Attribute-aware CF models aim at rating prediction given not only the historical rating given by users to items but also the information associated with users (e.g., age), items (e.g., price), and ratings (e.g., rating time). This paper surveys work in the past decade to develop attribute-aware CF systems and finds that they can be classified into four different categories mathematically. We provide readers not only with a high-level mathematical interpretation of the existing work in this area but also with mathematical insight into each category of models. Finally, we provide in-depth experiment results comparing the effectiveness of the major models in each category.

Attribute-aware CF models aim at rating prediction given not only the historical rating given by users to items but also the information associated with users (e.g., age), items (e.g., price), and ratings (e.g., rating time). This paper surveys work in the past decade to develop attribute-aware CF systems and finds that they can be classified into four different categories mathematically. We provide readers not only with a high-level mathematical interpretation of the existing work in this area but also with mathematical insight into each category of models. Finally, we provide in-depth experiment results comparing the effectiveness of the major models in each category.

Abstract Collaborative filtering (CF) is initiated by representing users and items as vectors, and seeks to describe the relationship between users and items at a profound level, thus predicting users’ preferred behavior. To address the issue that previous research ignored higher-order geographical interactions hidden in users’ historical behaviors, this paper proposes a location-aware neural graph collaborative filtering model (LA-NGCF), which incorporates location information of items for improving prediction performance. The model characterizes the interactions between items based on spatial decay law from a graph perspective and designs two strategies to capture the interaction effects of users and items considering node heterogeneity. An optimized loss function with spatial distances of items is also developed in the model. Extensive experiments are conducted on three publicly available real-world datasets to examine the effectiveness of our model. Results show that LA-NGCF achieves competitive performances compared with several state-of-the-art models, which suggests that location information of items is beneficial for improving the performance of personalized recommendations. This paper offers an approach to incorporate weighted interactions between items into CF algorithms and enriches the methods of utilizing geographical information for artificial intelligence applications.

Keywords: collaborative filtering, neural graph collaborative filtering, geographical location

This is the code and data of'"Location-aware neural graph collaborative filtering"

Attribute-aware CF models aim at rating prediction given not only the historical rating given by users to items but also the information associated with users (e.g., age), items (e.g., price), and ratings (e.g., rating time). This paper surveys work in the past decade to develop attribute-aware CF systems and finds that they can be classified into four different categories mathematically. We provide readers not only with a high-level mathematical interpretation of the existing work in this area but also with mathematical insight into each category of models. Finally, we provide in-depth experiment results comparing the effectiveness of the major models in each category.

A dataset for recommendations collected from ted.com which contains metadata fields for TED talks and user profiles with rating and commenting transactions.

The TED dataset contains all the audio-video recordings of the TED talks downloaded from the official TED website, http://www.ted.com, on April 27th 2012 (first version) and on September 10th 2012 (second version). No processing has been done on any of the metadata fields. The metadata was obtained by crawling the HTML source of the list of talks and users, as well as talk and user webpages using scripts written by Nikolaos Pappas at the Idiap Research Institute, Martigny, Switzerland. The dataset is shared under the Creative Commons license (the same as the content of the TED talks) which is stored in the COPYRIGHT file. The dataset is shared for research purposes which are explained in detail in the following papers. The dataset can be used to benchmark systems that perform two tasks, namely personalized recommendations and generic recommendations. Please check the CBMI 2013 paper for a detailed description of each task.

1. Nikolaos Pappas, Andrei Popescu-Belis, "Combining Content with User Preferences for TED Lecture Recommendation", 11th International Workshop on Content Based Multimedia Indexing, Veszprém, Hungary, IEEE, 2013
   PDF document, Bibtex citation
2. Nikolaos Pappas, Andrei Popescu-Belis, Sentiment Analysis of User Comments for One-Class Collaborative Filtering over TED Talks, 36th ACM SIGIR Conference on Research and Development in Information Retrieval, Dublin, Ireland, ACM, 2013
   PDF document, Bibtex citation

If you use the TED dataset for your research please cite one of the above papers (specifically the 1st paper for the April 2012 version and the 2nd paper for the September 2012 version of the dataset).

TED website

The TED website is a popular online repository of audiovisual recordings of public lectures given by prominent speakers, under a Creative Commons non-commercial license (see www.ted.com). The site provides extended metadata and user-contributed material. The speakers are scientists, writers, journalists, artists, and businesspeople from all over the world who are generally given a maximum of 18 minutes to present their ideas. The talks are given in English and are usually transcribed and then translated into several other languages by volunteer users. The quality of the talks has made TED one of the most popular online lecture repositories, as each talk was viewed on average almost 500,000 times.

Metadata

The dataset contains two main entry types: talks and users. The talks have the following data fields: identifier, title, description, speaker name, TED event at which they were given, transcript, publication date, filming date, number of views. Each talk has a variable number of user comments, organized in threads. In addition, three fields were assigned by TED editorial staff: related tags, related themes, and related talks. Each talk generally has three related talks and 95% of them have a high- quality transcript available. The dataset includes 1,149 talks from 960 speakers and 69,023 registered users that have made about 100,000 favorites and 200,000 comments.

The current worldwide pandemic has significantly increased the need for online learning platforms, hence presenting difficulty in choosing appropriate course materials from the vast online educational resources due to user knowledge frameworks variations. This paper presents a novel course recommendation system called the Deep Learning-based Course Recommendation System (DLCRS). The DLCRS combines a hybrid Sequential GRU+adam optimizer with collaborative filtering techniques to offer accurate and learner-centric course suggestions. The proposed approach integrates modules for learner feature extraction and course feature extraction that is performed using (Embeddings from Language Models) ELMO word embedding technique in order to gain a thorough understanding of learner and course profiles and feedback. In order to evaluate the efficacy of the proposed DLCRS, several extensive experiments were carried out utilizing authentic datasets sourced from a reputable public organization. The results indicate a notable area under the receiver operating characteristic curve (AUC) score of 89.62%, which exceeds the performance of similar advanced course recommendation systems. The experimental findings support the viability of the DLCRS, as seen by a significant hit ratio of 0.88, indicating high accuracy in its suggestions.

The current worldwide pandemic has significantly increased the need for online learning platforms, hence presenting difficulty in choosing appropriate course materials from the vast online educational resources due to user knowledge frameworks variations. This paper presents a novel course recommendation system called the Deep Learning-based Course Recommendation System (DLCRS). The DLCRS combines a hybrid Sequential GRU+adam optimizer with collaborative filtering techniques to offer accurate and learner-centric course suggestions. The proposed approach integrates modules for learner feature extraction and course feature extraction that is performed using (Embeddings from Language Models) ELMO word embedding technique in order to gain a thorough understanding of learner and course profiles and feedback. In order to evaluate the efficacy of the proposed DLCRS, several extensive experiments were carried out utilizing authentic datasets sourced from a reputable public organization. The results indicate a notable area under the receiver operating characteristic curve (AUC) score of 89.62%, which exceeds the performance of similar advanced course recommendation systems. The experimental findings support the viability of the DLCRS, as seen by a significant hit ratio of 0.88, indicating high accuracy in its suggestions.

The number of records, users, and items in each dataset after preprocessing.

With the rapid development of information technology, scientific social networks (SSNs) have become the fastest and most convenient way for researchers to communicate with each other. Many published papers are shared via SSNs every day, resulting in the problem of information overload. How to appropriately recommend personalized and highly valuable papers for researchers is becoming more urgent. However, when recommending papers in SSNs, only a small amount of positive instances are available, leaving a vast amount of unlabelled data, in which negative instances and potential unseen positive instances are mixed together, which naturally belongs to One-Class Collaborative Filtering (OCCF) problem. Therefore, considering the extreme data imbalance and data sparsity of this OCCF problem, a hybrid approach of Social and Content aware One-class Recommendation of Papers in SSNs, termed SCORP, is proposed in this study. Unlike previous approaches recommended to address the OCCF problem, social information, which has been proved playing a significant role in performing recommendations in many domains, is applied in both the profiling of content-based filtering and the collaborative filtering to achieve superior recommendations. To verify the effectiveness of the proposed SCORP approach, a real-life dataset from CiteULike was employed. The experimental results demonstrate that the proposed approach is superior to all of the compared approaches, thus providing a more effective method for recommending papers in SSNs.

In today’s society, time is considered more valuable than money, and researchers often have limited time to find relevant papers for their research. Identifying and accessing essential information can be a challenge in this situation. To address this, the personalized suggestion system has been developed, which uses a user’s behavior data to suggest relevant items. The collaborative filtering strategy has been used to provide a user with the top research articles based on their queries and similarities with other users’ questions, thus saving time by avoiding time-consuming searches. However, when rating data is abundant but sparse, the usual method of determining user similarity is relatively straightforward. Furthermore, it fails to account for changes in users’ interests over time resulting in poor performance. This research proposes a new similarity measure approach that takes both user confidence and time context into account to increase user similarity computation. The experimental results show that the proposed technique works well with sparse data, and improves accuracy by 16.2% compared to existing models, especially during prediction. Furthermore, it enhances the quality of recommendations.

Comparison of proposed algorithm with random, K-Means and Collaborative Filtering in terms of coverage, RMSE, and ROC.

Comparison of the experimental results on ML-1M, Epinions, and Yelp datasets using the HR.

Comparison of the related works with respect to the neighbor concept.

The number of records, users, and item in each dataset.

Statistic of each dataset.

Comparison of the experimental results on the ML-1M, Epinions, and Yelp datasets using nDCG.

Attribute-aware CF models aim at rating prediction given not only the historical rating given by users to items but also the information associated with users (e.g., age), items (e.g., price), and ratings (e.g., rating time). This paper surveys work in the past decade to develop attribute-aware CF systems and finds that they can be classified into four different categories mathematically. We provide readers not only with a high-level mathematical interpretation of the existing work in this area but also with mathematical insight into each category of models. Finally, we provide in-depth experiment results comparing the effectiveness of the major models in each category.

Recommender systems play a vital role in enhancing the user experience and facilitating content discovery on online platforms. However, conventional approaches often struggle to capture users’ evolving preferences over time, leading to suboptimal performance as recommended videos frequently do not align with users’ interests. To address this issue, this study introduces an innovative method that leverages watch-time duration to analyze long-term user behavior and generate personalized recommendations. The proposed Duration Count Matrix (DCM) technique includes two key components: User Profiling (DCM-UP) and User Similarity (DCM-US). DCM-UP constructs dynamic user profiles based on engagement with content, while DCM-US quantifies user similarity through collaborative filtering, enabling the system to predict user-to-user behavior and personalize recommendations. This innovative system, DCM-UP, utilizes matrix-based representations of users and items, dynamically updates profiles, and adapts to changing preferences over time, thus providing a more accurate reflection of user interests. Additionally, DCM-US facilitates the identification of user similarities by analyzing user-item generalizations. Moreover, the effectiveness of the proposed techniques was evaluated on a real-world dataset obtained from JAWWY, the Saudi Telecom Company. The study’s results clearly demonstrated that the DCM approach significantly outperformed existing state-of-the-art methods across various performance metrics, including precision, recall, F1-score, and accuracy. This highlights the superiority of the DCM technique in capturing and predicting long-term user behavior for more accurate and personalized recommendations.

The current worldwide pandemic has significantly increased the need for online learning platforms, hence presenting difficulty in choosing appropriate course materials from the vast online educational resources due to user knowledge frameworks variations. This paper presents a novel course recommendation system called the Deep Learning-based Course Recommendation System (DLCRS). The DLCRS combines a hybrid Sequential GRU+adam optimizer with collaborative filtering techniques to offer accurate and learner-centric course suggestions. The proposed approach integrates modules for learner feature extraction and course feature extraction that is performed using (Embeddings from Language Models) ELMO word embedding technique in order to gain a thorough understanding of learner and course profiles and feedback. In order to evaluate the efficacy of the proposed DLCRS, several extensive experiments were carried out utilizing authentic datasets sourced from a reputable public organization. The results indicate a notable area under the receiver operating characteristic curve (AUC) score of 89.62%, which exceeds the performance of similar advanced course recommendation systems. The experimental findings support the viability of the DLCRS, as seen by a significant hit ratio of 0.88, indicating high accuracy in its suggestions.

Considering that traditional biological experiments are expensive and time consuming, it is important to develop effective computational models to infer potential essential proteins. In this manuscript, a novel collaborative filtering model-based method called CFMM was proposed, in which, an updated protein–domain interaction (PDI) network was constructed first by applying collaborative filtering algorithm on the original PDI network, and then, through integrating topological features of PDI networks with biological features of proteins, a calculative method was designed to infer potential essential proteins based on an improved PageRank algorithm. The novelties of CFMM lie in construction of an updated PDI network, application of the commodity-customer-based collaborative filtering algorithm, and introduction of the calculation method based on an improved PageRank algorithm, which ensured that CFMM can be applied to predict essential proteins without relying entirely on known protein–domain associations. Simulation results showed that CFMM can achieve reliable prediction accuracies of 92.16, 83.14, 71.37, 63.87, 55.84, and 52.43% in the top 1, 5, 10, 15, 20, and 25% predicted candidate key proteins based on the DIP database, which are remarkably higher than 14 competitive state-of-the-art predictive models as a whole, and in addition, CFMM can achieve satisfactory predictive performances based on different databases with various evaluation measurements, which further indicated that CFMM may be a useful tool for the identification of essential proteins in the future.