User Attributes Research Articles

User Experience Adaptation of Complex Game Interface for User Behaviour Modeling Using RNN

In a video game review, the main focus is the narratives, characters, graphics, and mechanics in the gameplay. Some recent research mentions the user interface only when it comes into light as a creative platform for simple interactive narratives from a technical point of view; this narrative is mainly a software tool that requires traditionally modernized inputs from the user. The user needs to interact with the navigational controls or menus in order to start a basic game play. A complex game interface as stimulus is generally considered as having a feeling of immersion that allows for visual tracking of user behavioural patterns and use it to predict the next strategy of the user using robust computational models. A number of users have limited sensory perception in a gameplay and hence rely on complex game stimulus and an adaptive model is paramount when considering behavioural expectations that place the user in a digital environment with more expressive perceptions. We developed a custom based eye tracking and 3D object detection algorithm which was utilised by recruiting users to interact with visual 3D objects and trace their eye movement behaviour to generated data. We then applied the use of recurrent neural network (RNN) for direct tracing of user behavioural activities in a sequential manner to predict their behaviour for interface adaptation. Result indicates that redundant user attributes are flexible and flawless for identifying predicted response of the user in a controlled environment. This would lead to prototypical representation of user behavioural analytics as an embedded platform in the confined digital environment. One of the limitations of the project is its inability to basically specify the 3D gaze point at the inner boundaries of the visual field. Data visualisation is strictly based on combined object flow detection. The originality of the work is its ability to redefine fixation point to a rendered cascaded 3D gaze point and space-defined saccade which is indicated by the distance between one gaze points to the other. The 3D gaze point would be well suited for fixation generalisation on 3D as well as on 2D digital oriented environment.

An efficient blockchain‐based privacy‐preserving scheme with attribute and homomorphic encryption

As a distributed ledger technology, blockchain has excellent openness and transparency, which can provide data security management services for distributed intelligent systems and establish effective security guarantee mechanisms. However, precisely due to the open nature of blockchain, malicious users can trace the real transaction transfer path with high probability and even obtain the real identity of users by collecting transaction information on the blockchain and performing data analysis. Besides, existing intelligent systems lack effective encryption or desensitization measures, and attackers are able to access data in intelligent systems through identity forgery and other means, posing a huge potential risk to user privacy. To alleviate the above security issues, this paper proposes an efficient blockchain-based privacy-preserving scheme with attribute and homomorphic encryption, which can not only achieve user-level fine-grained secure access control but also supports the transmission and verification of blockchain data in the form of ciphertext. The access control method based on attribute-based encryption and the data transmission method based on homomorphic encryption are proposed, and the blockchain-based access whitelist mechanism is designed to reduce the resource loss due to repeated authentication. Simulation calculations and blockchain performance experiments show that this scheme can develop flexible access policies according to the attributes of users, has good performance in computational efficiency, and the blockchain performance test results are stable with errors in milliseconds for all operations. It has certain application potential in the field of distributed intelligent systems and blockchain.

Network Alignment across Social Networks Using Multiple Embedding Techniques

Network alignment, which is also known as user identity linkage, is a kind of network analysis task that predicts overlapping users between two different social networks. This research direction has attracted much attention from the research community, and it is considered to be one of the most important research directions in the field of social network analysis. There are many different models for finding users that overlap between two networks, but most of these models use separate and different techniques to solve prediction problems, with very little work that has combined them. In this paper, we propose a method that combines different embedding techniques to solve the network alignment problem. Each association network alignment technique has its advantages and disadvantages, so combining them together will take full advantage and can overcome those disadvantages. Our model combines three-level embedding techniques of text-based user attributes, a graph attention network, a graph-drawing embedding technique, and fuzzy c-mean clustering to embed each piece of network information into a low-dimensional representation. We then project them into a common space by using canonical correlation analysis and compute the similarity matrix between them to make predictions. We tested our network alignment model on two real-life datasets, and the experimental results showed that our method can considerably improve the accuracy by about 10–15% compared to the baseline models. In addition, when experimenting with different ratios of training data, our proposed model could also handle the over-fitting problem effectively.

