Account User Research Articles

Capacity-aware fair POI recommendation combining transformer neural networks and resource allocation policy

Point of Interest (POI) recommendations have primarily focused on maximising user satisfaction, while neglecting the needs of POIs and their operators. One such need is recommendation exposure, which can lead to envy among the POIs. Some POIs may be under-recommended, while others may be over-recommended, resulting in dissatisfaction for both staff and users due to long queues or overcrowding. Existing work has not addressed the trade-off between satisfying user preferences and being fair to POIs, which typically aim to operate at capacity. Therefore, we introduce the POI fair allocation problem to model this issue, taking into account both user satisfaction and POI exposure fairness. To address this problem, we propose a fair POI allocation technique that balances user satisfaction and POI capacity-based exposure simultaneously. Our proposed model utilises existing (transformer neural networks and attention LSTM model) personalised POI recommendation models that capture users’ spatio-temporal influences and interests in POI visits. We then propose POI capacity-based allocation using the over-demand cut policy and under-demand add policy, which ensures POI exposure ratio and envy-freeness up to certain thresholds. We evaluate the performance of our proposed model on five datasets containing real-life POI visits. Experimental evaluations show that our proposed model outperforms baselines in terms of user and POI-based evaluation metrics. To ensure reproducibility, we have publicly shared our source code at Codeocean.

De-Selection Bias Recommendation Algorithm Based on Propensity Score Estimation

There are various biases present in recommendation systems, and recommendation results that do not consider these biases are unfair to users, items, and platforms. To address the problem of selection bias in recommendation systems, in this study, the propensity score was utilized to mitigate this bias. A selection bias propensity score estimation method (SPE) was developed, which takes into account both user and item information. This method accurately estimates the user’s choice tendency by calculating the degree of difference between the user’s selection rate and the selected preference of the item. Subsequently, the SPE method was combined with the traditional matrix decomposition-based recommendation algorithms, such as the latent semantic model (LFM) and the bias singular value model (BiasSVD). The propensity score was then inversely weighted into the loss function, creating a recommendation model that effectively eliminated selection bias. The experiments were carried out on the public dataset MovieLens, and root mean square error (RMSE) and mean absolute error (MAE) were selected as evaluation indicators and compared with two baseline models and three models with other propensity score estimation methods. Overall, the experimental results demonstrate that the model combined with SPE achieves a minimum increase of 2.00% in RMSE and 2.97% in MAE compared to its baseline model. Moreover, in comparison to other propensity score estimation methods, the SPE method effectively eliminates selection bias in the scoring data, thereby enhancing the performance of the recommendation model.

Washington Post Enterprise

The Washington Post Enterprise subscription is available to institutions of higher education. It provides convenient and unlimited access to the digital edition of the Washington Post and The Post Archives from 1877 to the present. Users can access articles via IP access or sign up for an account. Account users get access to the full archives and other benefits. The main site is visually appealing and easy to navigate; however, the search functionality is not the best. The archives are hosted by ProQuest and include the benefits of that platform.

Self-Supervised Interest Transfer Network via Prototypical Contrastive Learning for Recommendation

Cross-domain recommendation has attracted increasing attention from industry and academia recently. However, most existing methods do not exploit the interest invariance between domains, which would yield sub-optimal solutions. In this paper, we propose a cross-domain recommendation method: Self-supervised Interest Transfer Network (SITN), which can effectively transfer invariant knowledge between domains via prototypical contrastive learning. Specifically, we perform two levels of cross-domain contrastive learning: 1) instance-to-instance contrastive learning, 2) instance-to-cluster contrastive learning. Not only that, we also take into account users' multi-granularity and multi-view interests. With this paradigm, SITN can explicitly learn the invariant knowledge of interest clusters between domains and accurately capture users' intents and preferences. We conducted extensive experiments on a public dataset and a large-scale industrial dataset collected from one of the world's leading e-commerce corporations. The experimental results indicate that SITN achieves significant improvements over state-of-the-art recommendation methods. Additionally, SITN has been deployed on a micro-video recommendation platform, and the online A/B testing results further demonstrate its practical value. Supplement is available at: https://github.com/fanqieCoffee/SITN-Supplement.

