Applied Sciences

Editorial

Jump to: Research

4 pages, 159 KiB

Open AccessEditorial

Recommender Systems and Collaborative Filtering

by Fernando Ortega and Ángel González-Prieto

Appl. Sci. 2020, 10(20), 7050; https://doi.org/10.3390/app10207050 - 11 Oct 2020

Cited by 6 | Viewed by 2494

Abstract

Recommender Systems (RSs) have become an essential tool for the information society [...] Full article

(This article belongs to the Special Issue Recommender Systems and Collaborative Filtering)

Research

Jump to: Editorial

18 pages, 1593 KiB

Open AccessArticle

Optimizing Latent Factors and Collaborative Filtering for Students’ Performance Prediction

by Juan A. Gómez-Pulido, Arturo Durán-Domínguez and Francisco Pajuelo-Holguera

Appl. Sci. 2020, 10(16), 5601; https://doi.org/10.3390/app10165601 - 12 Aug 2020

Cited by 13 | Viewed by 2369

Abstract

The problem of predicting students’ performance has been recently tackled by using matrix factorization, a popular method applied for collaborative filtering based recommender systems. This problem consists of predicting the unknown performance or score of a particular student for a task s/he did [...] Read more.

The problem of predicting students’ performance has been recently tackled by using matrix factorization, a popular method applied for collaborative filtering based recommender systems. This problem consists of predicting the unknown performance or score of a particular student for a task s/he did not complete or did not attend, according to the scores of the tasks s/he did complete and the scores of the colleagues who completed the task in question. The solving method considers matrix factorization and a gradient descent algorithm in order to build a prediction model that minimizes the error in the prediction of test data. However, we identified two key aspects that influence the accuracy of the prediction. On the one hand, the model involves a pair of important parameters: the learning rate and the regularization factor, for which there are no fixed values for any experimental case. On the other hand, the datasets are extracted from virtual classrooms on online campuses and have a number of implicit latent factors. The right figures are difficult to ascertain, as they depend on the nature of the dataset: subject, size, type of learning, academic environment, etc. This paper proposes some approaches to improve the prediction accuracy by optimizing the values of the latent factors, learning rate, and regularization factor. To this end, we apply optimization algorithms that cover a wide search space. The experimental results obtained from real-world datasets improved the prediction accuracy in the context of a thorough search for predefined values. Obtaining optimized values of these parameters allows us to apply them to further predictions for similar datasets. Full article

(This article belongs to the Special Issue Recommender Systems and Collaborative Filtering)

► Show Figures

Figure 1

18 pages, 3831 KiB

Open AccessArticle

An Attention-Based Latent Information Extraction Network (ALIEN) for High-Order Feature Interactions

by Ruo Huang, Shelby McIntyre, Meina Song, Haihong E and Zhonghong Ou

Appl. Sci. 2020, 10(16), 5468; https://doi.org/10.3390/app10165468 - 7 Aug 2020

Cited by 5 | Viewed by 2130

Abstract

One of the primary tasks for commercial recommender systems is to predict the probabilities of users clicking items, e.g., advertisements, music and products. This is because such predictions have a decisive impact on profitability. The classic recommendation algorithm, collaborative filtering (CF), still plays [...] Read more.

One of the primary tasks for commercial recommender systems is to predict the probabilities of users clicking items, e.g., advertisements, music and products. This is because such predictions have a decisive impact on profitability. The classic recommendation algorithm, collaborative filtering (CF), still plays a vital role in many industrial recommender systems. However, although straight CF is good at capturing similar users’ preferences for items based on their past interactions, it lacks regarding (1) modeling the influences of users’ sequential patterns from their individual history interaction sequences and (2) the relevance of users’ and items’ attributes. In this work, we developed an attention-based latent information extraction network (ALIEN) for click-through rate prediction, to integrate (1) implicit user similarity in terms of click patterns (analogous to CF), and (2) modeling the low and high-order feature interactions and (3) historical sequence information. The new model is based on the deep learning, which goes beyond the capabilities of econometric approaches, such as matrix factorization (MF) and k-means. In addition, the approach provides explainability to the recommendation by interpreting the contributions of different features and historical interactions. We have conducted experiments on real-world datasets that demonstrate considerable improvements over strong baselines. Full article