Building and exploiting spatial–temporal knowledge graph for next POI recommendation

Next Point-of-Interest (POI) recommendation has shown great value for both users and businesses in the field of location-based services. Many spatial–temporal inferring methods have been developed to perform this task, but the data sparsity of POI trajectories greatly hinders the recommendation performance. Knowledge graphs (KGs) have been demonstrated as an effective way to tackle data sparsity in the general recommendation field by leveraging the valuable information of entities and relations. Yet, few studies have explored applying KGs for the next POI recommendation task because of the following challenges: (1) how to represent the dynamic mobility behaviors of users with the static entities and relations in KGs; and (2) how to utilize the different types of entities and relations in KGs to capture long- and short-term preferences of users. In this work, we investigate building a spatial–temporal KG (STKG) from check-in sequences of users to promote the next POI recommendation, without introducing any external attributes of users and POIs. In STKG, we design a novel spatial–temporal transfer relation to intuitively capture users’ transition patterns between neighboring POIs. Then, based on the STKG, we propose an innovative model, named STKGRec, for the next POI recommendation, which explicitly models long- and short-term preferences of users in an end-to-end manner. In particular, STKGRec learns both the spatial–temporal correlation of consecutive and nonconsecutive visits in the current check-in sequence to comprehensively capture the short-term preferences of users. Extensive experiments on four real-world datasets demonstrate the superiority of STKGRec against the state-of-the-art baseline methods. The code of our proposed model is available athttps://github.com/WeiChen3690/STKGRec.

Research on loyalty prediction of e-commerce customer based on data mining

Abstract Analysing the data generated by the daily operations of enterprises through data mining technology can effectively predict customer loyalty and help enterprise leaders make correct decisions. Therefore, this paper classifies and analyses churn and loyalty of e-commerce customers, and by combining the application foundation of data mining technology in e-commerce customer loyalty prediction, a prediction model of e-commerce customer loyalty based on data mining is constructed. In this model, the local abnormal factor algorithm is used to eliminate the data for cleaning, the XGBoost algorithm is improved by adding penalty coefficient, and the prediction effect of the model is evaluated and compared according to the values of Accuracy, Precision, Recall and F. The results show that the model has high accuracy in predicting customer loyalty, which can accurately extract attributes of users and characteristic information of commodities.

Modeling and Analysis of Group User Portrait through WeChat Mini Program

Meeting users’ preferences and increasing business revenue is an ongoing challenge in the mobile service application. In this paper, we address these challenges by mining mobile user behavior patterns and propose an approach to construct a group user portrait by analyzing access data collected from the users of the WeChat Mini Program. We extract the attributes of mobile users considering their geographic information, online duration, and age group. UsingZ-score standardized processing andK-means clustering algorithm, we then model the user portraits through three dimensions including daily average duration, interaction intensity, and access frequency. Our analysis has two important features. Firstly, the significant log data used in our experiments was collected from the production environment ensuring that the results reflect the real attributes of WeChat Mini Program users’ behavior. Secondly, we provide data-driven decision-making to help marketers enhance the quality of the product and improve user experience. The experimental results indicate that by distilling and analyzing the key factors from the log data, the characters of typical users can be properly profiled to help product owners better optimize the exact set of the features which need to sustain and further grow.

A New Collaborative Filtering Algorithm Integrating Time and Multisimilarity

Aiming at the problem of low recommendation accuracy of existing recommendation algorithms, an algorithm integrating time factors and multisimilarity is proposed to improve the impact of long-term data, user attention, and project popularity on the recommendation algorithm and the similarity of user attributes is introduced to improve the problem of cold start to a certain extent. Considering that the longer the time, the less likely it is to be selected again, time is introduced into the algorithm as a weight factor. When the behavior occurs, i.e., interest in the project, so as to judge the similarity between users, not just the score value, we normalize the popularity to avoid misjudgment of high scoring and popular items. Because new users do not have past score records, the problem of cold start can be solved by calculating the similarity of user attributes. Through the comparative experiment on Movielens100K dataset and Epinions dataset, the results show that the algorithm can improve the accuracy of recommendation and give users a better recommendation effect.

Association between community psychological label and user portrait model based on multimodal neural network.

By analyzing traditional deep learning multimode retrieval methods, an optimized multimode retrieval model based on convolutional neural network is established. This article proposes an innovative semi-supervised social network user portrait analysis model (UPAM) based on user portrait model, which integrates users’ social information and some known user attribute information (such as educational background and residence) into a unified topic model framework. Finally, a semi-supervised user portrait analysis method based on user social information and partial known user attribute information is proposed. According to the correlation of user attributes, the cross-validation method is used to train model prediction task and improve the prediction effect. In the first-level model, using a different model to extract the features in the user query, the basis of the second hierarchy model, Stacking is used to further integrate characteristics, finally realizing the attribute population forecast, and experimental verification showing the proposed model’s effectiveness in various attributes of a population.

