Search results

In this “Info-plosion” era, recommendation systems (or recommenders) play a significant role in finding interesting items in the surge of online digital activity and e-commerce. The purpose of this paper is to model users' preference evolution to recommend potential items which users may be interested in.

A novel recommendation system, namely evolution-learning recommendation (ELR), is developed to precisely predict user interest for making recommendations. Differing from prior related methods, the authors integrate the matrix factorization (MF) and recurrent neural network (RNN) to effectively describe the variation of user preferences over time.

A novel cumulative factorization technique is proposed to efficiently decompose a rating matrix for discovering latent user preferences. Compared to traditional MF-based methods, the cumulative MF could reduce the utilization of computation resources. Furthermore, the authors depict the significance of long- and short-term effects in the memory cell of RNN for evolution patterns. With the context awareness, a learning model, V-LSTM, is developed to dynamically capture the evolution pattern of user interests. By using a well-trained learning model, the authors predict future user preferences and recommend related items.

Based on the relations among users and items for recommendation, the authors introduce a novel concept, virtual communication, to effectively learn and estimate the correlation among users and items. By incorporating the discovered latent features of users and items in an evolved manner, the proposed ELR model could promote “right” things to “right” users at the “right” time. In addition, several extensive experiments are performed on real datasets and are discussed. Empirical results show that ELR significantly outperforms the prior recommendation models. The proposed ELR exhibits great generalization and robustness in real datasets, including e-commerce, industrial retail and streaming service, with all discussed metrics.

The explosion of data due to the sophistication of information and communication technology makes it simple for prospective tourists to learn about previous hotel guests' experiences. They prioritize the rating score when selecting a hotel. However, rating scores are less reliable for suggesting a personalized preference for each aspect, especially when they are in a limited number. This study aims to recommend ratings and personalized preference hotels using cross-domain and aspect-based features.

We propose an aspect-based cross-domain personalized recommendation (AsCDPR), a novel framework for rating prediction and personalized customer preference recommendations. We incorporate a cross-domain personalized approach and aspect-based features of items from the review text. We extracted aspect-based feature vectors from two domains using bidirectional long short-term memory and then mapped them by a multilayer perceptron (MLP). The cross-domain recommendation module trains MLP to analyze sentiment and predict item ratings and the polarities of the aspect based on user preferences.

Expanded by its synonyms, aspect-based features significantly improve the performance of sentiment analysis on accuracy and the F1-score matrix. With relatively low mean absolute error and root mean square error values, AsCDPR outperforms matrix factorization, collaborative matrix factorization, EMCDPR and Personalized transfer of user preferences for cross-domain recommendation. These values are 1.3657 and 1.6682, respectively.

This study assists users in recommending hotels based on their priority preferences. Users do not need to read other people's reviews to capture the key aspects of items. This model could enhance system reliability in the hospitality industry by providing personalized recommendations.

This study introduces a new approach that embeds aspect-based features of items in a cross-domain personalized recommendation. AsCDPR predicts ratings and provides recommendations based on priority aspects of each user's preferences.

Online news websites provide huge amounts of timely news, bringing the challenge of recommending personalized news articles. Generative adversarial networks (GAN) based on collaborative filtering (CFGAN) can achieve effective recommendation quality. However, CFGAN ignores item contents, which contain more latent preference features than just user ratings. It is important to consider both ratings and item contents in making preference predictions. This study aims to improve news recommendation by proposing a GAN-based news recommendation model considering both ratings (implicit feedback) and the latent features of news content.

The collaborative topic modeling (CTM) can improve user preference prediction by combining matrix factorization (MF) with latent topics of item content derived from latent topic modeling. This study proposes a novel hybrid news recommendation model, Hybrid-CFGAN, which modifies the architecture of the CFGAN model with enhanced preference learning from the CTM. The proposed Hybrid-CFGAN model contains parallel neural networks – original rating-based preference learning and CTM-based preference learning, which consider both ratings and news content with user preferences derived from the CTM model. A tunable parameter is used to adjust the weights of the two preference learnings, while concatenating the preference outputs of the two parallel neural networks.

This study uses the dataset collected from an online news website, NiusNews, to conduct an experimental evaluation. The results show that the proposed Hybrid-CFGAN model can achieve better performance than the state-of-the-art GAN-based recommendation methods. The proposed novel Hybrid-CFGAN model can enhance existing GAN-based recommendation and increase the performance of preference predictions on textual content such as news articles.

