Sequence-Based Explainable Hybrid Song Recommendation

Damak, Khalil; Nasraoui, Olfa; Sanders, W. Scott

doi:10.3389/fdata.2021.693494

Cited by 5 publications

(5 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our model noticeably outperforms the baseline models. We also compare our model with Reference 12, where the author uses audio as content information, but instead of using audio, we use MIDI information with various deep neural networks (RNN, LSTM, GRU, CNN), 37 and results are shown in the Table 9 and it clearly shows that our model MSA‐SRec performs better compared to the baseline state‐of‐the‐art models. We also compare our model with some well known recommendation algorithm and all the comparative results are shown in Table 10 which clearly shows that MSA‐SRec is performing better. RQ3 ‐ Why we choose MIDI data as a content information?…”

Section: Analysis and Resultsmentioning

confidence: 99%

“…In a previous study, Van den Oord et al 12,37 and other researchers introduced many algorithms for music recommendation results with various content descriptions of music. These algorithms give a new direction in music recommendation systems, mainly to deal with the cold‐start problem.…”

Section: Proposed Problem Formulation and Algorithmmentioning

confidence: 99%

“…This dataset is very sparse, so we need to preprocess the dataset, where we delete users who have listened to less than 20 songs from the train_triplets dataset. We follow the preprocessing of these listen count of mapping to rating using methodology used in Reference 37. The Table 1 shows the play count conversion to the rating of the dataset.…”

Section: Proposed Problem Formulation and Algorithmmentioning

confidence: 99%

See 2 more Smart Citations

Improved self‐attentive Musical Instrument Digital Interface content‐based music recommendation system

Yadav

Singh

Pal

2022

Computational Intelligence

View full text Add to dashboard Cite

Automatic music recommendation is an open research problem that has seen much work in recent years.A common and successful music recommendation approach is collaborative filtering, which has worked well in this domain. One major drawback of this method is that it suffers from a cold-start problem, and it requires a lot of user-personalized information. It is an ineffective mechanism for recommending new and unpopular songs as well as for new users. In this article, we report a hybrid methodology that uses the song's content information. We use MIDI (Musical Instrument Digital Interface) content data, a compressed version of an audio song that contains digital information about a song and is machine-readable. We describe a model called MSA-SRec (MIDI Based Self Attentive Sequential Music Recommendation), a latent factor-based self-attentive deep learning model that uses a substantial amount of sequential information as content information of the song for recommendation generation. We use MIDI data of a song that is under-explored content information for music recommendation. We show that using MIDI as content data with user and item latent vector produces reasonable recommendations. We also demonstrate that using MIDI over other music metadata performs better

show abstract

Section: Analysis and Resultsmentioning

confidence: 99%

Section: Proposed Problem Formulation and Algorithmmentioning

confidence: 99%

Section: Proposed Problem Formulation and Algorithmmentioning

confidence: 99%

See 1 more Smart Citation

Improved self‐attentive Musical Instrument Digital Interface content‐based music recommendation system

Yadav

Singh

Pal

2022

Computational Intelligence

View full text Add to dashboard Cite

show abstract

“…Other methods relied on post-hoc approaches that try to extract explanations for the recommendations after they occur. For instance, [35] and [11] use influence functions to determine the effect of each input interaction on the recommendation; while [13] proposed an approach that forward-propagates song segments through the trained recurrent neural network model to determine the most explanatory segment in a song recommendation. In contrast to the above methods, some explainable recommender systems rely solely on feedback data such as ratings or interactions.…”

Section: Explainability In Recommendationmentioning

confidence: 99%

Debiased Explainable Pairwise Ranking from Implicit Feedback

Damak

Khenissi

Nasraoui

2021

Fifteenth ACM Conference on Recommender Systems

Self Cite

View full text Add to dashboard Cite

Recent work in recommender systems has emphasized the importance of fairness, with a particular interest in bias and transparency, in addition to predictive accuracy. In this paper, we focus on the state of the art pairwise ranking model, Bayesian Personalized Ranking (BPR), which has previously been found to outperform pointwise models in predictive accuracy, while also being able to handle implicit feedback. Specifically, we address two limitations of BPR: (1) BPR is a black box model that does not explain its outputs, thus limiting the user's trust in the recommendations, and the analyst's ability to scrutinize a model's outputs; and (2) BPR is vulnerable to exposure bias due to the data being Missing Not At Random (MNAR). This exposure bias usually translates into an unfairness against the least popular items because they risk being under-exposed by the recommender system. In this work, we first propose a novel explainable loss function and a corresponding Matrix Factorization-based model called Explainable Bayesian Personalized Ranking (EBPR) that generates recommendations along with item-based explanations. Then, we theoretically quantify additional exposure bias resulting from the explainability, and use it as a basis to propose an unbiased estimator for the ideal EBPR loss. The result is a ranking model that aptly captures both debiased and explainable user preferences. Finally, we perform an empirical study on three real-world datasets that demonstrate the advantages of our proposed models.

show abstract

“…Traditional recommendation algorithms are mainly represented by collaborative ltering model. e most common collaborative ltering algorithms mainly include neighborhood method and matrix decomposition model, which can achieve good recommendation e ect when there are few data samples [8]. However, the current network data has the characteristics of complex and high-dimensional.…”

Section: Introductionmentioning

confidence: 99%

User Personalized Recommendation Algorithm Based on GRU Network Model in Social Networks

Zeng

Tang

Wang

2022

Mobile Information Systems

View full text Add to dashboard Cite

Efficient and accurate personalized recommendation algorithms can effectively improve user experience satisfaction, in order to improve the performance of user personalized recommendation algorithm, this study proposes a user personalized recommendation algorithm based on deep learning network. The algorithm uses Gate Recurrent Unit (GRU) network to build the main model of personalized recommendation algorithm to reduce the influence of over fitting of multi-layer network; The attention mechanism is introduced into GRU network, so that the recommendation model can obtain the feature information of user data more accurately and reduce the influence of irrelevant data on the model; At the same time, due to the introduction of variable length mini-batch allocation method, the model training data is more complete and reliable, which can effectively improve the accuracy of user personalized recommendation. The simulation experiment is based on Amazon dataset and MovieLens dataset. The experimental results show that the proposed method has good personalized recommendation ability.

show abstract

Sequence-Based Explainable Hybrid Song Recommendation

Cited by 5 publications

References 58 publications

Improved self‐attentive Musical Instrument Digital Interface content‐based music recommendation system

Improved self‐attentive Musical Instrument Digital Interface content‐based music recommendation system

Debiased Explainable Pairwise Ranking from Implicit Feedback

User Personalized Recommendation Algorithm Based on GRU Network Model in Social Networks

Contact Info

Product

Resources

About