Historical User Behavior Research Articles

A small neighborhood fabric recommender system based on user historical behavior and preference

In the current landscape, textile companies need rapid, precise, and personalized assistance, especially as digitalization and information, such as e-commerce and websites, are developing rapidly. Textile enterprises can mine user preferences to make personalized recommendations of appropriate textile fabrics; this is not only in keeping with current trends, but more importantly, can control production costs and improve user satisfaction. To support the transformation of textile enterprises to a small-batch and multi-variety business model, this paper proposes a fabric recommendation system; specifically, a fabric recommender system based on user historical behavior and preference is proposed. The proposed method is mainly based on the integration of preference, user activity, and rating; firstly, according to the fabric products purchased by the user, the features of the fabric are mined using a neural network to obtain the user’s preferences; secondly, neighbors with similar user behaviors are found according to similarity in users’ activity; and finally, understanding of the fabric is enhanced through a matrix based on the fabric ratings of the user. A focus on recommendation algorithm parameterization, including selection, thresholding, and neighborhood optimization, elevates the recommendation quality. A user–fabric dataset was used for experimental verification, and included the user’s purchase score of the fabric and the image of the fabric. Comparative analyses demonstrate superior precision with fewer neighborhoods, achieving a score of up to 0.93. Our research provides insights into user behavior and personalization, guiding future recommender system design and optimization.

Emerging synergies between large language models and machine learning in e-commerce recommendations

This paper explores the integration of large language models (LLMs) into collaborative filtering algorithms to enhance recommendation systems in the e-commerce domain. The proposed approach combines user-based and item-based collaborative filtering with LLMs to improve recommendation accuracy and personalization. Specifically, the study introduces a novel framework called PALR, which leverages LLMs to refine user-item interactions and enrich item representations. PALR utilizes historical user behavior data, such as clicks, purchases, and ratings, to guide candidate retrieval and generate recommended items. This study highlights the importance of integrating LLMs into recommendation systems to deliver more accurate and personalized suggestions, ultimately improving user satisfaction and driving sales in e-commerce platforms.

LGMRec: Local and Global Graph Learning for Multimodal Recommendation

The multimodal recommendation has gradually become the infrastructure of online media platforms, enabling them to provide personalized service to users through a joint modeling of user historical behaviors (e.g., purchases, clicks) and item various modalities (e.g., visual and textual). The majority of existing studies typically focus on utilizing modal features or modal-related graph structure to learn user local interests. Nevertheless, these approaches encounter two limitations: (1) Shared updates of user ID embeddings result in the consequential coupling between collaboration and multimodal signals; (2) Lack of exploration into robust global user interests to alleviate the sparse interaction problems faced by local interest modeling. To address these issues, we propose a novel Local and Global Graph Learning-guided Multimodal Recommender (LGMRec), which jointly models local and global user interests. Specifically, we present a local graph embedding module to independently learn collaborative-related and modality-related embeddings of users and items with local topological relations. Moreover, a global hypergraph embedding module is designed to capture global user and item embeddings by modeling insightful global dependency relations. The global embeddings acquired within the hypergraph embedding space can then be combined with two decoupled local embeddings to improve the accuracy and robustness of recommendations. Extensive experiments conducted on three benchmark datasets demonstrate the superiority of our LGMRec over various state-of-the-art recommendation baselines, showcasing its effectiveness in modeling both local and global user interests.

Detecting Offensive Language Based on Graph Attention Networks and Fusion Features

The pervasiveness of offensive language on social networks has caused adverse effects on society, such as abusive behavior online. It is urgent to detect offensive language and curb its spread. In the popular datasets, the distribution of users and tweets is imbalanced, which limits the generalization ability of the model. In addition, existing research shows that methods with community information extracted from the social graphs effectively improve the performance of offensive language detection. However, the existing models deal with social graphs independently, which seriously affects the effectiveness of detection models. In this article, we release a new dataset with users and social relationships. To encode community information, we construct the social graphs based on the user historical behavior information and social relationships. Moreover, we propose a model based on graph attention networks (GATs) and fusion features for offensive language detection (GF-OLD). Specifically, the community information is directly captured by the GAT module, and the text embeddings are taken from the last hidden layer of bidirectional encoder representation from transformer (BERT). Attention mechanisms and position encoding are used to fuse these features. Our method outperforms baselines with the F1-score of 89.94%. The results show that our model effectively learns the potential information of social graphs and text, and user historical behavior information is more suitable for user attribute in the social graphs.