As the existing CFGAN model does not consider content information and solely relies on history logs, it may not be effective in recommending news articles. Our proposed Hybrid-CFGAN model modified the architecture of the CFGAN generator by adding a parallel neural network to gain the relevant information from news content and user preferences derived from the CTM model. The novel idea of adjusting the preference learning from two parallel neural networks – original rating-based preference learning and CTM-based preference learning – contributes to improve the recommendation quality of the proposed model by considering both ratings and latent preferences derived from item contents. The proposed novel recommendation model can improve news recommendation, thereby increasing the commercial value of news media platforms.

Using the data set about the restaurants from different countries and their customer's feedback, the purpose of this paper is to address the following issues: in the restaurant industry, how have user behavior and preferences changed during the COVID-19 restrictions period, how did these changes influence the performance of recommendation algorithms and which methods can be proposed to improve the quality of restaurant recommendations in a lockdown scenario.

To assess changes in user behavior and preferences, quantitative and qualitative data analysis was performed to assess the changes in user behavior and preferences. The authors compared the situation before and during the COVID-19 restrictions period. To evaluate the performance of restaurant recommendation systems in a non-stationary setting, the authors tested state-of-the-art collaborative filtering algorithms. This study proposes and investigates a filtering-based approach to improve the quality of recommendation algorithms for a lockdown scenario.

This study revealed that during the COVID-19 restrictions period, the average rating values and the number of reviews have changed. The experimental study confirmed that: the performance of all state-of-the-art recommender systems for the restaurant industry has significantly degraded during the COVID-19 restrictions period; and the accuracy and the stability of restaurant recommendations in non-stationary settings may be improved using the sliding window and post-filtering methods.

The authors propose two novel methods: the sliding window and closed restaurants post-filtering method based on the CatBoost classification model. These methods can be applied to classical collaborative recommender algorithms and increase the value of metrics under non-stationary conditions. These methods can be helpful for developers of recommender systems and massive aggregators of restaurants and hotels. Thus, it benefits both the app end-user and business owners because users honestly rate restaurants when they receive good recommendations and do not downgrade because of external factors.

To the best of the authors’ knowledge, this paper provides the first extensive and multifaceted experimental study of the impact of COVID-19 restrictions on the effectiveness of restaurant recommendation systems in different countries. Two novel methods to tackle restaurant recommendations' performance degradation are proposed and validated.

利用关于不同国家餐厅及其顾客反馈的数据, 我们探索了以下问题：(i) 在餐饮行业, 用户行为和偏好在COVID-19限制期间如何改变, (ii) 这些变化如何影响推荐算法的性能, 以及 (iii) 可以提出哪些方法来改进封锁情景下的餐厅推荐质量。

为了评估用户行为和偏好的变化, 本研究进行了定量和定性数据分析, 对比了COVID-19限制期前后的情况。为了评估非稳态环境中餐厅推荐系统的性能, 我们测试了最先进的协同过滤算法。我们提出并研究了一种基于过滤的方法, 以提高封锁情景下推荐算法的质量。

研究发现, 在COVID-19限制期间, 平均评分和评论数量发生了变化。实验研究证实：(i) 在COVID-19限制期间, 所有最先进的餐厅行业推荐系统的性能显著下降; (ii) 使用滑动窗口和后过滤方法可以改进非稳态环境下餐厅推荐的准确性和稳定性。

我们提出了两种新方法：基于CatBoost分类模型的关闭餐厅后过滤和滑动窗口方法。这些方法可以应用于经典的协同过滤推荐算法, 并在非稳态条件下提高指标值。这些方法对于推荐系统的开发者和大规模餐厅和酒店聚合平台都有帮助。因此, 这对于应用的最终用户和企业主都有好处, 因为当用户得到良好的推荐时, 他们会诚实地对餐厅进行评价, 而不会因为外部因素降低评分。

本文首次提供了COVID-19限制对不同国家餐厅推荐系统有效性影响的广泛多方面的实验研究, 并提出和验证了两种解决餐厅推荐性能下降问题的新方法。

The purpose of this paper is to provide adaptive access to learning resources in the digital library.

A novel method using ontology-based multi-attribute collaborative filtering is proposed. Digital libraries are those which are fully automated and all resources are in digital form and access to the information available is provided to a remote user as well as a conventional user electronically. To satisfy users' information needs, a humongous amount of newly created information is published electronically in digital libraries. While search applications are improving, it is still difficult for the majority of users to find relevant information. For better service, the framework should also be able to adapt queries to search domains and target learners.