Persuasion-enhanced computational argumentative reasoning through argumentation-based persuasive frameworks

AbstractOne of the greatest challenges of computational argumentation research consists of creating persuasive strategies that can effectively influence the behaviour of a human user. From the human perspective, argumentation represents one of the most effective ways to reason and to persuade other parties. Furthermore, it is very common that humans adapt their discourse depending on the audience in order to be more persuasive. Thus, it is of utmost importance to take into account user modelling features for personalising the interactions with human users. Through computational argumentation, we can not only devise the optimal solution, but also provide the rationale for it. However, synergies between computational argumentative reasoning and computational persuasion have not been researched in depth. In this paper, we propose a new formal framework aimed at improving the persuasiveness of arguments resulting from the computational argumentative reasoning process. For that purpose, our approach relies on an underlying abstract argumentation framework to implement this reasoning and extends it with persuasive features. Thus, we combine a set of user modelling and linguistic features through the use of a persuasive function in order to instantiate abstract arguments following a user-specific persuasive policy. From the results observed in our experiments, we can conclude that the framework proposed in this work improves the persuasiveness of argument-based computational systems. Furthermore, we have also been able to determine that human users place a high level of trust in decision support systems when they are persuaded using arguments and when the reasons behind the suggestion to modify their behaviour are provided.

Pengembangan koleksi Perpustakaan Samudra Pustaka Desa Plosorejo Kecamatan Kademangan Kabupaten Blitar

Introduction. This study aims to describe the collection development of the Samudra Pustaka Library.. Samudra Pustaka Library is a village library that became the best village library in 2021 nationally. The completeness of the collection is one of the indicators of the success of managing the village library management.
 Data Collection Methods. The method used was a qualitative descriptive with several data collection techniques including interviews, observations, and documentation studies.
 Data Analysis. Data analysis was conducted by following stages of collection development developed by Evans and Saponaro 
 Results and Discussion. Samudra Pustaka Library currently does not have their own collection development policy Societal analysis was conducted based on user suggestions and identified community livelihoods.. Selection criteria focus on purchases, donations, and collaboration. Weeding activities are carried out by withdrawing collections deemed unreadable. Evaluation activities are carried out by taking into account user suggestions related to collections. Several identified constraints were found on the budget, collections, and human resources.
 Conclusion. All collection development processes are on the right track. A collection development policy should be created immediately.

Islamic Law Review of Discounts Obtained by Having Multiple Accounts on The Shopee Platform

The implementation of online buying and selling transactions through the shopee marketplace is included in the buying and selling category that is currently in vogue, because indeed the convenience offered is also the various discounts provided, including tempting discount promos including: price discount discounts, cashback, postage discounts and so on. Various methods have been used by some Shopee account users to get these discounts; one way is to have more than one Shopee platform account. The formulation of the problem in this study is how is the practice of having multiple accounts by certain users to get discount promos and what is the review of Islamic law on discounts that are obtained by having multiple accounts on the Shopee platform. The purpose of this study is to find out the practice of having multiple accounts by certain users in order to get discount promos and to find out an overview of Islamic law on discounts that are obtained by having multiple accounts on the shopee platform. The research method used in this study is a qualitative method. The main type of data source taken is in the form of primary data, namely interviews with Shopee account users, and secondary as supporting data obtained from literature studies such as the Al-Qur'an, hadits, books of fiqh, books, previous research, journals and others. Data collection techniques include interviews, observation and documentation. The data analysis technique in this study is a descriptive way of explaining the research problems by describing the events that occurred and using the legal basis to discuss the problems of the study in this research, namely Islamic law. The results of this study are that buying and selling through the shopee platform as well as the discounts provided are permissible in Islam, but the practice of using multiple accounts on the shopee platform is a sharia violation because this practice is included in the tadlis category and also violates the ethics of honesty in buying and selling.

Copyright ownership of user-generated content in games

An increasing number of games provide players with freedom to participate within the game world. Using , a world-famous game developed by Nintendo, as a case study, this article discusses the copyright ownership issues of player-created works in China. Although gaming companies hold intellectual property of gaming software, the copyright ownership of user-generated content still needs clarification. The article reviews the framework of copyright protection in China, followed by an analysis of courts’ interpretation of originality that is required for copyright protection. The user agreement between players and Tencent, the company representing Nintendo’s business in mainland China, is analysed to answer the question of the ownership of user-created works. This article finds that although players own the copyright of user-generated content, they are in a weak position to control the exploitation of rights due to the strict Tencent-represented Nintendo Switch Account User Agreement.