Sequence recommendation using multi-level self-attention network with gated spiking neural P systems

Sequence recommendation is used to predict the user's next potentially interesting items and behaviors. It not only focuses on the user's independent interaction behavior, but also considers the user's historical behavior sequence. However, sequence recommendation still faces some challenges: the existing models still have shortcomings in addressing long-term dependencies and fully utilizing contextual information in sequence recommendation. To address these challenges, we propose a four-channel model based on a multi-level self-attention network with gated spiking neural P (GSNP) systems, termed SR-MAG model. The four channels are divided into two groups, and each group is composed of an attention channel and an GSNP attention channel. Moreover, they process long-term sequences and short-term sequences respectively to obtain long-term or short-term attention channel features. These features are then passed through a self-attention network to effectively extract user context information. The proposed SR-MAG model is tested on three real datasets and compared with 10 baseline methods. Experimental results demonstrate the effectiveness of the proposed SR-MAG model in sequence recommendation tasks.

Deep learning methods used in movie recommendation systems

As the amount of internet movie data grows rapidly, traditional movie recommendation systems face increasing challenges. They typically rely on statistical algorithms such as item-based or user-based collaborative filtering. However, these algorithms struggle to handle large-scale data and often fail to capture the complexity and contextual information of user behavior. Therefore, deep learning techniques have been widely applied to movie recommendation systems. This paper reviews movie recommendation algorithms based on traditional statistical models and introduces three main deep learning techniques: Artificial Neural Networks (ANN), Convolutional Neural Networks (CNN), and Recurrent Neural Networks (RNN). ANN can extract features at different levels of users and movies; CNN can capture features of movie posters and movie data to recommend similar movies; RNN can consider user historical behavior and contextual information to better understand user interests and demands. The application of these deep learning techniques can enhance the accuracy and user experience of movie recommendation systems. This paper also demonstrates the advantages and disadvantages of these models and their specific application methods in movie recommendation systems, and points out the direction for further development and improvement of deep learning models in this field.

Enhancing JWT Authentication and Authorization in Web Applications Based on User Behavior History

The rapid growth of the web has transformed our daily lives and the need for secure user authentication and authorization has become a crucial aspect of web-based services. JSON Web Tokens (JWT), based on RFC 7519, are widely used as a standard for user authentication and authorization. However, these tokens do not store information about the user’s behavior history. To address this issue, this paper presents a solution to enhance the trustworthiness of user authentication in web applications based on their behavior history. The solution considers factors such as the number of password attempts, IP address consistency, and user agent type and assigns a weight or percentage to each. These weights are summed up and stored in the user’s account, and updated after each transaction. The proposed approach was implemented using the .NET framework, C# programming language, and PostgreSQL database. The results show that the proposed solution effectively increases the level of trust in user authentication. The paper concludes by highlighting the strengths and limitations of the proposed solution.

Service selection model based on user intention and context

The internet interconnects billions of objects and services. Real-world services are offered by entities with various functions communicating with one another. The selection of services based on their functionality is a complex process because as the number of services rises, so does the number of services that offer the same functionality. Quality of service (QoS) can be a criterion for selecting a suitable service. However, QoS' relative significance fluctuates due to changing user preferences, and users may exhibit various behaviors depending on their contexts and intentions. Defining a user's preference based on user intentions and context is similarly challenging; nonetheless, scholars have paid little attention to this topic. This study provides a new model for service selection based on user intentions and context. The model dynamically selects the appropriate set of QoS with their importance to specify a user preference for various behaviors. The issue of assessing user preference to select the desired service is resolved by calculating the QoS importance based on the user's behavior history and context. The study proposed a dynamic K-Skyline method to optimize a search space and a multi-criteria decision-making technique to select and rank services efficiently. A case study and an experiment demonstrating the proposed model are presented, in which real-world datasets are utilized. The experimental results of the proposed model validate the model's efficiency and robustness.

On the User Behavior Leakage from Recommender System Exposure

Modern recommender systems are trained to predict users’ potential future interactions from users’ historical behavior data. During the interaction process, despite the data coming from the user side, recommender systems also generate exposure data to provide users with personalized recommendation slates. Compared with the sparse user behavior data, the system exposure data are much larger in volume since only very few exposed items would be clicked by the user. In addition, user historical behavior data are privacy sensitive and commonly protected with careful access authorization. However, the large volume of recommender exposure data generated by the service provider itself usually receives less attention and could be accessed within a relatively larger scope of various information seekers or even potential adversaries. In this article, we investigate the problem of user behavior data leakage in the field of recommender systems. We show that the privacy-sensitive user past behavior data can be inferred through the modeling of system exposure. In other words, one can infer which items the user has clicked just from the observation of current system exposure for this user . Given the fact that system exposure data could be widely accessed from a relatively larger scope, we believe that user past behavior privacy has a high risk of leakage in recommender systems. More precisely, we conduct an attack model whose input is the current recommended item slate (i.e., system exposure) for the user while the output is the user’s historical behavior. Specifically, we exploit an encoder-decoder structure to construct the attack model and apply different encoding and decoding strategies to verify attack performance. Experimental results on two real-world datasets indicate a great danger of user behavior data leakage. To address the risk, we propose a two-stage privacy-protection mechanism that first selects a subset of items from the exposure slate and then replaces the selected items with uniform or popularity-based exposure. Experimental evaluation reveals a trade-off effect between the recommendation accuracy and the privacy disclosure risk, which is an interesting and important topic for privacy concerns in recommender systems.