Sarve: synthetic data and local differential privacy for private frequency estimation

The collection of user attributes by service providers is a double-edged sword. They are instrumental in driving statistical analysis to train more accurate predictive models like recommenders. The analysis of the collected user data includes frequency estimation for categorical attributes. Nonetheless, the users deserve privacy guarantees against inadvertent identity disclosures. Therefore algorithms called frequency oracles were developed to randomize or perturb user attributes and estimate the frequencies of their values. We propose Sarve, a frequency oracle that used Randomized Aggregatable Privacy-Preserving Ordinal Response (RAPPOR) and Hadamard Response (HR) for randomization in combination with fake data. The design of a service-oriented architecture must consider two types of complexities, namely computational and communication. The functions of such systems aim to minimize the two complexities and therefore, the choice of privacy-enhancing methods must be a calculated decision. The variant of RAPPOR we had used was realized through bloom filters. A bloom filter is a memory-efficient data structure that offers time complexity of O(1). On the other hand, HR has been proven to give the best communication costs of the order of log(b) for b-bits communication. Therefore, Sarve is a step towards frequency oracles that exhibit how privacy provisions of existing methods can be combined with those of fake data to achieve statistical results comparable to the original data. Sarve also implemented an adaptive solution enhanced from the work of Arcolezi et al. The use of RAPPOR was found to provide better privacy-utility tradeoffs for specific privacy budgets in both high and general privacy regimes.

Mathematical Modeling of Static Data Attribute Encryption Based on Big Data Technology

Attribute encryption is an effective one to many network communication technologies, which supports flexible access control strategies and is very suitable for fine-grained access control in large-scale information systems. In order to improve the attributes of static data, encryption technology can provide a reliable technical guarantee for network security. This paper presents a mathematical modeling method of static data attribute encryption based on big data technology. The big data redundancy elimination algorithm based on similarity calculation is analyzed. By using static data attribute encryption based on big data technology, the length of encrypted data packets will not increase, and partial redundancy of fragments can be eliminated, which can greatly improve the efficiency of the system. The attribute-based encryption mechanism uses attributes as public keys, and the decryption user is a group; so, the encryption efficiency is very high. It can realize efficient encryption and decryption, as well as flexible access control based on user attributes. This scheme can reflect the importance of attributes; so, it is more practical.

Offline/Online lattice-based ciphertext policy attribute-based encryption

Attribute Based Encryption (ABE) is a new public key encryption scheme which allows users to encrypt and decrypt messages based on user attributes, and it can enforce fine grained access control over the encrypted data. However, encryption and key generation computational costs grow with the complexity of the access policy or number of attributes, which makes it unsuitable for mobile device scenario.To address this problem, we propose an offline/online lattice-based ciphertext policy attribute-based encryption scheme under the Ring Learning with Errors (R-LWE) assumption where the computations for the algorithms are split into two phases: offline and online. In the process of generating the private key, the offline stage generates the intermediate private key before the attributes are known, and the online stage generates the corresponding private key based on the attributes. In the encryption process, the offline stage generates the intermediate ciphertext before the plaintext message and access policy are known, and preprocesses the complex computations required for encryption. After the online stage knows the plaintext message and access policy, it only needs to perform a small amount of simple computations to generate the final ciphertext. Compared with the Learning with Errors (LWE) based attribute-based encryption scheme, our scheme has better computational performance. Compared with the regular lattice based attribute based encryption scheme, our scheme is suitable for mobile devices. Compared with the attribute-based encryption schemes based on bilinear pairing, our scheme is resistant against quantum computing attacks.

Time-Weighted Community Search Based on Interest

Community search aims to provide users with personalized community query services. It is a prerequisite for various recommendation systems and has received widespread attention from academia and industry. The existing literature has established various community search models and algorithms from different dimensions of social networks. Unfortunately, they only judge the representative attributes of users according to the frequency of attribute keywords, completely ignoring the temporal characteristics of keywords. It is clear that a user’s interest changes over time, so it is essential to select users’ representative attributes in combination with time. Therefore, we propose a time-weighted community search model (TWC) based on user interests which fully considers the impact of time on user interests. TWC reduces the number of query parameters as much as possible and improves the usability of the model. We design the time-weighted decay function of the attribute. We then extract the user’s time-weighted representative attributes to express the user’s short-term interests more clearly in the query window. In addition, we propose a new attribute similarity scoring function and a community scoring function. To solve the TWC problem, we design and implement the Local Extend algorithm and the Shrink algorithm. Finally, we conduct extensive experiments on a real dataset to verify the superiority of the TWC model and the efficiency of the proposed algorithm.