(This article belongs to the Special Issue Recommender Systems and Collaborative Filtering)

► Show Figures

Figure 1

21 pages, 7097 KiB

Open AccessArticle

Enabling “Untact” Culture via Online Product Recommendations: An Optimized Graph-CNN based Approach

by Wafa Shafqat and Yung-Cheol Byun

Appl. Sci. 2020, 10(16), 5445; https://doi.org/10.3390/app10165445 - 6 Aug 2020

Cited by 12 | Viewed by 3423

Abstract

The COVID-19 pandemic is swiftly changing our behaviors toward online channels across the globe. Cultural patterns of working, thinking, shopping, and use of technology are changing accordingly. Customers are seeking convenience in online shopping. It is the peak time to assist the digital [...] Read more.

The COVID-19 pandemic is swiftly changing our behaviors toward online channels across the globe. Cultural patterns of working, thinking, shopping, and use of technology are changing accordingly. Customers are seeking convenience in online shopping. It is the peak time to assist the digital marketplace with right kind of tools and technologies that uses the strategy of click and collect. Session-based recommendation systems have the potential to be equally useful for both the customers and the service providers. These frameworks can foresee customer’s inclinations and interests, by investigating authentic information on their conduct and activities. Various methods exist and are pertinent in various situations. We propose a product recommendation system that uses a graph convolutional neural network (GCN)-based approach to recommend products to users by analyzing their previous interactions. Unlike other conventional techniques, GCN is not widely explored in recommendation systems. Therefore, we propose a variation of GCN that uses optimization strategy for better representation of graphs. Our model uses session-based data to generate patterns. The input patterns are encoded and passed to embedding layer. GCN uses the session graphs as input. The experiments on data show that the optimized GCN (OpGCN) was able to achieve higher prediction rate with around 93% accuracy as compared with simple GCN (around 88%). Full article

(This article belongs to the Special Issue Recommender Systems and Collaborative Filtering)

► Show Figures

Figure 1

32 pages, 3514 KiB

Open AccessArticle

Time-Aware Music Recommender Systems: Modeling the Evolution of Implicit User Preferences and User Listening Habits in A Collaborative Filtering Approach

by Diego Sánchez-Moreno, Yong Zheng and María N. Moreno-García

Appl. Sci. 2020, 10(15), 5324; https://doi.org/10.3390/app10155324 - 31 Jul 2020

Cited by 15 | Viewed by 3992

Abstract

Online streaming services have become the most popular way of listening to music. The majority of these services are endowed with recommendation mechanisms that help users to discover songs and artists that may interest them from the vast amount of music available. However, [...] Read more.

Online streaming services have become the most popular way of listening to music. The majority of these services are endowed with recommendation mechanisms that help users to discover songs and artists that may interest them from the vast amount of music available. However, many are not reliable as they may not take into account contextual aspects or the ever-evolving user behavior. Therefore, it is necessary to develop systems that consider these aspects. In the field of music, time is one of the most important factors influencing user preferences and managing its effects, and is the motivation behind the work presented in this paper. Here, the temporal information regarding when songs are played is examined. The purpose is to model both the evolution of user preferences in the form of evolving implicit ratings and user listening behavior. In the collaborative filtering method proposed in this work, daily listening habits are captured in order to characterize users and provide them with more reliable recommendations. The results of the validation prove that this approach outperforms other methods in generating both context-aware and context-free recommendations. Full article

(This article belongs to the Special Issue Recommender Systems and Collaborative Filtering)

► Show Figures

Figure 1

14 pages, 946 KiB

Open AccessArticle

Deep Matrix Factorization Approach for Collaborative Filtering Recommender Systems

by Raúl Lara-Cabrera, Ángel González-Prieto and Fernando Ortega

Appl. Sci. 2020, 10(14), 4926; https://doi.org/10.3390/app10144926 - 17 Jul 2020

Cited by 28 | Viewed by 6563

Abstract

Providing useful information to the users by recommending highly demanded products and services is a fundamental part of the business of many top tier companies. Recommender Systems make use of many sources of information to provide users with accurate predictions and novel recommendations [...] Read more.