News Recommendation Based on User Topic and Entity Preferences in Historical Behavior

A news-recommendation system is designed to deal with massive amounts of news and provide personalized recommendations for users. Accurately modeling of news and users is the key to news recommendation. Researchers usually use auxiliary information such as social networks or item attributes to learn about news and user representation. However, existing recommendation systems neglect to explore the rich topics in the news. This paper considered the knowledge graph as the source of side information. Meanwhile, we used user topic preferences to improve recommendation performance. We proposed a new framework called NRTEH that was based on topic and entity preferences in user historical behavior. The core of our approach was the news encoder and the user encoder. Two encoders in NRTEH handled news titles from two perspectives to obtain news and user representation embedding: (1) extracting explicit and latent topic features from news and mining user preferences for them; and (2) extracting entities and propagating users’ potential preferences in the knowledge graph. Experiments on a real-world dataset validated the effectiveness and efficiency of our approach.

Position-Enhanced and Time-aware Graph Convolutional Network for Sequential Recommendations

The sequential recommendation (also known as the next-item recommendation), which aims to predict the following item to recommend in a session according to users’ historical behavior, plays a critical role in improving session-based recommender systems. Most of the existing deep learning-based approaches utilize the recurrent neural network architecture or self-attention to model the sequential patterns and temporal influence among a user's historical behavior and learn the user's preference at a specific time. However, these methods have two main drawbacks. First, they focus on modeling users’ dynamic states from a user-centric perspective and always neglect the dynamics of items over time. Second, most of them deal with only the first-order user-item interactions and do not consider the high-order connectivity between users and items, which has recently been proved helpful for the sequential recommendation. To address the above problems, in this article, we attempt to model user-item interactions by a bipartite graph structure and propose a new recommendation approach based on a Position-enhanced and Time-aware Graph Convolutional Network (PTGCN) for the sequential recommendation. PTGCN models the sequential patterns and temporal dynamics between user-item interactions by defining a position-enhanced and time-aware graph convolution operation and learning the dynamic representations of users and items simultaneously on the bipartite graph with a self-attention aggregator. Also, it realizes the high-order connectivity between users and items by stacking multi-layer graph convolutions. To demonstrate the effectiveness of PTGCN, we carried out a comprehensive evaluation of PTGCN on three real-world datasets of different sizes compared with a few competitive baselines. Experimental results indicate that PTGCN outperforms several state-of-the-art sequential recommendation models in terms of two commonly-used evaluation metrics for ranking. In particular, it can make a better trade-off between recommendation performance and model training efficiency, which holds great potential for online session-based recommendation scenarios in the future.

Disentangled Graph Neural Networks for Session-Based Recommendation

Session-based recommendation (SBR) has drawn increasingly research attention in recent years, due to its great practical value by only exploiting the limited user behavior history in the current session. The key of SBR is to accurately infer the anonymous user purpose in a session which is typically represented as session embedding, and then match it with the item embeddings for the next item prediction. Existing methods typically learn the session embedding at the item level, namely, aggregating the embeddings of items with or without assigned attention weights to items. However, they ignore the fact that a user's intent on adopting an item is driven by certain factors of the item (e.g., the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">leading actors</i> of an movie). In other words, they have not explored finer-granularity interests of users at the factor level to generate the session embedding, leading to sub-optimal performance. To address the problem, we propose a novel method called Disentangled Graph Neural Network (Disen-GNN) to capture the session purpose with the consideration of factor-level attention on each item. Specifically, we first employ the disentangled learning technique to cast item embeddings into the embeddings of multiple factors, and then use the gated graph neural network (GGNN) to learn the embedding factor-wisely based on the item adjacent similarity matrix computed for each factor. Moreover, the distance correlation is adopted to enhance the independence between each pair of factors. After representing each item with independent factors, an attention mechanism is designed to learn user intent to different factors of each item in the session. The session embedding is then generated by aggregating the item embeddings with attention weights of each item's factors. To this end, our model takes user intents at the factor level into account to infer the user purpose in a session. Extensive experiments on three benchmark datasets demonstrate the superiority of our method over existing methods.

