Review
Computer Science, Artificial Intelligence
Jon Nicolas Bondevik, Kwabena Ebo Bennin, Onder Babur, Carsten Ersch
Summary: This paper presents a systematic literature review of Food Recommender Systems (FRS), summarizing the current state-of-the-art in the field. The review reveals that FRS methods and algorithms, data processing, and evaluation methods vary greatly. Most FRS employ content-based filtering and machine learning approaches to provide non-personalized recommendations. This review provides valuable information to researchers in the field for selecting a strategy to develop FRS.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Review
Health Care Sciences & Services
Robin De Croon, Leen Van Houdt, Nyi Nyi Htun, Gregor Stiglic, Vero Vanden Abeele, Katrien Verbert
Summary: Health recommender systems (HRSs) have the potential to motivate and engage users to change their behavior by sharing better choices and actionable knowledge based on observed user behavior. A systematic review identified that the majority of HRSs use hybrid recommendation algorithms and evaluations vary greatly, with some studies only evaluating the algorithms while others conducting full-scale trials or in-the-wild studies. Five reporting guidelines were derived to serve as a reference frame for future HRS studies, indicating significant opportunities for HRS to inform and guide health actions.
JOURNAL OF MEDICAL INTERNET RESEARCH
(2021)
Review
Computer Science, Information Systems
Imran Uddin, Ali Shariq Imran, Khan Muhammad, Nosheen Fayyaz, Muhammad Sajjad
Summary: Online learning environments such as LMS and MOOC are becoming increasingly popular in the education sector, offering flexibility and convenience to learners worldwide. Recommender systems play a crucial role in assisting learners to navigate through the vast amount of available content and make appropriate choices to fulfill their academic requirements.
Review
Computer Science, Artificial Intelligence
Diego Monti, Giuseppe Rizzo, Maurizio Morisio
Summary: This work presents a systematic literature review in the field of multicriteria recommender systems, analyzing the research status quo in terms of research problems, recommendation approaches, data mining and machine learning algorithms. It delves into the domains of application, evaluation protocols, metrics, datasets, and offers promising suggestions for future works.
ARTIFICIAL INTELLIGENCE REVIEW
(2021)
Review
Computer Science, Information Systems
Mirko Farina, Anna Gorb, Artem Kruglov, Giancarlo Succi
Summary: This study aims to discover technologies for building Goal-Question-Metrics (GQM) based metrics recommender system for software developers. Through a systematic literature review, the study analyzed the components of recommender systems, including data sets, algorithms, and recommendations. The study found that there are currently no recommendation systems developed for processing metrics.
Review
Chemistry, Analytical
Aleksandra Pawlicka, Marek Pawlicki, Rafal Kozik, Ryszard S. Choras
Summary: This paper discusses the valuable role recommender systems may play in cybersecurity by presenting the types, advantages, disadvantages, applications, and security concerns of recommender systems. It also collects and presents the current state and future ideas of using recommender systems in cybersecurity, providing a comprehensive survey of recommender types that adds to the existing knowledge in the field.
Review
Computer Science, Artificial Intelligence
Maryam Etemadi, Sepideh Bazzaz Abkenar, Ahmad Ahmadzadeh, Mostafa Haghi Kashani, Parvaneh Asghari, Mohammad Akbari, Ebrahim Mahdipour
Summary: This paper systematically examines and compares current research on healthcare recommender systems (HRS) through a systematic literature review. The study reveals that HRSs are still in their early stages of development and face challenges such as lack of standardization in medical codes and the cold start problem. To improve trust from both patients and healthcare professionals, it is necessary to establish a reliable and scalable framework.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Review
Health Care Sciences & Services
Yue Sun, Jia Zhou, Mengmeng Ji, Lusi Pei, Zhiwen Wang
Summary: This study aimed to identify and evaluate the development of Health Recommender Systems (HRSs) and create an evidence map. A total of 51 studies were included for data extraction. The findings showed that only 19.6% of the systems considered the personal preferences of end users in the design stage. The evaluation methods varied, with 62.7% of the studies using offline evaluations and 33.3% including end users in the evaluation process. More user-centered evaluation studies are needed in the future.