An effective energy management Layout-Based reinforcement learning for household demand response in digital twin simulation

With the growth in energy consumption, demand response (DR) programs in the power network have gained popularity and can be expected to become more widespread in the future. Through DR programs, users are encouraged for utilizing renewable energy and reducing their power consumption at peak times, thereby helping to balance supply and demand on the grid, as well as generating revenue from the sale of excess power. This paper presents an effective energy management layout (EML) for household DR employing Reinforcement Learning (RL) and Fuzzy Reasoning (FR). RL would be a model-free control method that consists of doing measures and assessing the outcomes as it interacts with the environments. Through direct integration of customer feedback into its control logic, the suggested method takes into account user satisfaction by utilizing FR as a reward function. Through the shift of controllable devices from peak hours, whenever energy cost is higher, to off-peak periods, whenever energy cost is low, Q-learning, an RL method according to a reward scheme, has been applied for scheduling the execution of smart home devices. With the suggested method, 14 home devices can be controlled by one agent, and many status-action pairs as well as fuzzy logic for the reward function are used to assess the actions taken for a particular status. Simulations are implemented in the digital twin environment and demonstrate that the suggested device planning method smooths the energy usage and minimizes the energy price by taking into account the consumers' satisfaction, the consumers' feedback, and their satisfaction settings. The Home EML has been presented with a consumer interface in MATLAB/Simulink for demonstrating the suggested DR approach. The simulation tools include smart devices, energy price signals, smart meters, solar photovoltaics, batteries, electric vehicle, and grid supply.

Assuring the Sellers Legal Security When Accepting Payments from Joint Accounts Online

Abstract: As technology has improved, it has become easier to share information and less restricted. Anyone, anywhere, can talk to someone with different hobbies in a one-way or two-way exchange. In this age of globalization, changes in technology have made it easier for people to do things like E-Commerce. A "joint account" is a third-party service that allows people to share money online in a safe and friendly way. This is one of the many ways to pay for e-commerce, which is online shopping. This study will look at the legal protections that buyers have when they use joint accounts to do business online. If a seller who is also a joint account user breaks a contract during an online transaction, the law may support the seller.

Self Disclosure Analysis of Alter Account Users on Twitter: A Social Media Study

Social media is something that cannot be separated from the life of a society that is very attached to technology. With social media, people can easily build new identities and express themselves within them. This study aims to analyze Alter account users on Twitter social media to conduct self-disclosure. The method used in this research is descriptive qualitative with social media analysis. The results of the study show that individuals who use alter accounts do self-disclosure because of social influence, new benefits, privacy risks, and a tendency for reciprocity.

The m-polar fuzzy set ELECTRE-I with revised Simos’ and AHP weight calculation methods for selection of non-traditional machining processes

Using improvements to the recently published m-polar fuzzy set (mFS) elimination and choice translating reality-I (ELECTRE-I) approach for calculating criteria weights, the selection of a Non-Traditional Machining (NTM) process problem from the industry is solved in this research. The criteria weights for the m-polar fuzzy ELECTRE-I method are evaluated using the Analytical Hierarchy Process (AHP) approach and the Revised Simos' method. For the ELECTRE family's criteria weight calculations, the Simos’ approach has been revised. Many researchers calculated the weight of the criteria in the selection of the NTM process using the AHP approach. Problems with both physical and intangible properties can be solved using the m-polar fuzzy ELECTRE-I approach. Additionally, it has the ability to solve MCDM issues with more variables. The improved Simos' technique is used in this work because it incorporates user choices for the criteria, or user voting for the criterion. Using expert assistance, the AHP technique prioritizes the criterion based on pair-by-pair comparisons of the criteria. The AHP approach makes compromises between the criteria. The ultimate selection of the process based on the needed aim is affected by both tangible and intangible features in the NTM selection dilemma. The impact of criteria weight techniques on the choice of the NTM process is examined using a single dimensional sensitivity analysis. AHP approach is proven to be less stable for criteria weight variation than the improved Simos' weight calculation method. The updated Simos' method, which takes into account user preferences, performs better for the m-polar fuzzy ELECTRE-I algorithm than the AHP weight calculation method.

Characteristics of the Patient's Internet Account (IKP) users in Poland between 2019 and 2021

Objective This retrospective database analysis aimed to characterize Patient's Internet Account (IKP) users in Poland, before and after the COVID-19 pandemic onset. Methods Data were received from the e-Health Centre – public administration office tasked with the digitization of healthcare in Poland. Data on the number of newly created Patient's Internet Accounts between January 2019 and December 2021 were collected. Moreover, data on the gender and age of the users were also analyzed. Results Between January 2019 and December 2021, the cumulative number of Patient’s Internet Account users increased from 32.6 thousand to 14.1 million. In 2021, December 2021, the cumulative number of Patient’s Internet Account users more than doubled (from 5.6 million in January to 14.1 million in December). In 2019, the monthly number of newly created Patient’s Internet Accounts varied from 17 thousand in February to 180 thousand in December. In the last quarter of 2020 (lifting major anti-epidemic restrictions), a significant increase in the monthly number of newly created Patient’s Internet Accounts was observed (500 thousand accounts per month). The highest number of newly created Patient’s Internet Accounts (over 1.25 million) was in April and July 2021. In December 2021, the highest number (3.3 million) of active Patient’s Internet Accounts was among children aged 0-17 (parental access) and Individuals aged 31-40 years (2.7 million). Conclusions This study revealed high interest in Patient’s Internet Accounts during the COVID-19 pandemic. An increase in the number of Patient’s Internet Account users was related to the new service functionalities such as COVID-19 test results and COVID-19 vaccination appointments.