Anticipated versus Actual Effects of Platform Design Change: A Case Study of Twitter's Character Limit

The design of online platforms is both critically important and challenging, as any changes may lead to unintended consequences, and it can be hard to predict how users will react. Here we conduct a case study of a particularly important real-world platform design change: Twitter's decision to double the character limit from 140 to 280 characters to soothe users' need to "cram" or "squeeze" their tweets, informed by modeling of historical user behavior. In our analysis, we contrast Twitter's anticipated pre-intervention predictions about user behavior with actual post-intervention user behavior: Did the platform design change lead to the intended user behavior shifts, or did a gap between anticipated and actual behavior emerge? Did different user groups react differently? We find that even though users do not "cram" as much under 280 characters as they used to under 140 characters, emergent "cramming" at the new limit seems to not have been taken into account when designing the platform change. Furthermore, investigating textual features, we find that, although post-intervention "crammed" tweets are longer, their syntactic and semantic characteristics remain similar and indicative of "squeezing". Applying the same approach as Twitter policy-makers, we create updated counterfactual estimates and find that the character limit would need to be increased further to reduce cramming that re-emerged at the new limit. We contribute to the rich literature studying online user behavior with an empirical study that reveals a dynamic interaction between platform design and user behavior, with immediate policy and practical implications for the design of socio-technical systems.

Prediction of Online Consumers’ Repeat Purchase Behavior via BERT-MLP Model

It is an effective means for merchants to carry out precision marketing and improve ROI by using historical user behavior data obtained from promotional activities in order to build a model to predict the repeat purchase behavior of users after promotional activities. Most of the existing prediction models are supervised learning, which does not work well with a small amount of labeled data. This paper proposes a BERT-MLP prediction model that uses “large-scale data unsupervised pre-training + small amount of labeled data fine-tuning.” The experimental results on Alibaba real dataset show that the accuracy of the BERT-MLP model is better than the baseline model.

User dynamic topology-information-based matrix factorization for e-government recommendation

Today, there is a growing tendency to integrate all public services on e-government websites, a trend that increases the risk of information overload. Matrix factorization (MF)-based recommendation models can effectively predict the user preference for an item, thus demonstrating their superiority in alleviating information overload problems. However, factors such as poor latent representations and the linear interaction function limit the further performance of these models To address these issues, we propose a novel method named user dynamic topology-information-based matrix factorization (User-DTMF). User-DTMF contains two designed modules: the dynamic topology feature learning module and the interactive preference learning module. The former first constructs the user dynamic topology sequence based on user historical behaviors. A convolutional neural network (CNN) is then used to extract features from the sequence. To obtain the final representations of users and items, the latter module uses MF and a fully connected (FC) neural network to model the dynamic topology features and static user-item interactive information. Next, another FC layer, which can be regarded as a nonlinear interaction function, is used to predict the probability of a user clicking on an item. Comprehensive experiments on a real dataset show that User-DTMF outperforms the best benchmark method by a margin of 1.68% and 3.05% in terms of Recall@10 and NDCG@10, respectively.

Who to show the ad to? Behavioral targeting in Internet advertising

PurposeThe performance of behavioral targeting (BT) mainly relies on the effectiveness of user classification since advertisers always want to target their advertisements to the most relevant users. In this paper, the authors frame the BT as a user classification problem and describe a machine learning–based approach for solving it.Design/methodology/approachTo perform such a study, two major research questions are investigated: the first question is how to represent a user’s online behavior. A good representation strategy should be able to effectively classify users based on their online activities. The second question is how different representation strategies affect the targeting performance. The authors propose three user behavior representation methods and compare them empirically using the area under the receiver operating characteristic curve (AUC) as a performance measure.FindingsThe experimental results indicate that ad campaign effectiveness can be significantly improved by combining user search queries, clicked URLs and clicked ads as a user profile. In addition, the authors also explore the temporal aspect of user behavior history by investigating the effect of history length on targeting performance. The authors note that an improvement of approximately 6.5% in AUC is achieved when user history is extended from 1 day to 14 days, which is substantial in targeting performance.Originality/valueThis paper confirms the effectiveness of BT on user classification and provides a validation of BT for Internet advertising.

Temporal dynamics of requirements engineering from mobile app reviews.