JOURNAL OF MEDICAL INTERNET RESEARCH
(2023)
Review
Computer Science, Theory & Methods
Deepjyoti Roy, Mala Dutta
Summary: This paper provides a systematic review of recent contributions in the field of recommender systems, focusing on diverse applications and analyzing algorithmic and component aspects. The evaluation of datasets, simulation platforms, and performance metrics adds further value to the review. It offers an overview of the current research state and identifies existing gaps and challenges for the development of efficient recommender systems.
JOURNAL OF BIG DATA
(2022)
Review
Green & Sustainable Science & Technology
Silja Zimmermann, Brian J. Dermody, Bert Theunissen, Martin J. Wassen, Lauren M. Divine, Veronica M. Padula, Henrik von Wehrden, Ine Dorresteijn
Summary: Arctic food systems are facing challenges like climate change, food security loss, and destabilization of Indigenous practices. Despite growing scientific knowledge, Indigenous communities still struggle with sustainability challenges. A systematic review of 526 articles was conducted to understand the existing knowledge on Arctic Indigenous food systems. The study identified gaps and proposed directions for future research to enable sustainability transformations.
SUSTAINABILITY SCIENCE
(2023)
Review
Education & Educational Research
Nur W. Rahayu, Ridi Ferdiana, Sri S. Kusumawardani
Summary: This study reviews learning paths in ontology-based recommender systems, covering recommendation trends, ontology use, recommendation process, recommendation technique, contributing factors, and recommender evaluations. The findings show that student models, learning objects, learning activities, and external environment are important factors for recommending learning object sequences. The recommendation process consists of four phases: predelivery of the first learning object, current learning object delivery, learning object postdelivery, and predelivery of the next learning object. Performance is evaluated using real students, control groups, and student satisfaction surveys.
EDUCATION AND INFORMATION TECHNOLOGIES
(2023)
Article
Computer Science, Artificial Intelligence
Mauricio Noris Freire, Leandro Nunes de Castro
Summary: This study systematically reviewed recommender systems applied to e-Recruitment from 2012 to 2020, collecting 63 research works out of 896 papers. The study categorized recommender types, information types, and assessment types, finding a clear trend for hybrid and non-traditional techniques to overcome challenges in the e-Recruitment domain.
KNOWLEDGE AND INFORMATION SYSTEMS
(2021)
Review
Computer Science, Artificial Intelligence
Qazi Mohammad Areeb, Mohammad Nadeem, Shahab Saquib Sohail, Raza Imam, Faiyaz Doctor, Yassine Himeur, Amir Hussain, Abbes Amira
Summary: A filter bubble refers to the isolation of individuals on the internet due to customization, resulting in exposure to a limited set of content. This research study investigates the impact of filter bubbles in recommender systems, proposes solutions, and develops a tool to help users avoid them. A systematic literature review reveals evidence of filter bubbles in recommender systems, identifies biases contributing to their existence, and suggests mechanisms to mitigate their impact and promote diversity in recommendations.
WILEY INTERDISCIPLINARY REVIEWS-DATA MINING AND KNOWLEDGE DISCOVERY
(2023)
Review
Education & Educational Research
Felipe Leite da Silva, Bruna Kin Slodkowski, Ketia Kellen Araujo da Silva, Silvio Cesar Cazella
Summary: Recommender systems play a vital role in personalized content filtering in education. However, there is a lack of literature on the current trends in recommendation production and evaluation, as well as the research limitations and opportunities in this field.
EDUCATION AND INFORMATION TECHNOLOGIES
(2023)
Review
Computer Science, Artificial Intelligence
Atena Torkashvand, Seyed Mahdi Jameii, Akram Reza
Summary: This systematic review provides a comprehensive analysis of recent research on deep learning-based collaborative filtering recommender systems. It covers research methodology, paper selection process, method classification, and key information for each selected paper. The study finds that CNN, AE, DNN, and hybrid networks are commonly used neural networks in recommender systems, while Python, MATLAB, and Java are frequently used tools. Movies, products, and music recommendation are the most common applications. The study also highlights key challenges and future research directions.
NEURAL COMPUTING & APPLICATIONS
(2023)