Application of graph auto-encoders based on regularization in recommendation algorithms.

Social networking has become a hot topic, in which recommendation algorithms are the most important. Recently, the combination of deep learning and recommendation algorithms has attracted considerable attention. The integration of autoencoders and graph convolutional neural networks, while providing an effective solution to the shortcomings of traditional algorithms, fails to take into account user preferences and risks over-smoothing as the number of encoder layers increases. Therefore, we introduce L1 and L2 regularization techniques and fuse them linearly to address user preferences and over-smoothing. In addition, the presence of a large amount of noisy data in the graph data has an impact on feature extraction. To our best knowledge, most existing models do not account for noise and address the problem of noisy data in graph data. Thus, we introduce the idea of denoising autoencoders into graph autoencoders, which can effectively address the noise problem. We demonstrate the capability of the proposed model on four widely used datasets and experimentally demonstrate that our model is more competitive by improving up to 1.3, 1.4, and 1.2, respectively, on the edge prediction task.

Research On Influencing Factors of Wechat Public Account Users' Attention Intention

In the context of the rapid development of new media, wechat public accounts are gradually welcomed by government agencies, social organizations and individuals with the advantages of simple operation and low cost. At the same time, how to let users pay attention to the wechat public number has become the biggest problem facing individual operators. In this paper, the wechat official account of Gending Theory is taken as the research object, and the user's attention intention is taken as the research direction. Based on the success of Information System (D&M) model, the new variables of knowledge seeking psychology, curiosity psychology, entertainment psychology and the key factors of D&M model are added to construct the user's attention intention model.

Evaluation of macroscopic fundamental diagram characteristics for a quantified penetration rate of autonomous vehicles

BackgroundThe availability of private vehicles with autonomous features is widespread nowadays. Various car manufacturers are providing attributes like collision warning, city automatic emergency braking, adaptive cruise control, pedestrian detection, lane-keeping assistance and lane departure warning, rear cross-traffic and blind-spot warning in their high-end models.PurposeSuch features can automatically manage the macroscopic fundamental traffic parameters such as speed, headway, etc adaptively. Consequently leading to a heterogeneous traffic stream with diverse car-following behaviour comprising completely manual/traditional (TVs) and autonomous vehicles (AVs). This questions the applicability of classic traffic flow theory relationships on such heterogeneous traffic streams.MethodologyThis paper focuses on developing the macroscopic fundamental diagram for such heterogeneous traffic streams based on the quantified penetration rate (QPR) for autonomous vehicles. The penetration rate is devised by taking into account user demographics, land usage and road network properties. QPR is used as an input for heterogeneous urban traffic stream scenarios to calculate the aggregated urban traffic network dynamics of flow and density for the same network. Travel time versus flow characteristics is evaluated based on calibrated hyperbolic urban link travel time function for both interrupted and uninterrupted flows following the aggregated speed and density output from MFDs for heterogeneous traffic streams. Also, two scenarios are generated for comparison to explain the improvement in the network characteristics together with a sensitivity analysis.ResultsCompared to the base scenario there could be 25-35% of AVs on the road networks based on the analysis in coming fifteen years. This increment in usage impacts the capacity of road networks positively by increasing it up to 59%.ConclusionsResults obtained after the application of the suggested model approach to the real network can be used to define a realistic method for multi-vehicle equilibrium assignment models for heterogeneous traffic streams including autonomous vehicles instead of approximating the penetration rates.

Predicting millionaires from Ethereum transaction histories using node embeddings and artificial neural nets

We demonstrate the possibility of predicting the millionaire status of an externally-owned Ethereum account based on information queried out of the Blockchain and features describing its role in the network based on node embedding techniques. These features are fed into artificial neural nets and used for status prediction within a systematic model selection process. We report key methodological insights about training and comparing cross-validated deep and shallow neural networks that yield up to 82 percent testset accuracy in predicting the millionaire status of account users.