Providing useful information to the users by recommending highly demanded products and services is a fundamental part of the business of many top tier companies. Recommender Systems make use of many sources of information to provide users with accurate predictions and novel recommendations of items. Here we propose, DeepMF, a novel collaborative filtering method that combines the Deep Learning paradigm with Matrix Factorization (MF) to improve the quality of both predictions and recommendations made to the user. Specifically, DeepMF performs successive refinements of a MF model with a layered architecture that uses the acquired knowledge in a layer as input for subsequent layers. Experimental results showed that the quality of both the predictions and recommendations of DeepMF overcome the baselines. Full article

(This article belongs to the Special Issue Recommender Systems and Collaborative Filtering)

► Show Figures

Figure 1

21 pages, 1450 KiB

Open AccessArticle

Personalized Standard Deviations Improve the Baseline Estimation of Collaborative Filtering Recommendation

by Zhenhua Tan, Liangliang He, Danke Wu, Qiuyun Chang and Bin Zhang

Appl. Sci. 2020, 10(14), 4756; https://doi.org/10.3390/app10144756 - 10 Jul 2020

Cited by 6 | Viewed by 2898

Abstract

Baseline estimation is a critical component for latent factor-based collaborative filtering (CF) recommendations to obtain baseline predictions by evaluating global deviations for both users and items from personalized ratings. Classical baseline estimation presupposes that the user’s factual rating range is the same as [...] Read more.

Baseline estimation is a critical component for latent factor-based collaborative filtering (CF) recommendations to obtain baseline predictions by evaluating global deviations for both users and items from personalized ratings. Classical baseline estimation presupposes that the user’s factual rating range is the same as the system’s given rating range. However, from observations on real datasets of movie recommender systems, we found that different users have different actual rating ranges, and users can be classified into four kinds according to their personalized rating criterion, including normal, strict, lenient, and middle. We analyzed ratings’ distributions and found that the proportion of user ratings’ local standard deviation to the system’s global standard deviation is equal to that of the user’s actual rating range to the system’s rating range. We propose an improved and unified baseline estimation model based on the standard deviation’s proportion to alleviate the influence of classical baseline estimation’s limitation. We also apply the proposed baseline estimation model in existing latent factor-based CF recommendations and propose two instances. We performed experiments on full ratings of datasets by cross evaluations, including Flixster, Movielens (10 M), Movielens (latest small), FilmTrust, and MiniFilm. The results prove that the proposed baseline estimation model has better predictive accuracy than the classical model and is efficient in improving prediction performance for existing latent factor-based CF recommendations. Full article

(This article belongs to the Special Issue Recommender Systems and Collaborative Filtering)

► Show Figures

Figure 1

16 pages, 326 KiB

Open AccessArticle

Examining the Usefulness of Quality Scores for Generating Learning Object Recommendations in Repositories of Open Educational Resources

by Aldo Gordillo, Daniel López-Fernández and Katrien Verbert

Appl. Sci. 2020, 10(13), 4638; https://doi.org/10.3390/app10134638 - 4 Jul 2020

Cited by 10 | Viewed by 2919

Abstract

Open educational resources (OER) can contribute to democratize education by providing effective learning experiences with lower costs. Nevertheless, the massive amount of resources currently available in OER repositories makes it difficult for teachers and learners to find relevant and high-quality content, which is [...] Read more.

Open educational resources (OER) can contribute to democratize education by providing effective learning experiences with lower costs. Nevertheless, the massive amount of resources currently available in OER repositories makes it difficult for teachers and learners to find relevant and high-quality content, which is hindering OER use and adoption. Recommender systems that use data related to the pedagogical quality of the OER can help to overcome this problem. However, studies analyzing the usefulness of these data for generating OER recommendations are very limited and inconclusive. This article examines the usefulness of using pedagogical quality scores for generating OER recommendations in OER repositories by means of a user study that compares the following four different recommendation approaches: a traditional content-based recommendation technique, a quality-based non-personalized recommendation technique, a hybrid approach that combines the two previous techniques, and random recommendations. This user study involved 53 participants and 400 OER whose quality was evaluated by reviewers using the Learning Object Review Instrument (LORI). The main finding of this study is that pedagogical quality scores can enhance traditional content-based OER recommender systems by allowing them to recommend OER with more quality without detriment to relevance. Full article

(This article belongs to the Special Issue Recommender Systems and Collaborative Filtering)

20 pages, 924 KiB

Open AccessArticle

SoftRec: Multi-Relationship Fused Software Developer Recommendation

by Xinqiang Xie, Bin Wang and Xiaochun Yang

Appl. Sci. 2020, 10(12), 4333; https://doi.org/10.3390/app10124333 - 24 Jun 2020

Cited by 7 | Viewed by 2295

Abstract

Collaboration efficiency is of primary importance in software development. It is widely recognized that choosing suitable developers is an efficient and effective practice for improving the efficiency of software development and collaboration. Recommending suitable developers is complex and time-consuming due to the difficulty [...] Read more.

