make use of a safe browsing service to mitigate phishing attacks and our measurements indicate that this raises few privacy concerns. Similarly, with regard to the Chrome extension update service accessed by Chromium-base browsers (Chrome, Brave, Edge). Overall, we find that both the desktop and mobile versions of Brave do not use any identifiers allowing tracking of IP address over time, and do not share details of web pages visited with backend servers. In contrast, Chrome, Firefox, Safari and Edge all share details of web pages visited with backend servers. Additionally, Chrome, Firefox and Edge all share long-lived identifiers that can be used to link connections together and so potentially allow tracking over time. In the case of Edge these are device and hardware identifiers that are hard/impossible for users to change. On mobile devices, but not desktop devices, Firefox also shares device identifiers.

As cloud service becomes more and more capable, available and powerful, wiseCIO has emerged from an innovative roadmap toward archival Content Management Service (aCMS) and massive Content Delivery Service (mCDS) in support of Anything-as-a-Service (XaaS) via Digital Archiving and Transformed Analytics (DATA); DATA aims to automate UBC with FAST solutions throughout a feasible, analytical, scalable and testable approach. This paper, based on the novel wiseCIO (web-based intelligent service engaging Cloud Intelligence Outlet), presents digital archiving and transformed analytics via machine learning automata for intelligent UBC processes to liaise with Universal interface for human-computer interaction, enable Brewing aggregation (differing from traditional web browsing), and engage Centered user experience. As one of the most practical aspects of artificial intelligence, machine learning is applied to analytical model building and massive and/or multidimensional Online Analytical Processing (mOLAP) for more intelligent cloud service with little explicit coding required. DATA is central to useful information via archival transformation and analytics, and utilizable intelligence for Business, Education and Entertainment (iBEE) in support of decision-making. As a result, DATA orchestrates wiseCIO to promote ACTiVE XaaS that enables accessibility, contextuality and traceability of information for vast engagement with various cloud services, such as aCMS (archival Content Management Service), COSA (Context-Oriented Screening Aggregation), DASH (Deliveries Assembled for fast Search and Hits), OLAS (Online Learning via Analytical Synthesis), REAP (Rapid Extension and Active Presentation), and SPOT (Special Points On Top) with great ease.

While working from home is not a new concept, the advent of the Covid-19 pandemic has, for many in the workforce, rendered it the ‘new normal’, concomitant with enhanced use of workplace surveillance technologies to monitor and track staff working from home. Even prior to the global pandemic, organisations were increasingly using a variety of electronic surveillance methods to monitor their employees and the places where they work, whether it be in an office building or remotely. This technology traverses various facets of the work environment, including email communications, web browsing, the use of active badges for locating and tracking employees, and the gathering of personal information by employers. The application of these technologies, nevertheless, raises privacy concerns, which are exacerbated when work is undertaken in employees’ own homes, a phenomenon that has become more prevalent due to Covid-19. This article addresses the issue of electronic workplace monitoring, its implications for employees’ privacy and the role of collective bargaining in addressing this emergent practice, which has also been given new impetus during the pandemic.

Mobile devices have become the primary mode of Internet access. Yet, differences in mobile hardware resources, such as device memory, coupled with the rising complexity of Web pages can lead to widely different quality of experience for users. In this work, we analyze how device memory usage affects Web browsing performance. We quantify the memory footprint of popular Web pages over different mobile devices, mobile browsers, and Android versions, analyze the induced memory distribution across different browser components (e.g., JavaScript engine and compositor), investigate how performance gets impacted under memory pressure and propose optimizations to reduce the memory footprint of Web browsing. We show that these optimizations can improve performance and reduce chances of browser crashes in low memory scenarios.

Objectives To assess the quantity and type of vaccine-related information Americans consume online and its relationship to social media use and attitudes toward vaccines. Methods Analysis of individual-level web browsing data linked with survey responses from representative samples of Americans collected between October 2016 and February 2019. Results We estimate that approximately 84% of Americans visit a vaccine-related webpage each year. Encounters with vaccine-skeptical content are less frequent; they make up only 7.5% of vaccine-related pageviews and are encountered by only 18.5% of people annually. However, these pages are more likely to be published by untrustworthy sources. Moreover, skeptical content exposure is more common among people with less favorable vaccine attitudes. Finally, usage of online intermediaries is frequently linked to vaccine-related information exposure. Google use is differentially associated with subsequent exposure to non-skeptical content, whereas exposure to vaccine-skeptical webpages is associated with usage of webmail and, to a lesser extent, Facebook. Conclusions Online exposure to vaccine-skeptical content is relatively rare, but vigilance is required given the potential for exposure among vulnerable audiences.

Many researchers have proposed a causal link between low domain knowledge and disorientation in hypertext. Our objective was to challenge this hypothesis, examining other variables that might have an influence, such as design, reading instructions, or working memory capacity. We analysed navigation patterns and comprehension scores in a sample of low topic knowledge undergraduate students (N = 45) who were assigned to one of three hypertext conditions: reading for a test, reading to write a summary, and elaborative interrogation. Another sample (N = 45) of low knowledgeable undergraduate students were used as a control group, performing the same tasks using printed texts. Regarding disorientation, and contrasting with previous research, only a minority of students became disoriented in hypertext. Neither reading instructions nor working memory capacity had the expected impact on readers’ behaviour or outcomes, so hypertext design might be a key aspect on explaining disorientation. Implications for hypertext design and education are discussed. Implications for practice or policy: The general assumption of low prior knowledge readers becoming disoriented in hypertext is falsified. Educational hypertext designers should always consider hypertext structure, graphical overviews, and usability elements. Educators must be aware that novices may show difficulties to adapt their learning behaviour to different reading goals.