An Empirical Spatial Network Model Based on Human Mobility for Epidemiological Research: A Case Study

Constructing a data-driven spatial contact network model is challenging in epidemiological research. In this study, we examine the applicability of geotagged Twitter data as an instrumental data source for tackling such a challenge. Geotagged Twitter data carrying geolocations of the account users have the strength for longitudinal data collection at a massive scale. Still, the unstructured nature of the data exerts significant methodological and computational difficulties. We focus on methodological solutions and develop a novelty approach that lets a spatial contact network emerge naturally from the massive amount of geospatial tweets. We show that such a data-driven network has reflected the assumptions made by network models regarding human behaviors and has the potential of being used for epidemiological research. To this end, we investigate the network properties and study the spread of pathogens on the proposed spatial contact network by using the homogeneous and heterogeneous susceptible–infectious–recovered (SIR) network models and the event-driven Gillespie’s algorithm. Our simulation results strongly suggest that it is feasible to explicitly construct data-driven spatial models using massive longitudinal Twitter data for public health research.

A new optimized demand management system for smart grid-based residential buildings adopting renewable and storage energies

Demand Side Management (DSM) implies intelligently managing load appliances in a Smart Grid (SG). DSM programs help customers save money by reducing their electricity bills, minimizing the utility’s peak demand, and improving load factor. To achieve these goals, this paper proposes a new load shifting-based optimal DSM model for scheduling residential users’ appliances. The proposed system effectively handles the challenges raised in the literature regarding the absence of using recent, easy, and more robust optimization techniques, a comparison procedure with well-established ones, using Renewable Energy Resources (RERs), Renewable Energy Storage (RES), and adopting consumer comfort. This system uses recent algorithms called Virulence Optimization Algorithm (VOA) and Earth Worm Optimization Algorithm (EWOA) for optimally shifting the time slots of shiftable appliances. The system adopts RERs, RES, as well as utility grid energy for supplying load appliances. This system takes into account user preferences, timing factors for each appliance, and a pricing signal for relocating shiftable appliances to flatten the energy demand profile. In order to figure out how much electricity users will have to pay, a Time Of Use (TOU) dynamic pricing scheme has been used. Using MATLAB simulation environment, we have made effectiveness-based comparisons of the adopted optimization algorithms with the well-established meta-heuristics and evolutionary algorithms (Genetic Algorithm (GA), Cuckoo Search Optimization (CSO), and Binary Particle Swarm Optimization (BPSO) in order to determine the most efficient one. Without adopting RES, the results indicate that VOA outperforms the other algorithms. The VOA enables 59% minimization in Peak-to-Average Ratio (PAR) of consumption energy and is more robust than other competitors. By incorporating RES, the EWOA, alongside the VOA, provides less deviation and a lower PAR. The VOA saves 76.19% of PAR, and the EWOA saves 73.8%, followed by the BPSO, GA, and CSO, respectively. The electricity consumption using VOA and EWOA-based DSM cost 217 and 210 USD cents, respectively, whereas non-scheduled consumption costs 273 USD cents and scheduling based on BPSO, GA, and CSO costs 219, 220, and 222 USD cents.

Process Modelling of an Analytic Control Machine in Virtual Reality Platform

While the combination of virtual reality (VR), industrial internet of things (IIoT) and digital twin (DT) can promote the integration of the physical world (real) and the digital world (virtual), one of the most important challenges that companies face is the choice of architecture. This study intends to utilize VR, IIoT, DT advantages and to reduce some adverse effects the constituent processes produce when they are individually applied. This bridges the existing gap between the physical and digital machines to enable near real-time monitoring control of the manufacturing process. In the realization of this paradigm shift, we use of IIoT infrastructures by adopting a bi-directional communication protocol for conveyance of data and information between the physical and virtual models in hardware in the loop or software in loop configuration. This study takes into account user case industrial application for the formation of silica scale and methods of reducing its production. In systems operating above pH 8.5, magnesium silicate is very likely to form due to the presence of magnesium hydroxide Mg(OH)2 and silicate (SiO4)4− ions. In this research work, the developed platform (VR, IIoT and DT) is used to remotely monitor and control the process that prevents silica scale formation by maintaining an acidic solution (pH < 6.7). A supervisory control is achieved using VR whereby instructions and commands sent to the physical station for execution. The data collected is stored in a data lake and is used to find the PID controller trends for pH 4 dosing and gain actionable insights. Analysis of the data is done by utilization of visualization schemes, diagrams and infographics. Results show the achievement of near real-time control (correlation coefficient at 99.92%) of a cyber-physical machine using VR by the adoption of bi-directional communication between the physical and virtual models in an immersive environment.