Deep learning based semantic personalized recommendation system

Sharma, Sunny; Vijay, Ritu; Kumar, Vivek

doi:10.1016/j.jjimei.2021.100028

Cited by 42 publications

(10 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A Deep Neural Network (DNN) [65] is an Artificial Neural Network with several layers between the input and output layers. These neural networks come in various shapes and sizes, but they all have the same fundamental components: neurons, weights, biases, and functions.…”

Section: Constructing Deep Neural Networkmentioning

confidence: 99%

TD-DNN: A Time Decay-Based Deep Neural Network for Recommendation System

et al. 2022

View full text Add to dashboard Cite

In recent years, commercial platforms have embraced recommendation algorithms to provide customers with personalized recommendations. Collaborative Filtering is the most widely used technique of recommendation systems, whose accuracy is primarily reliant on the computed similarity by a similarity measure. Data sparsity is one problem that affects the performance of the similarity measures. In addition, most recommendation algorithms do not remove noisy data from datasets while recommending the items, reducing the accuracy of the recommendation. Furthermore, existing recommendation algorithms only consider historical ratings when recommending the items to users, but users’ tastes may change over time. To address these issues, this research presents a Deep Neural Network based on Time Decay (TD-DNN). In the data preprocessing phase of the model, noisy ratings are detected from the dataset and corrected using the Matrix Factorization approach. A power decay function is applied to the preprocessed input to provide more weightage to the recent ratings. This non-noisy weighted matrix is fed into the Deep Learning model, consisting of an input layer, a Multi-Layer Perceptron, and an output layer to generate predicted ratings. The model’s performance is tested on three benchmark datasets, and experimental results confirm that TD-DNN outperforms other existing approaches.

show abstract

Section: Constructing Deep Neural Networkmentioning

confidence: 99%

TD-DNN: A Time Decay-Based Deep Neural Network for Recommendation System

et al. 2022

View full text Add to dashboard Cite

show abstract

“…A recommendation system is software that helps users identify interesting and relevant learning information from a variety of educational information. Referral systems aim to provide learners with relevant research results tailored to their needs by making predictions about their preferences and by providing educational content that may be closer than expected (Sharma, 2021). In addition, referral systems must use different sources of information such as pedagogical databases, learning object repositories (LORs), LOR federations, and so on (Danaf et al, 2020).…”

Section: The Use Of Educational Recommendation Systemsmentioning

confidence: 99%

Design and implementation of the multi-agent system in education

Hamal

Faddouli

Harouni

2021

WJET

View full text Add to dashboard Cite

Nowadays, AI is a real springboard for finding solutions to optimize and improve learning and teaching processes. This issue has been a focus of humanity for millennia, and very significant advances have been made in this quest. This article aims to address the issue of optimizing and improving learning and teaching processes through AI (Artificial Intelligence), considering crossroads of research fields AIED (Artificial Intelligence in Education), EDM (Educational Data Mining) and LA (Learning Analytic). The research made use of secondary data collected from previous research on the topic and primary data was collected using a case study. A comparative analysis was conducted and based on this opportunity, we propose a multi-agent system based on AI techniques, which is capable of performing broader analyses of learning and teaching processes. The research also implemented a prototype of EMAS. Through this system, teachers and learners will be able to access a wide range of relevant and reliable information about learning and teaching processes. Key words: AIED, EDM, EMAS, LA, recommendation system, education dropping out, emotion detection

show abstract

“…The application of ML on the large clinical data [ 24 ] can ensure trustworthy and efficient healthcare decisions benefiting both patients [ 25 , 26 ] and providers [ 27 ]. Personalization facilitated by ML has become engrained in our daily interactions with a variety of digital systems [ 28 ], including e-commerce [ 29 ], movie recommendations, exercise advice [ 30 ], and therapy recommendations [ 31 ]. Thus, personalized RS in ASD management can utilize patients’ medical meta-data and assessment records to recommend personalized treatment prescriptions to improve their well-being that would not be achievable through conventional procedures [ 32 ].…”

Section: Introductionmentioning

confidence: 99%

Machine learning-based ABA treatment recommendation and personalization for autism spectrum disorder: an exploratory study

et al. 2022

View full text Add to dashboard Cite

Autism spectrum is a brain development condition that impairs an individual’s capacity to communicate socially and manifests through strict routines and obsessive–compulsive behavior. Applied behavior analysis (ABA) is the gold-standard treatment for autism spectrum disorder (ASD). However, as the number of ASD cases increases, there is a substantial shortage of licensed ABA practitioners, limiting the timely formulation, revision, and implementation of treatment plans and goals. Additionally, the subjectivity of the clinician and a lack of data-driven decision-making affect treatment quality. We address these obstacles by applying two machine learning algorithms to recommend and personalize ABA treatment goals for 29 study participants with ASD. The patient similarity and collaborative filtering methods predicted ABA treatment with an average accuracy of 81–84%, with a normalized discounted cumulative gain of 79–81% (NDCG) compared to clinician-prepared ABA treatment recommendations. Additionally, we assess the two models’ treatment efficacy (TE) by measuring the percentage of recommended treatment goals mastered by the study participants. The proposed treatment recommendation and personalization strategy are generalizable to other intervention methods in addition to ABA and for other brain disorders. This study was registered as a clinical trial on November 5, 2020 with trial registration number CTRI/2020/11/028933.

show abstract

Deep learning based semantic personalized recommendation system

Cited by 42 publications

References 28 publications

TD-DNN: A Time Decay-Based Deep Neural Network for Recommendation System

TD-DNN: A Time Decay-Based Deep Neural Network for Recommendation System

Design and implementation of the multi-agent system in education

Machine learning-based ABA treatment recommendation and personalization for autism spectrum disorder: an exploratory study

Contact Info

Product

Resources

About