Create User Profiles Research Articles

A Survey on User Profiling, Data Collection, and Privacy Issues of Internet Services

Users are usually required to share several types of data, including their personal data, as different providers strive to offer high-quality services that are often tailored to end-users’ preferences. However, when it comes to personalizing services, there are several challenges for meeting user’s needs and preferences. For content personalization and delivery of services to end users, services typically create user profiles. When user profiles are created, user data is collected and organized to meet the personalization requirements of the services. In this paper, we provide an overview of current research activities that focus on user profiling and ways to protect user data privacy. The paper presents different types of data that services collect from users on examples of commonly used Internet services. It proposes data categorization as a prerequisite for controlled data sharing between users and Internet services. Furthermore, it discusses how data generalization can be used for anonymization purposes on examples of the proposed data categories. Finally, it gives an overview of the privacy framework being developed and gives guidelines for future work focusing on data generalization methods in order to reduce user privacy risks.

Simulation of E-learning video recommendation based on virtual reality environment on English teaching platform

E-learning video is an effective teaching tool, and virtual reality technology can enhance the learning experience. However, the current English teaching platform lacks the personalized and real-time feedback video recommendation system. Therefore, this study proposes an E-learning video recommendation system based on virtual reality environment, which aims to provide a personalized, interactive and real-time feedback learning experience. In this paper, the prototype of E-learning video recommendation system based on virtual reality environment is designed, and the simulation experiment is carried out on the English teaching platform. In the environment of the E-learning platform, human–computer interaction and entertainment media can enhance students’ learning process and assist in teaching work. This article analyzes the simulation of E-learning video recommendation based on virtual reality environment on English teaching platforms. The E-learning video recommendation system can create user profiles on the website based on their basic information and behavior, fully tap into their preferences, and provide personalized learning services for them. The recommendation system can be divided into two parts: offline and online. Offline systems are mainly responsible for creating video related content, while online systems store data in databases, allowing for real-time investigation and retrieval of data; Online systems can respond to user requests in real-time, and combining online extraction with user behavior analysis can generate the final recommendation results. While constructing an artificial intelligence platform for English teaching, it is also necessary to propose application strategies for English teaching and achieve modernization of curriculum teaching.

Recommendation System Using Speech Recognition By Creating User Profiles

Recommendation System Using Speech Recognition By Creating User Profiles

Digital Transformation of Advertising: Trends, Strategies, and Evolving User Preferences in Online Advertising

This study discusses the evolving trends in online advertising, diverse marketing models, and changing user needs. From the early development of the Internet, especially in the early 1990s, to the emergence of numerous advertising formats, online advertising has become an integral part of modern marketing. Different types of online advertisements, such as banner ads, pop-up ads, video ads, native ads, search engine ads, and social media ads, fulfill different needs of advertisers. In addition, the study also explores diverse marketing models for online advertising, including pay-per-click, pay-per-thousand-displays, pay-per-action, affiliate marketing, targeted ads, and video ads, which provide more choices for advertisers. In terms of user characteristics and needs, as technology continues to evolve, user reliance on mobile devices increases, the use of ad-blocking and anti-advertising technologies rises, concerns about data privacy increase, social media becomes an important channel for advertising, and data analytics and ad-tracking technologies become increasingly critical. A user’s age, gender, geographic location, interests, purchase history, device and platform, social interactions, and privacy preferences are important in creating user profiles and target market analysis. In summary, online advertising plays a key role in the modern marketplace, providing advertisers with global advertising opportunities and the need to continually adapt to market and technological changes to maximize ad effectiveness.

Enhancing Recommender Systems with Semantic User Profiling through Frequent Subgraph Mining on Knowledge Graphs

Recommender systems play a crucial role in personalizing online user experiences by creating user profiles based on user–item interactions and preferences. Knowledge graphs (KGs) are intricate data structures that encapsulate semantic information, expressing users and items in a meaningful way. Although recent deep learning-based recommendation algorithms that embed KGs have demonstrated impressive performance, the richness of semantics and explainability embedded in the KGs are often lost due to the opaque nature of vector representations in deep neural networks. To address this issue, we propose a novel user profiling method for recommender systems that can encapsulate user preferences while preserving the original semantics of the KGs, using frequent subgraph mining. Our approach involves creating user profile vectors from a set of frequent subgraphs that contain information about user preferences and the strength of those preferences, measured by frequency. Subsequently, we trained a deep neural network model to learn the relationship between users and items, thereby facilitating effective recommendations using the neural network’s approximation ability. We evaluated our user profiling methodology on movie data and found that it demonstrated competitive performance, indicating that our approach can accurately represent user preferences while maintaining the semantics of the KGs. This work, therefore, presents a significant step towards creating more transparent and effective recommender systems that can be beneficial for a wide range of applications and readers interested in this field.