Hybrid deep learning – picture fuzzy set model for monitoring human behaviour in forest protection

In conventional monitoring forest protection, detection methods use optical sensors or RGB cameras combine features including smokes, fires and human-destroyed forests at national forests. This paper has presented a new approach using Deep learning integrated with Picture Fuzzy Set for the surveillance monitoring system to be activated to confirm human behaviour in real-time in forest protection. Picture Fuzzy Graph (PFG) are applied to solve many complex problems in the real-world problems. The paper has presented a novel approach using deep learning with knowledge graphs to find a human profile including the detection of humans in large data. In the proposed model, digital human profiles are collected from conventional databases combination with social networks in real-time, and a knowledge graph is created to represent complex-relational user attributes of human profile in large datasets. PFG is applied to quantify the degree centrality of nodes. To confirm the proposed model, the proposed model has been tested with data sets through case studies of a forest. Experimental results show that the proposed model has been validated on real world datasets to demonstrate this method’s effectiveness.

The protection of commodified data in e-platforms

Using limited information, notably excluding paramount items in e-platforms, the user leads to sub-optimal decisions regarding his/her data to digital commodes. Thus, the study statement: personal data has been commodified. The study uses a method the mitigation of data commodification risk. It aims to find a way for data protection when a person uses e-platforms. It is important because user's attributes that allow others to recognize each other are closely aligned with a person's being, and individuals identify themselves through these attributes. As such, they are essential to personhood and warrant protection. The personality of user in e-platforms must be dignity - inalienable.
 Based on the GDPR Article 25 and Recital 78, the measure for the data protection is assumed to comply when data systems go along with technical and organizational safeguards. The EU's concept advances a new legal approach where users are holders of their data. It allows them to manage data in secure, local, and online storage orderliness, dispensing it by person's choice. Selves are capable to select settings for data execution and data accord. This mitigation technique acknowledges a human-centric distinction and increased e-platforms for empowered designs. It can also guard against unlawful profiling techniques that strive to circumvent critical measures for the risk mitigation of data commodification. The solution is found aground in the experience of e-platforms such as Mydex, NextCloud, and MyData Global. In this regard, the article defends the digital integrity in e-platforms through data protection by design, informed consent, and the prohibition in e-platforms to consider data - a source of financial gain. The conclusion would remain to go along with data accuracy, time reservation, and user informativeness.

Gender Prediction of Indonesian Twitter Users Using Tweet and Profile Features

The increasing use of social media generates huge amounts of data which in turn triggers research into social media analytics. Social media contents can be analyzed to explore public opinion on an issue or provide the insights reflecting proxy indicators towards real-world events. Understanding the demographics of social media users can increase the potential for applications of sentiment analysis, topic modeling, and other analytical tasks. To map demographics, we need to know the latent attributes of users, such as age, gender, occupation and location of residence. Since this attribute is not directly available, we need to do some inference from the social media data. This study aims to predict the gender attribute given a Twitter user account. We conducted experiments with several supervised classifiers with feature extraction, including the use of word embedding representations. The results of this study indicate that the combination of features extracted from Tweet contents and user profile structured data can predict the gender of Twitter users in Indonesia with accuracy above 80%.

The Adoption Factors of Mobile Games in the Wireless Environment.

The factors that influence how people play mobile games have been studied from a variety of perspectives in the wireless broadband environment. The original data in the background of the game, such as user operation records, consumption records, and social behavior records, are converted into user attributes, user tags are generated, and data sets are constructed in this study, which primarily uses data mining technology to study user behavior and form user portraits. By incorporating the similarity of players' subspace interests into the CFR (collaborative filtering recommendation) algorithm, a personalized game recommendation model, as well as the relationship management level of mobile game players, is created. The final fusion model's ROC-AUC value is 0.921, which has a percentile enhancement effect, according to the results. The findings show that using a personalized game recommendation model can help to improve the scalability of the CFR algorithm and the impact of data scarcity on the quality of mobile games recommended by players.

