DST-HRS: A topic driven hybrid recommender system based on deep semantics

Khan, Zafran; Iltaf, Naima; Afzal, Hammad; Abbas, Haider

doi:10.1016/j.comcom.2020.02.068

Cited by 21 publications

(9 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the other hand, it is great to devote future research to developing and extracting more other features from the similarity graph, which we did not mention in the current study. Besides, the structure of the Autoencoder might be an impor- (Bag et al, 2019) -1.7 DST-HRS (Khan et al, 2020) -0.846 Autoencoder COFILS (Barbieri et al, 2017) 0.885 0.838 Baseline COFILS (Barbieri et al, 2017) 0.892 0.848 Kernel PCA COFILS (Barbieri et al, 2017) 0.898 -Slope One (Lemire and Maclachlan, 2005) 0.937 0.9 Regularized SVD (Paterek, 2007) 0.989 0.96 Improved Regularized SVD (Paterek, 2007) 0.954 0.907 SVD++ (Koren, 2008) 0.903 0.856 Non-Negative Matrix Factorization (Lee and Seung, 2001) 0.944 0.912 Bayesian Probabilistic Matrix Factorization (Salakhutdinov and Mnih, 2008) 0.901 0.84 RBM-CF (Salakhutdinov et al, 2007) 0.936 0.872 AutoRec (Sedhain et al, 2015) 0.887 0.844 Mean Field (Langseth and Nielsen, 2015) 0.903 0.856 GHRS (Proposed Method) 0.887 0.833 tant area for future research. The different structures should be examined regarding the Autoencoder structure affecting feature extraction, training duration, and the model's final performance.…”

Section: Discussionmentioning

confidence: 99%

GHRS: Graph-based Hybrid Recommendation System with Application to Movie Recommendation

Darban,

Valipour

2021

Preprint

View full text Add to dashboard Cite

Research about recommender systems emerges over the last decade and comprises valuable services to increase different companies' revenue. Several approaches exist in handling paper recommender systems. While most existing recommender systems rely either on a content-based approach or a collaborative approach, there are hybrid approaches that can improve recommendation accuracy using a combination of both approaches. Even though many algorithms are proposed using such methods, it is still necessary for further improvement. In this paper, we propose a recommender system method using a graph-based model associated with the similarity of users' ratings, in combination with users' demographic and location information. By utilizing the advantages of Autoencoder feature extraction, we extract new features based on all combined attributes. Using the new set of features for clustering users, our proposed approach (GHRS) has gained a significant improvement, which dominates other methods' performance in the cold-start problem. The experimental results on the MovieLens dataset show that the proposed algorithm outperforms many existing recommendation algorithms on recommendation accuracy.

show abstract

Section: Discussionmentioning

confidence: 99%

GHRS: Graph-based Hybrid Recommendation System with Application to Movie Recommendation

Darban,

Valipour

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Deep graph neural network (Yin et al , 2019), deep learning-based recommender system (Aujla et al , 2019), social attentive deep learning (Lei et al , 2020) and patient diet recommender system (Iwendi et al , 2020) were the key contributions in the field of RS. LSTM-based approaches (Zarzour et al , 2020), music recommender using deep learning (Fessahaye et al , 2019), autoencoder for top-N recommendations (Pan et al , 2019; Jiang et al , 2020; https://nijianmo.github.i; Zhu et al , 2017), reinforcement learning (Yuan et al , 2020), medical image segmentation using deep learning (Wang et al , 2020), topic-driven hybrid approach (Khan et al , 2020) and a deep learning approach with K pickup points (Berdeddouch et al , 2020) are important approaches found. Collaborative deep learning (Yang et al , 2020) and joint representation learning (Wu et al , 2017) are other approaches studied.…”

Section: Related Workmentioning

confidence: 99%

A multi-preference integrated algorithm (MPIA) for the deep learning-based recommender framework (DLRF)

Vikram

Reddy

Madhavi

2022

IJICC

View full text Add to dashboard Cite

PurposeThe deep learning-based recommender framework (DLRF) is based on an improved long short-term memory (LSTM) structure with additional controllers; thus, it considers contextual information for state transition. It also handles irregularities in the data to enhance performance in generating recommendations while modelling short-term preferences. An algorithm named a multi-preference integrated algorithm (MPIA) is proposed to have dynamic integration of both kinds of user preferences aforementioned. Extensive experiments are made using Amazon benchmark datasets, and the results are compared with many existing recommender systems (RSs).Design/methodology/approachRSs produce quality information filtering to the users based on their preferences. In the contemporary era, online RSs-based collaborative filtering (CF) techniques are widely used to model long-term preferences of users. With deep learning models, such as recurrent neural networks (RNNs), it became viable to model short-term preferences of users. In the existing RSs, there is a lack of dynamic integration of both long- and short-term preferences. In this paper, the authors proposed a DLRF for improving the state of the art in modelling short-term preferences and generating recommendations as well.FindingsThe results of the empirical study revealed that the MPIA outperforms existing algorithms in terms of performance measured using metrics such as area under the curve (AUC) and F1-score. The percentage of improvement in terms AUC is observed as 1.3, 2.8, 3 and 1.9% and in terms of F-1 score 0.98, 2.91, 2 and 2.01% on the datasets.Originality/valueThe algorithm uses attention-based approaches to integrate the preferences by incorporating contextual information.

show abstract

“…Notably, sentiment analysis has been proposed to predict song contest results [ 16 ]. For recommender systems, LDA-based topic hybrid recommender system has been proposed [ 33 ], and semantic analysis for recommendations has been also used in learning environments [ 32 ]. Moreover, semantic modeling of the user interactions with a chatbot allows for personalized interactions [ 43 ].…”

Section: Related Workmentioning

confidence: 99%

Neuro-semantic prediction of user decisions to contribute content to online social networks

Cleveland

Ríos

Aguilera

et al. 2022

Neural Comput & Applic

View full text Add to dashboard Cite

Understanding at microscopic level the generation of contents in an online social network (OSN) is highly desirable for an improved management of the OSN and the prevention of undesirable phenomena, such as online harassment. Content generation, i.e., the decision to post a contributed content in the OSN, can be modeled by neurophysiological approaches on the basis of unbiased semantic analysis of the contents already published in the OSN. This paper proposes a neuro-semantic model composed of (1) an extended leaky competing accumulator (ELCA) as the neural architecture implementing the user concurrent decision process to generate content in a conversation thread of a virtual community of practice, and (2) a semantic modeling based on the topic analysis carried out by a latent Dirichlet allocation (LDA) of both users and conversation threads. We use the similarity between the user and thread semantic representations to built up the model of the interest of the user in the thread contents as the stimulus to contribute content in the thread. The semantic interest of users in discussion threads are the external inputs for the ELCA, i.e., the external value assigned to each choice.. We demonstrate the approach on a dataset extracted from a real life web forum devoted to fans of tinkering with musical instruments and related devices. The neuro-semantic model achieves high performance predicting the content posting decisions (average F score 0.61) improving greatly over well known machine learning approaches, namely random forest and support vector machines (average F scores 0.19 and 0.21).

show abstract

DST-HRS: A topic driven hybrid recommender system based on deep semantics

Cited by 21 publications

References 19 publications

GHRS: Graph-based Hybrid Recommendation System with Application to Movie Recommendation

GHRS: Graph-based Hybrid Recommendation System with Application to Movie Recommendation

A multi-preference integrated algorithm (MPIA) for the deep learning-based recommender framework (DLRF)

Neuro-semantic prediction of user decisions to contribute content to online social networks

Contact Info

Product

Resources

About