Perception based User Profiles for Web Personalization

Personalized web services reduce the burden of information overload by collecting facts that match the needs of the user. An important aspect of personalized web services is the creation of user profiles that contain user information and settings. This article introduces a unique method called Perception-Based User Profiles (PUP) based on perception and browsing order, develops and updates user profiles. User profiles include perceptions and relationships, which can help guarantee that user interests are represented semantically. Second, when calculating the perception and duration of the relationship, for each site in a session, the user's browsing order is considered. Third, cognitive psychometric memory model is used to update the user profile's perceptions and relationships at the end of each session, ensuring the user profile's dynamics. The results of the tests suggest that this strategy works well for building and updating user profiles.

Cookiepocalypse: What are the most effective strategies for advertisers to reshape the future of display advertising?

A third-party cookie is a tracking code set by a third-party platform or a technology provider on the website the user is visiting. This small amount of text identifies users online, reveals their interests, and provides powerful information useful in enhancing online display advertising. With the passing of new legislation protecting the user's privacy, the phasing out of third-party cookies has started. By the end of 2024, all major browsers will block all third-party cookies and identifiers for advertiser (IDFA) tracking. Therefore, advertisers and marketers are becoming more restricted in their ability to create user profiles, personalize ads, and analyze performances. Advertisers need to start pivoting now to prepare for what is next. In that context, the purpose of this study is to investigate different alternatives and forecast technological progress to help advertisers implement the most appropriate strategies and technologies to effectively overcome the disappearance of third-party cookies. By conducting two qualitative studies, semistructured interviews with 15 experts and a focus group, we established a framework that categorizes the alternative strategies into six categories as well as the technological progress made by different actors in the value chain. The study has strong implications for advertisers and policy-makers.

Knowledge Discovery from Library Automation via Bibliomining using the Apriori Algorithm

Today which is called as the digital age with the considerably developing information systems, the constant increase in the data amount being recorded has revealed the concept of big data. Obtaining the strategic information which is crucial for decision-makers especially in managerial terms is only possible through processing these big data with accurate techniques. Data mining techniques have frequently been used in recent years in order to reach meaningful and useful knowledge among data stacks. In this study, the Apriori Algorithm was used for the managers of university library information systems, which provide data-oriented service, to make investment decisions in the future effectively and create user profiles. Within the scope of the study, an application was performed on the basis of an information system comprising of real data of Erzincan Binali Yıldırım University Central Library. By means of association rules, which are one of the descriptive models of data mining, ten different association rules regarding the joint borrowing of publications were applied and results were obtained in the confidence intervals of 57.1% and 95.8%. In addition, information such as library inventory, member profile, and publication borrowing habits were obtained and evaluations were made in line with this information at the end of the study.

Real-time recommendations for energy-efficient appliance usage in households.

According to several studies, the most influencing factor in a household's energy consumption is user behavior. Changing user behavior to improve energy usage leads to efficient energy consumption, saving money for the consumer and being more friendly for the environment. In this work we propose a framework that aims at assisting households in improving their energy usage by providing real-time recommendations for efficient appliance use. The framework allows for the creation of household-specific and appliance-specific energy consumption profiles by analyzing appliance usage patterns. Based on the household profile and the actual electricity use, real-time recommendations notify users on the appliances that can be switched off in order to reduce consumption. For instance, if a consumer forgets their A/C on at a time that it is usually off (e.g., when there is no one at home), the system will detect this as an outlier and notify the consumer. In the ideal scenario, a household has a smart meter monitoring system installed, that records energy consumption at the appliance level. This is also reflected in the datasets available for evaluating such systems. However, in the general case, the household may only have one main meter reading. In this case, non-intrusive load monitoring (NILM) techniques, which monitor a house's energy consumption using only one meter, and data mining algorithms that disaggregate the consumption into appliance level, can be employed. In this paper, we propose an end-to-end solution to this problem, starting with the energy disaggregation process, and the creation of user profiles that are then fed to the pattern mining and recommendation process, that through an intuitive UI allows users to further refine their energy consumption preferences and set goals. We employ the UK-DALE (UK Domestic Appliance-Level Electricity) dataset for our experimental evaluations and the proof-of-concept implementation. The results show that the proposed framework accurately captures the energy consumption profiles of each household and thus the generated recommendations are matching the actual household energy habits and can help reduce their energy consumption by 2–17%.