An Attribute-Based Encryption Method Using Outsourced Decryption and Hierarchical Access Structure

Cloud computing is being rapidly adopted by many organizations from different domains and large amounts of data is stored in the cloud. In order to ensure data security, the attribute-based access control mechanism has been emerging recently as a fine-grained access control model that grants access based on the data user’s attributes. In this model, the data owner builds the access policy using the attributes of the data users and access to the data is granted only if the requirements of such an access policy are satisfied. Ciphertext policy-based attribute-based encryption (CPABE) is one of the most widely used methods for providing encrypted access control. Complex, time consuming and costly paring operations are the major issue with the CPABE method. Hence, another efficient method is needed to reduce the data user’s overhead while decrypting data. This paper presents an efficient method consisting in outsourcing decryption operations to a third-party server, so that complex operations may be performed by that machine with only some simple calculations left on the data user’s side. The concept of a hierarchical access structure is also integrated with the traditional CPABE technique. The hierarchical approach enables the data owner to encrypt multiple data using a single common hierarchical access structure. This allows the user to decrypt only the relevant part of ciphertext, depending on which fragment of the hierarchical access structure is satisfied. The paper evaluates also the performance of the proposed model in terms of time and storage cost.

IntegrateCF: Integrating explicit and implicit feedback based on deep learning collaborative filtering algorithm

Due to the expansion of e-business, the availability of products on the internet has massively increased. Finding suitable stuff from the vast array of products available on the internet is a time-consuming task. Collaborative Filtering (CF) is the most effective recommendation method for providing users with the ability to identify relevant content and, therefore, increase engagement. However, CF has several flaws, including data sparsity and cold start problems. These are ongoing research questions that pose major hurdles to the precision of the algorithms. Therefore, in this work, a novel neural recommendation model is proposed based on non-independent and identically distributed (Non-IID) for CF by incorporating explicit and implicit coupling interaction. The explicit interactions consist of two models, namely Intra-coupling interactions within users and items, and Inter-coupling interactions between different users and items concerning the attributes of users and items. The Intra-coupled model learns using deep learning convolutional neural networks and is combined with the Inter-coupled model. Besides explicit coupling interactions, we present a Generalized Matrix Factorization Bias (GMFB) model that systematically trains the implicit user-item coupling. Finally, we combined with explicit and implicit coupling interactions within and between users and items accompanying the extra information about users and items under a framework called “IntegrateCF.” Extensive experiments on two large real-world datasets have shown that the proposed model performs better than existing methods.

LightFIG: simplifying and powering feature interactions via graph for recommendation.

The attributes of users and items contain key information for recommendation. The latest advances demonstrate that better representations can be learned by performing graph convolutions on attribute graph of the user-item pair. Recently proposed models construct graphs that not only connect edges between user attributes and item attributes, but also within user (item) attributes. However, to determine whether a user is interested in an item, the relationships between user attributes and item attributes are what we really need to mine. In many cases, due to the low correlation between relationships within user (item) attributes and preference of the user, the artificially connected edges within user (item) attributes contribute little to the recommendation. Even worse, including them will not only drastically increase the training time, but may also introduce noise and lead to degraded performance. In addition, the use of the optimizer is also relatively simple. One single optimizer is the default configuration for recommendation models. This may not be the best way to exploit it in many cases however. To solve these problems, we propose an enhanced model named LightFIG in this work. The key idea of LightFIG is twofold: First, we simplify the construction of attribute graph which focuses on mining relationships cross user attributes and item attributes, not between user (item) attributes. Second, we propose the idea of relay optimization, which employs two different optimizers to continuously optimize model parameters. Comprehensive experiments on three public datasets demonstrate the effectiveness of our proposed model.

An SKP-ABE Scheme for Secure and Efficient Data Sharing in Cloud Environments

Security threats such as data forgery and leakage may occur when sharing data in cloud environments. Therefore, it is important to encrypt your data and securely access it when sharing it with other users via a cloud server. Of the various security technologies, research on secure data sharing commonly employs Key Policy Attribute-Based Encryption (KP-ABE). However, existing KP-ABE schemes generally lack ciphertext search features. Furthermore, even if a KP-ABE scheme incorporates it, the number of searches required increases markedly by the number of attributes used in the search. It in turn proportionally increases the ciphertext size. In addition, the attribute authority (AA) could be attacked, which can result in the leakage of users’ decryption keys. AA is a server that manages user attributes and decryption keys when using attribute-based encryption in a cloud environment. If the AA is curious, it can cause problems with the key escrow with the attributes and decryption (secret) key information of the users it knows. In this paper, to solve all these problems, we present a new scheme called Searchable Key-Policy Attribute-Based Encryption (SKP-ABE) for secure and efficient data sharing in the cloud. This proposed SKP-ABE scheme allows fast ciphertext search and keeps the ciphertext of constant size. The key escrow problem is solved via user key generation.