This paper improves the accuracy and efficiency of predicting and recommending personalized learning resources in digital libraries. To facilitate a personalized digital learning environment, the authors propose a novel method using ontology-supported collaborative filtering (CF) recommendation system. The objective is to provide adaptive access to learning resources in the digital library. The proposed model is based on user-based CF which suggests learning resources for students based on their course registration, preferences for topics and digital libraries. Using ontological framework knowledge for semantic similarity and considering multiple attributes apart from learners' preferences for the learning resources improve the accuracy of the proposed model.

The results of this work majorly rely on the developed ontology. More experiments are to be conducted with other domain ontologies.

The proposed approach is integrated into Nucleus, a Learning Management System (https://nucleus.amcspsgtech.in). The results are of interest to learners, academicians, researchers and developers of digital libraries. This work also provides insights into the ontology for e-learning to improve personalized learning environments.

This paper computes learner similarity and learning resources similarity based on ontological knowledge, feedback and ratings on the learning resources. The predictions for the target learner are calculated and top N learning resources are generated by the recommendation engine using CF.

With the increasing number of mobile applications, efficiently recommending mobile applications to users has become a challenging problem. Although existing mobile application recommendation approaches based on user attributes and behaviors have achieved notable effectiveness, they overlook the diffusion patterns and interdependencies of topic-specific mobile applications among user groups. mobile applications among user groups. This paper aims to capture the diffusion patterns and interdependencies of mobile applications among user groups. To achieve this, a topic-aware neural network-based mobile application recommendation method, referred to as TN-MR, is proposed.

In this method, first, the user representations are enhanced by introducing a topic-aware attention layer, which captures both the topic context and the diffusion history context. Second, it exploits a time-decay mechanism to simulate changes in user interest. Multitopic user representations are aggregated by the time decay module to output the user representations of cascading representations under multiple topics. Finally, user scores that are likely to download the mobile application are predicted and ranked.

Experimental comparisons and analyses were conducted on the actual 360App data set, and the results demonstrate that the effectiveness of mobile application recommendations can be significantly improved by using TN-MR.

In this paper, the authors propose a mobile application recommendation method based on topic-aware attention networks. By capturing the diffusion patterns and dependencies of mobile applications, it effectively assists users in selecting their applications of interest from thousands of options, significantly improving the accuracy of mobile application recommendations.

Online reviews are regarded as a source of information for decision-making because of the abundance and ready availability of information. Whereas, the sheer volume of online reviews makes it hard for consumers, especially the older adults who perceive more difficulties in reading reviews and obtaining information compared to younger adults, to locate the useful ones. The main objective of this study is to propose an effective method to locate valuable reviews of mobile phones for older adults. Besides, the authors also want to explore what characteristics of the technology older adults prefer. This will benefit both e-retailers and e-commerce platforms.

After collecting online reviews related to mobile phones designed for older adults from a popular Chinese e-commerce platform (JD Mall), topic modeling, term frequency-inverse document frequency (TF-IDF), and linguistic inquiry and word count (LIWC) methods were applied to extract latent topics and uncover potential dimensions that consumers frequently referred to in their reviews. According to consumers' attitudes towards different popular topics, seven machine learning models were employed to predict the usefulness and popularity of online reviews due to their excellent performance in prediction. To improve the performance, a weighted model based on the two best-performing models was built and evaluated.

Based on the TF-IDF, topic modeling, and LIWC methods, the authors find that older adults are more interested in the exterior, sound, and communication functions of mobile phones. Besides, the weighted model (Random Forest: Decision Tree = 2:1) is the best model for predicting the online review popularity, while random forest performs best in predicting the perceived usefulness of online reviews.

This study’s findings can help e-commerce platforms and merchants identify the needs of the targeted consumers, predict reviews that will get more attention, and provide some early responses to some questions.

The results propose that older adults pay more attention to the mobile phones' exterior, sound, and communication function, guiding future research. Besides, this paper also enriches the current studies related to making predictions based on the information contained in the online reviews.

Communities representing groups of agents with similar interests or functions are one of the essential features of complex networks. Finding communities in real-world networks is critical for analyzing complex systems in various areas ranging from collaborative information to political systems. Given the different characteristics of networks and the capability of community detection in handling a plethora of societal problems, community detection methods represent an emerging area of research. Contributing to this field, the authors propose a new community detection algorithm based on the hybridization of node and link granulation.

The proposed algorithm utilizes a rough set-theoretic concept called closure on networks. Initial sets are constructed by using neighborhood topology around the nodes as well as links and represented as two different categories of granules. Subsequently, the authors iteratively obtain the constrained closure of these sets. The authors use node mutuality and link mutuality as merging criteria for node and link granules, respectively, during the iterations. Finally, the constrained closure subsets of nodes and links are combined and refined using the Jaccard similarity coefficient and a local density function to obtain communities in a binary network.