Opinion mining for app reviews aims to analyze people’s comments from app stores to support data-driven requirements engineering activities, such as bug report classification, new feature requests, and usage experience. However, due to a large amount of textual data, manually analyzing these comments is challenging, and machine-learning-based methods have been used to automate opinion mining. Although recent methods have obtained promising results for extracting and categorizing requirements from users’ opinions, the main focus of existing studies is to help software engineers to explore historical user behavior regarding software requirements. Thus, existing models are used to support corrective maintenance from app reviews, while we argue that this valuable user knowledge can be used for preventive software maintenance. This paper introduces the temporal dynamics of requirements analysis to answer the following question: how to predict initial trends on defective requirements from users’ opinions before negatively impacting the overall app’s evaluation? We present the MAPP-Reviews (Monitoring App Reviews) method, which (i) extracts requirements with negative evaluation from app reviews, (ii) generates time series based on the frequency of negative evaluation, and (iii) trains predictive models to identify requirements with higher trends of negative evaluation. The experimental results from approximately 85,000 reviews show that opinions extracted from user reviews provide information about the future behavior of an app requirement, thereby allowing software engineers to anticipate the identification of requirements that may affect the future app’s ratings.

Message Transmission Strategy Based on Recurrent Neural Network and Attention Mechanism in Iot System

With the popularization of the Internet of Things technology and the improvement of 5G communication technology, the influence of mobile devices on the network structure is increasing. The devices in the network are usually regarded as social users that transmit information. Because the movement of users is dynamic and random, it is more difficult for complex networks to grasp the changing rules of their topological structure. The data transmission model established by considering only the historical behavior of users can no longer meet the demand for fast transmission of large-capacity data. Based on this, this paper proposes a dynamic personalized data transmission model (GRDPS) that considers the recurrent neural network and attention mechanism. First, it uses a recurrent neural network to build users’ personalized preferences and model the user’s historical behavior. Then, GRDPS introduces an attention mechanism to dynamically weight historical user behaviors based on the user’s current message transmission. It is different from the previous methods of modeling user historical behaviors. Based on the requirements of user dynamics, GRDPS effectively considers the temporal characteristics of user historical behaviors and automatically learns the evolution law of user behaviors. Based on the demand of user randomness, GRDPS fully considers the characteristic correlation between the user’s historical behavior and current transmission demand. Finally, GRDPS combines these two points to obtain a personalized ranking of users. The simulation results show that the delivery rate of GRDPS is up to 0.95. Moreover, its data transmission delay and network overhead are better than other methods in the experiment.

A Hybrid Neural Network Architecture to Predict Online Advertising Click-Through Rate Behaviors in Social Networks

People connected by huge-size socialnetworks are highly dependent on recommendation systems to discover interesting persons, contents, and commodities. Extracting user interests and modeling their evolutions from user historical behavior are vital for algorithms to judge whether users are interested in given persons and items. The existing methods have two shortcomings: firstly, they do not have the high-order ability to process temporal sequences, which leads to their inability to mine the evolution of user interests; secondly, the models take full large-scale information of items as input, which causes a severe problem of overfitting. Thus, we propose a new hybrid neural network, DGRU, which integrates Factorization-Machine Based Neural Network (DeepFM) and Gated Recurrent Unit Neural Network (GRU). The DeepFM component is responsible for performing the autonomic feature combination, and the GRU component is designed to model user interests and evolutions. The GRU component is fed with a series of 1 and 0 representing user click behaviors. It contains information on what users like and dislike. Moreover, the conciseness of the format is helpful to avoid the problem of overfitting. Experiments on three real datasets demonstrated that the proposed model has a better CTR prediction performance and robustness than the state-of-the-art models.

Sequential Recommendation through Graph Neural Networks and Transformer Encoder with Degree Encoding

Predicting users’ next behavior through learning users’ preferences according to the users’ historical behaviors is known as sequential recommendation. In this task, learning sequence representation by modeling the pairwise relationship between items in the sequence to capture their long-range dependencies is crucial. In this paper, we propose a novel deep neural network named graph convolutional network transformer recommender (GCNTRec). GCNTRec is capable of learning effective item representation in a user’s historical behaviors sequence, which involves extracting the correlation between the target node and multi-layer neighbor nodes on the graphs constructed under the heterogeneous information networks in an end-to-end fashion through a graph convolutional network (GCN) with degree encoding, while the capturing long-range dependencies of items in a sequence through the transformer encoder model. Using this multi-dimensional vector representation, items related to a user historical behavior sequence can be easily predicted. We empirically evaluated GCNTRec on multiple public datasets. The experimental results show that our approach can effectively predict subsequent relevant items and outperforms previous techniques.