Collaboration efficiency is of primary importance in software development. It is widely recognized that choosing suitable developers is an efficient and effective practice for improving the efficiency of software development and collaboration. Recommending suitable developers is complex and time-consuming due to the difficulty of learning developers’ expertise and willingness. Existing works focus on learning developers’ expertise and interactions from their explicit historical information and matching them to specific task. However, such procedures may suffer low accuracy because they ignore implicit information, such as (1) developer–developer collaboration relationships, (2) developer–task implicit interaction relationships, and (3) task–task association relationships, etc. To that end, this paper proposes a multi-relationship fused approach for software developer recommendation (termed SoftRec). First, in addition to explicit developer–task interactions, it considers multivariate implicit relationships, including the three types mentioned above. Second, it integrates these relationships based on joint matrix factorization and generates forecast results upon the architecture of deep neural network. Furthermore, we propose a fast update method to address the cold start issue by making online recommendations for new developers and new tasks. Extensive experiments are conducted on two real-world datasets, and a user study is conducted in a well-known software company. The results demonstrate that SoftRec outperforms four state-of-the-art works. Full article

(This article belongs to the Special Issue Recommender Systems and Collaborative Filtering)

► Show Figures

Figure 1

14 pages, 1311 KiB

Open AccessArticle

Cognitive Similarity-Based Collaborative Filtering Recommendation System

by Luong Vuong Nguyen, Min-Sung Hong, Jason J. Jung and Bong-Soo Sohn

Appl. Sci. 2020, 10(12), 4183; https://doi.org/10.3390/app10124183 - 18 Jun 2020

Cited by 41 | Viewed by 4744

Abstract

This paper provides a new approach that improves collaborative filtering results in recommendation systems. In particular, we aim to ensure the reliability of the data set collected which is to collect the cognition about the item similarity from the users. Hence, in this [...] Read more.

This paper provides a new approach that improves collaborative filtering results in recommendation systems. In particular, we aim to ensure the reliability of the data set collected which is to collect the cognition about the item similarity from the users. Hence, in this work, we collect the cognitive similarity of the user about similar movies. Besides, we introduce a three-layered architecture that consists of the network between the items (item layer), the network between the cognitive similarity of users (cognition layer) and the network between users occurring in their cognitive similarity (user layer). For instance, the similarity in the cognitive network can be extracted from a similarity measure on the item network. In order to evaluate our method, we conducted experiments in the movie domain. In addition, for better performance evaluation, we use the F-measure that is a combination of two criteria

P r e c i s i o n

and

R e c a l l

. Compared with the Pearson Correlation, our method more accurate and achieves improvement over the baseline 11.1% in the best case. The result shows that our method achieved consistent improvement of 1.8% to 3.2% for various neighborhood sizes in MAE calculation, and from 2.0% to 4.1% in RMSE calculation. This indicates that our method improves recommendation performance. Full article

(This article belongs to the Special Issue Recommender Systems and Collaborative Filtering)

► Show Figures

Figure 1

15 pages, 984 KiB

Open AccessArticle

Neighborhood Aggregation Collaborative Filtering Based on Knowledge Graph

by Dehai Zhang, Linan Liu, Qi Wei, Yun Yang, Po Yang and Qing Liu

Appl. Sci. 2020, 10(11), 3818; https://doi.org/10.3390/app10113818 - 30 May 2020

Cited by 21 | Viewed by 4011

Abstract

In recent years, the research of combining a knowledge graph with recommendation systems has caused widespread concern. By studying the interconnections in knowledge graphs, potential connections between users and items can be discovered, which provides abundant and complementary information for recommendation of items. [...] Read more.