СОВРЕМЕННЫЕ ПРАКТИКИ АНГЛОЯЗЫЧНОЙ ОНЛАЙН-ЛЕКСИКОГРАФИИ

The study attempts to analyze the current state of English online lexicography evolving in the context of electronic digital technology. The research is based on more than 30 online dictionaries of English and over 30 meta-lexicographic resources using the following methods: theoretical and linguistic analysis of literature, lexicographic analysis and com-parative analysis. The research allowed to define the main concepts and principles underlying modern online dictionar-ies of English, including integration of lexicographic forms and functions, universalization of online dictionary re-sources followed by the expansion of the user audience solving various linguistic problems, optimization of tools for the search and retrieval of information providing for high retrieval rate, relevance and reliability of the data, as well as dictionary ergonomics, intuitiveness of its methods and functions, etc. Online lexicographic resources also find themselves striving for “smartization” seen in the customization of the vocabulary look-up mode and creation of user profiles, compilation of context aware dictionaries embedded in other resources, application of the latest technologies to assess the users’ “lexicographic behavior”, such as eye-tracking and interpretation of user log files. Literature review and online dictionary analysis give grounds to assert that the lexicographic paradigm formed in the second half of the 20th century is being “fine-tuned” in the era of globalization and digitalization: once an automated reference guide with a solid information base, the dictionary is advancing to the level of a dynamically changing, personally configura-ble innovative synergetic resource, thus becoming a user’s full partner in the solution of a large number of tasks related to data reception and generation.

I-Rebound after Stroke-Eat for Health: Mediterranean Dietary Intervention Co-Design Using an Integrated Knowledge Translation Approach and the TIDieR Checklist.

Lifestyle interventions to reduce second stroke risk are complex. For effective translation into practice, interventions must be specific to end-user needs and described in detail for replication. This study used an Integrated Knowledge Translation (IKT) approach and the Template for Intervention Description and Replication (TIDieR) checklist to co-design and describe a telehealth-delivered diet program for stroke survivors. Stroke survivors and carers (n = 6), specialist dietitians (n = 6) and an IKT research team (n = 8) participated in a 4-phase co-design process. Phase 1: the IKT team developed the research questions, and identified essential program elements and workshop strategies for effective co-design. Phase 2: Participant co-design workshops used persona and journey mapping to create user profiles to identify barriers and essential program elements. Phase 3: The IKT team mapped Phase 2 data to the TIDieR checklist and developed the intervention prototype. Phase 4: Co-design workshops were conducted to refine the prototype for trial. Rigorous IKT co-design fundamentally influenced intervention development. Modifications to the protocol based on participant input included ensuring that all resources were accessible to people with aphasia, an additional support framework and resources specific to outcome of stroke. The feasibility and safety of this intervention is currently being pilot tested (randomised controlled trial; 2019/ETH11533, ACTRN12620000189921).

Optimized recommendations by user profiling using apriori algorithm

Collaborative filtering has been the most straightforward and most preferable approach in the recommender systems. This technique recommends an item to a target user from the preferences of top-k similar neighbors. In a sparse data scenario, the recommendation accuracy of the collaborative filtering degrades significantly due to the limitations of existing various similarity measures. Such constraints offer an open scope for enhancing the accuracy of optimized user-specific recommendations. Many techniques have been utilized for this, like Particle Swarm Optimization and other evolutionary collaborative filtering algorithms. The proposed approach utilizes the Apriori algorithm to form users’ profiles from the items’ ratings and categorical attributes. The user profile creation is performed using the apriori algorithm. The profile of each user involves the likes and disliking of categorical characteristics of objects by users. In the collected MovieLens dataset, the efficiency of the proposed recommendation approach is tested. The comparative results show proof that the proposed novel algorithm outperforms other prominent collaborative filtering algorithms on the MovieLens datasets based on rating prediction accuracy.

Overview of Methods to Avoid User Profiling

Nowadays online communication services have obtained a stronger impact in our world. Some companies that provide communication services take advantage of them to create user profiles, which they further use to send undesired advertisements (Ads), or spam, to their users. This article explores several methods, developed based on different areas of knowledge including natural language processing, steganography, cryptography, which can help a user to avoid being profiled while sending and receiving texts over the internet.

Natural Disaster Resilience Approach (NDRA) to Online Social Networks

Numerous disasters impact people around the world, including floods, cyclones, tsunamis and so on. Disaster resilience (recovery) is a realtime challenge. The research goal of the proposed Natural Disaster Resilience Approach (NDRA) is to fasten and automate disaster resilience within the affected region. Prioritization for saving lives must be provided to the region most affected. Currently almost all people use the Online Social Networks (OSNs) to share their daily activities. Actually only their friends in OSN can note the photos posted by OSN users in the disaster-affected region and in turn can support the friends in need. Our research goal is to conduct speedier and prioritized disaster resilience processes by directly addressing honest disaster help requests from images posted by OSN users. To achieve the above goal, we suggest an approach known as the Natural Disaster Resilience Approach (NDRA). The NDRA is a three-tiered framework: Tier-1: sybil(malicious) user avoidance engine: prevents fake OSN user profile creation; Tier-2: ‘D’- attributed image classifier: determines the originality of the images posted and Tier-3: sybil user prediction: uses an Advanced Sybil Node Prediction Algorithm (ASYNPA) to check the authenticity of the user and priorities for faster resilience requests. In NDRA we use Advogato dataset with 6541 users and 51,127 edges. Ultimately, the comparison is only made between the proposed ASYNPA tier-3 and the existing VoteTrust algorithm, and the graph is plotted against the False Positive (FP) rate, taking into account the precision and recall metrics. Around 99.84% of the expected sybils were confirmed in ASYNPA, which is 3.49% higher than VoteTrust.

New technique to alleviate the cold start problem in recommender systems using information from social media and random decision forests

The aim of recommender systems is to provide users with items that could be of their interest. However one of the biggest drawbacks from recommender systems is the so called cold start problem, which occurs when new users or products are added to the system and therefore there is no previous information about them. There are many proposals in the literature that aim to deal with this issue. In some cases the user is required to provide some explicit information about them, which demands some effort on their part. Because of that and due to the great boom of social networks, we will focus on extracting implicit information from user’s social stream. In this paper we will present an approach on which social media data will be used to create a behavioural profile to classify the users and based on this classification will create predictions making use of machine learning techniques such as classification trees and random forests. Thus the user will not have to provide actively any kind of data explicitly but their social media source, alleviating in this way the cold start problem since the system would use this data in order to create user profiles, which will be the input for the engine of the recommender systems. We have carried out numerous experiments, as well as a comparison with some other state-of-the-art new user cold-start algorithms, obtaining very satisfactory results.

Engagement in mHealth behavioral interventions for HIV prevention and care: making sense of the metrics.

Engagement is the primary metric by which researchers can assess whether participants in a mHealth intervention used and interacted with the intervention's content as intended over a pre-specified period to result in behavior change. Paradata, defined as the process data documenting users' access, participation, and navigation through a mHealth intervention, have been associated with differential treatment outcomes in mHealth interventions. Within behavioral mHealth interventions, there has been an increase in the number of studies addressing the HIV prevention and care continuum in recent years, yet few have presented engagement metrics or examined how these data could inform design modifications, promote continued engagement, and supplement primary intervention efficacy and scale-up efforts. We review common paradata metrics in mHealth interventions (e.g., amount, frequency, duration and depth of use), using case studies from four technology-driven HIV interventions to illustrate their utility in evaluating mHealth behavioral interventions for HIV prevention and care. Across the four case studies, participants' ages ranged between 15 and 30 years and included a racially and ethnically diverse sample of youth. The four case studies had different approaches for engaging young men who have sex with men: a tailored brief intervention, an interactive modular program, a daily tool to monitor and self-regulate treatment adherence, and an online platform promoting social engagement and social support. Each focused on key outcomes across the HIV prevention and care continuum [e.g., safer sex behaviors, HIV testing, antiretroviral therapy (ART) adherence] and collected paradata metrics systematically. Across the four interventions, paradata was utilized to identify patterns of use, create user profiles, and determine a minimum engagement threshold for future randomized trials based on initial pilot trial data. Evidence of treatment differences based on paradata analyses were also observed in between-arm and within-arm analyses, indicating that intervention exposure and dosage might influence the strength of the observed intervention effects. Paradata reflecting participants' engagement with intervention content was used to suggest modifications to intervention design and navigation, to understand what theoretically-driven content participants chose to engage with in an intervention, and to illustrate how engagement was linked to HIV-related outcomes. Paradata monitoring and reporting can enhance the rigor of mHealth trials. Metrics of engagement must be systematically collected, analyzed and interpreted to meaningfully understand a mHealth intervention's efficacy. Future mHealth trials should work to identify suitable engagement metrics during intervention development, ensure their collection throughout the trial, and evaluate their impact on trial outcomes.

Emotional Map : Building a Data Tool for Geolocation-related Product Design

This article introduces a solution of design simulation system based on data processing. It is to observe and analyze user behavior by reflecting a large number of user behavior data trajectories on city maps. We believe that under the technical background of big data and cloud technology, it is possible to build a tool that can help designers to predict user behavior to a certain extent. This article describes the design of the simulation system divided into five stages: data collection, local database establishment, cloud database establishment, user model simulation, and user model-based behavior prediction. We also introduce the experimental design for the first stage: data collection. This research proposes an experimental method of using sensor-based wearable data collecting devices to simulate the scenario with users of smart wearable devices and using the method of diary studies to create user profiles. The study believes that user’s emotion data, such as subjective feelings, which is difficult to measure directly through physical sensors, also plays an important role in the simulation analysis of the design process. This study collated the multi-dimensional information categories needed for user analysis of geolocation-based designs, including geographic data, biological data, and emotional data. In the experiment, a mechanism for collecting emotional data through user’s subjective selection was also introduced.

Environmental monitoring: personalized access approach to the remote sensing information resources

The article considers the necessity to apply a user profile operating with the earth remote sensing information used in the environmental monitoring. The stages of forming a user profile are presented; a dynamic profile model is given. It allows to take into account both long-term and short-term profiles. The main attention is paid to the following issues in describing the stages of user personalization: monitoring the user’s activity; creating user profiles; evaluating the effectiveness of personification. The proposed approach has been successfully implemented for the environmental monitoring of the power plants.

APIs and Your Privacy

Application programming interfaces, or APIs, have been the topic of much recent discussion. Newsworthy events, including those involving Facebook’s API and Cambridge Analytica obtaining information about millions of Facebook users, have highlighted the technical capabilities of APIs for prominent websites and mobile applications. At the same time, media coverage of ways that APIs have been misused has sparked concern for potential privacy invasions and other issues of public policy. This paper seeks to educate consumers on how APIs work and how they are used within popular websites and mobile apps to gather, share, and utilize data. APIs are used in mobile games, search engines, social media platforms, news and shopping websites, video and music streaming services, dating apps, and mobile payment systems. If a third-party company, like an app developer or advertiser, would like to gain access to your information through a website you visit or a mobile app or online service you use, what data might they obtain about you through APIs and how? This report analyzes 11 prominent online services to observe general trends and provide you an overview of the role APIs play in collecting and distributing information about consumers. For example, how might your data be gathered and shared when using your Facebook account login to sign up for Venmo or to access the Tinder dating app? How might advertisers use Pandora’s API when you are streaming music? After explaining what APIs are and how they work, this report categorizes and characterizes different kinds of APIs that companies offer to web and app developers. Services may offer content-focused APIs, feature APIs, unofficial APIs, and analytics APIs that developers of other apps and websites may access and use in different ways. Likewise, advertisers can use APIs to target a desired subset of a service’s users and possibly extract user data. This report explains how websites and apps can create user profiles based on your online behavior and generate revenue from advertiser-access to their APIs. The report concludes with observations on how various companies and platforms connecting through APIs may be able to learn information about you and aggregate it with your personal data from other sources when you are browsing the internet or using different apps on your smartphone or tablet. While the paper does not make policy recommendations, it demonstrates the importance of approaching consumer privacy from a broad perspective that includes first parties and third parties, and that considers the integral role of APIs in today’s online ecosystem.

Classification of readers profiles of a digital journal

In this article, we analyzed the behavior of readers of a digital newspaper in order to find the profiles associated with the use of the website, in order to define content strategies and new newspaper products. A sample of 689 users was taken corresponding to three months of activity, through the tool Google Analytics, it was determined the sections of the newspaper that were used in each visit by the users to consolidate the database. In the process of analysis, the multivariate techniques are used main component analysis and cluster analysis, by means of which graphs and visualizations were obtained that allow a better interpretation of the results and help to the process of creation of userprofiles. The result shows the identification of three user profiles, for which content strategies and new products have been defined.Key words: User profiles, multivariate analysis, profile analysis, digital newspaper