Extensive experiments conducted on twelve real-world networks followed by a comparison with state-of-the-art methods demonstrate the viability and effectiveness of the proposed algorithm.

The study also contributes to the ongoing effort related to the application of soft computing techniques to model complex systems. The extant literature has integrated a rough set-theoretic approach with a fuzzy granular model (Kundu and Pal, 2015) and spectral clustering (Huang and Xiao, 2012) for node-centric community detection in complex networks. In contributing to this stream of work, the proposed algorithm leverages the unexplored synergy between rough set theory, node granulation and link granulation in the context of complex networks. Combined with experiments of network datasets from various domains, the results indicate that the proposed algorithm can effectively reveal co-occurring disjoint, overlapping and nested communities without necessarily assigning each node to a community.

This study carries important practical implications for complex adaptive systems in business and management sciences, in which entities are increasingly getting organized into communities (Jacucci et al., 2006). The proposed community detection method can be used for network-based fraud detection by enabling experts to understand the formation and development of fraudulent setups with an active exchange of information and resources between the firms (Van Vlasselaer et al., 2017). Products and services are getting connected and mapped in every walk of life due to the emergence of a variety of interconnected devices, social networks and software applications.

The proposed algorithm could be extended for community detection on customer trajectory patterns and design recommendation systems for online products and services (Ghose et al., 2019; Liu and Wang, 2017). In line with prior research, the proposed algorithm can aid companies in investigating the characteristics of implicit communities of bloggers or social media users for their services and products so as to identify peer influencers and conduct targeted marketing (Chau and Xu, 2012; De Matos et al., 2014; Zhang et al., 2016). The proposed algorithm can be used to understand the behavior of each group and the appropriate communication strategy for that group. For instance, a group using a specific language or following a specific account might benefit more from a particular piece of content than another group. The proposed algorithm can thus help in exploring the factors defining communities and confronting many real-life challenges.

This work is based on a theoretical argument that communities in networks are not only based on compatibility among nodes but also on the compatibility among links. Building up on the aforementioned argument, the authors propose a community detection method that considers the relationship among both the entities in a network (nodes and links) as opposed to traditional methods, which are predominantly based on relationships among nodes only.

Given the critical role of user-generated content (UGC) in e-commerce, exploring various aspects of UGC can aid in understanding user purchase intention and commodity recommendation. Therefore, this study investigates the impact of UGC on purchase decisions and proposes new recommendation models based on sentiment analysis, which are verified in Douban, one of the most popular UGC websites in China.

After verifying the relationship between various factors and product sales, this study proposes two models, collaborative filtering recommendation model based on sentiment (SCF) and hidden factors topics recommendation model based on sentiment (SHFT), by combining traditional collaborative filtering model (CF) and hidden factors topics model (HFT) with sentiment analysis.

The results indicate that sentiment significantly influences purchase intention. Furthermore, the proposed sentiment-based recommendation models outperform traditional CF and HFT in terms of mean absolute error (MAE) and root mean square error (RMSE). Moreover, the two models yield different outcomes for various product categories, providing actionable insights for organizers to implement more precise recommendation strategies.

The findings of this study advocate the incorporation of UGC sentimental factors into websites to heighten recommendation accuracy. Additionally, different recommendation strategies can be employed for different products types.

This study introduces a novel perspective to the recommendation algorithm field. It not only validates the impact of UGC sentiment on purchase intention but also evaluates the proposed models with real-world data. The study provides valuable insights for managerial decision-making aimed at enhancing recommendation systems.

Community detection of dynamic networks provides more effective information than static network community detection in the real world. The mainstream method for community detection in dynamic networks is evolutionary clustering, which uses temporal smoothness of community structures to connect snapshots of networks in adjacent time intervals. However, the error accumulation issues limit the effectiveness of evolutionary clustering. While the multi-objective evolutionary approach can solve the issue of fixed settings of the two objective function weight parameters in the evolutionary clustering framework, the traditional multi-objective evolutionary approach lacks self-adaptability.

This paper proposes a community detection algorithm that integrates evolutionary clustering and decomposition-based multi-objective optimization methods. In this approach, a benchmark correction procedure is added to the evolutionary clustering framework to prevent the division results from drifting.

Experimental results demonstrate the superior accuracy of this method compared to similar algorithms in both real and synthetic dynamic datasets.

To enhance the clustering results, adaptive variances and crossover probabilities are designed based on the relative change amounts of the subproblems decomposed by MOEA/D (A Multiobjective Optimization Evolutionary Algorithm based on Decomposition) to dynamically adjust the focus of different evolutionary stages.