In recent years, the research of combining a knowledge graph with recommendation systems has caused widespread concern. By studying the interconnections in knowledge graphs, potential connections between users and items can be discovered, which provides abundant and complementary information for recommendation of items. However, most existing studies have not effectively established the relation between entities and users. Therefore, the recommendation results may be affected by some unrelated entities. In this paper, we propose a neighborhood aggregation collaborative filtering (NACF) based on knowledge graph. It uses the knowledge graph to spread and extract the user’s potential interest, and iteratively injects them into the user features with attentional deviation. We conducted a large number of experiments on three public datasets; we verifyied that NACF is ahead of the most advanced models in top-k recommendation and click-through rate (CTR) prediction. Full article

(This article belongs to the Special Issue Recommender Systems and Collaborative Filtering)

► Show Figures

Figure 1

19 pages, 2942 KiB

Open AccessArticle

Improving Matrix Factorization Based Expert Recommendation for Manuscript Editing Services by Refining User Opinions with Binary Ratings

by Yeonbin Son and Yerim Choi

Appl. Sci. 2020, 10(10), 3395; https://doi.org/10.3390/app10103395 - 14 May 2020

Cited by 4 | Viewed by 2041

Abstract

As language editing became an essential process for enhancing the quality of a research manuscript, there are several companies providing manuscript editing services. In such companies, a manuscript submitted for proofreading is matched with an editing expert through a manual process, which is [...] Read more.

As language editing became an essential process for enhancing the quality of a research manuscript, there are several companies providing manuscript editing services. In such companies, a manuscript submitted for proofreading is matched with an editing expert through a manual process, which is costly and often subjective. The major drawback of the manual process is that it is almost impossible to consider the inherent characteristics of a manuscript such as writing style and paragraph composition. To this end, we propose an expert recommendation method for manuscript editing services based on matrix factorization, a well-known collaborative filtering approach for learning latent information in ordinal ratings given by users. Specifically, binary ratings are utilized to substitute ordinal ratings when negative opinions are expressed by users since negative opinions are more accurately expressed by binary ratings than ordinal ratings. From the experiments using a real-world dataset, the proposed method outperformed the rest of the compared methods with an RMSE (root mean squared error) of 0.1. Moreover, the effectiveness of substituting ordinal ratings with binary ratings was validated by conducting sentiment analysis on text reviews. Full article

(This article belongs to the Special Issue Recommender Systems and Collaborative Filtering)

► Show Figures

Figure 1

14 pages, 2009 KiB

Open AccessArticle

Deep Learning Architecture for Collaborative Filtering Recommender Systems

by Jesus Bobadilla, Santiago Alonso and Antonio Hernando

Appl. Sci. 2020, 10(7), 2441; https://doi.org/10.3390/app10072441 - 3 Apr 2020

Cited by 68 | Viewed by 8048

Abstract

This paper provides an innovative deep learning architecture to improve collaborative filtering results in recommender systems. It exploits the potential of the reliability concept to raise predictions and recommendations quality by incorporating prediction errors (reliabilities) in the deep learning layers. The underlying idea [...] Read more.

This paper provides an innovative deep learning architecture to improve collaborative filtering results in recommender systems. It exploits the potential of the reliability concept to raise predictions and recommendations quality by incorporating prediction errors (reliabilities) in the deep learning layers. The underlying idea is to recommend highly predicted items that also have been found as reliable ones. We use the deep learning architecture to extract the existing non-linear relations between predictions, reliabilities, and accurate recommendations. The proposed architecture consists of three related stages, providing three stacked abstraction levels: (a) real prediction errors, (b) predicted errors (reliabilities), and (c) predicted ratings (predictions). In turn, each abstraction level requires a learning process: (a) Matrix Factorization from ratings, (b) Multilayer Neural Network fed with real prediction errors and hidden factors, and (c) Multilayer Neural Network fed with reliabilities and hidden factors. A complete set of experiments has been run involving three representative and open datasets and a state-of-the-art baseline. The results show strong prediction improvements and also important recommendation improvements, particularly for the recall quality measure. Full article

(This article belongs to the Special Issue Recommender Systems and Collaborative Filtering)

► Show Figures

Graphical abstract

Journal Menu

Journal Browser

Recommender Systems and Collaborative Filtering

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Published Papers (13 papers)

Editorial

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI