RETRACTED ARTICLE: Implementation and comparison of topic modeling techniques based on user reviews in e-commerce recommendations

Chehal, Dimple; Gupta, Phalguni; Gulati, Payal

doi:10.1007/s12652-020-01956-6

Cited by 37 publications

(14 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The recommendation criteria' central core is to make a regression style for predictive prophetic user evaluations based on nerve organ networks. Chehal, D. et al [2] The advice system's real success depends on generating suggestions swiftly and directed in regards to the right buyers. This system of activity should be because fundamental because it is striking a good interactive discussion between 2 different people.…”

Section: Background Of the Studymentioning

confidence: 99%

“…Ratings grow to be reflections linked with the users endorsement based on the latest scale (say, 0-5).Earlier studies are likely to be exact first hand information about the own personal user's sensible knowledge on product/service. Evaluations along with testimonials indicate a good buyer's achievement [2]. The sooner job in regards to investigation during the situation with wording typically points out the thought of what actually message exploration is actually happened.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

ERS: Latent Dirichlet Allocation Based E-Commerce Recommendation System Using Deep Neural Network

Sheeja¹

2021

pae

View full text Add to dashboard Cite

Online shopping is the best solution for busy life in today’s world. In the past decade, there had been a massive change in the way of customer’s shopping. In days individuals can help by keeping their time and effort by purchasing pieces online with various websites. Their particular working experience using a system is present in reviews/feedback given for these products. Recommender’s solutions offer heart-felt selections so that people can end-users just by recording their valuable pursuits together with preferences. Recommender devices provide fantastic opportunities to organizations; therefore, establishing new recommender system strategies and strategies has been increasing the focus. In this document, the ERS (Ecommerce recommendation system) using a serious neural community is recommended. We tend to produce some glossary about capabilities from each product or service kind and examine these to get rid of unimportant phrases by using Latent Dirichlet Allocation. Afterward, people being used any full nerve system network having the capacity to extract rich features inside reviews-characteristics matrix to deal with sparsity, ambiguity, apart from redundancy. Most people have applied factorization because of the collaborative, integrated choice supply regulations.

show abstract

Section: Background Of the Studymentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

ERS: Latent Dirichlet Allocation Based E-Commerce Recommendation System Using Deep Neural Network

Sheeja¹

2021

pae

View full text Add to dashboard Cite

show abstract

“…Foram gerados os tópicos de cada modelo, os mesmos foram avaliados visualmente e chegaram a conclusão que para esses modelos e para o tema escolhido, os modelos se complementam. A abordagem usada por [Chehal et al 2021] utiliza os modelos LSA, PLSA, LDA e CTM, e uma base de dados de avaliações de usuários de celulares Moto E5 do site Amazon.com. A ideia dos autoreś e de gerar um sistema de recomendação personalizadas em sites de e-commerce por meio de modelagem de tópicos.…”

Section: Trabalhos Relacionadosunclassified

Modelagem Probabilística de Tópicos: Uma Comparação Empírica

Rocha¹,

Welter²,

Duarte³

2021

Anais Da XVI Escola Regional De Banco De Dados (ERBD 2021)

View full text Add to dashboard Cite

Abordagens probabilísticas de tópicos são ferramentas para descobrir e explorar estruturas temáticas escondidas em coleções de textos. Dada uma coleção de documentos, a tarefa de extrair os tópicos consiste em criar um vocabulário a partir da coleção, verificar a probabilidade de cada palavra pertencer a um documento da coleção. Em seguida, baseado no número de tópicos desejado, a probabilidade de cada palavra estar associada a um determinado tópico é contabilizada. Assim, um tópico é um conjunto de palavras ordenadas pela probabilidade de estar associada ao tópico. Várias abordagens são encontradas na literatura para criação de modelos de tópicos, e.g., Hierarchical Dirichlet Process (HDP), Latent Dirichlet Allocation (LDA), Non-Negative Matrix Factorization (NMF) e Dirichlet-multinomial Regression (DMR). Este trabalho procura identificar a qualidade dos tópicos construídos pelas quatro abordagens citadas. A Qualidade será medida por métricas de coerência e todas as abordagens terão a mesma coleção de documentos como entrada: notícias de websites dos jornais Breibart, Business Insider, The Atlantic, CNN e New York Times contendo 50.000 artigos. Os resultados mostram que DMR e LDA são os melhores modelos para extrair tópicos da coleção utilizada.

show abstract

“…At the same time, researchers keep investigating better TM approaches using different datasets. Studies of Anantharaman, et al, Ray, et al, and Chehal, et al compared the existing methods explained above, and the conclusions of the studies show that the best methods are different depending on the datasets [16,17,18]. Furthermore, the researchers sometimes modified the exiting methods to adjust them according to the datasets or purposes.…”

Section: Recent Studies Of Topic Modellingmentioning

confidence: 99%

Investigation of Topic Modelling Methods for Understanding the Reports of the Mining Projects in Queensland

Okamoto¹,

Balasubramaniam²,

Nayak³

2021

Preprint

View full text Add to dashboard Cite

In the mining industry, many reports are generated in the project management process. These past documents are a great resource of knowledge for future success. However, it would be a tedious and challenging task to retrieve the necessary information if the documents are unorganized and unstructured. Document clustering is a powerful approach to cope with the problem, and many methods have been introduced in past studies. Nonetheless, there is no silver bullet that can perform the best for any types of documents. Thus, exploratory studies are required to apply the clustering methods for new datasets. In this study, we will investigate multiple topic modelling (TM) methods. The objectives are finding the appropriate approach for the mining project reports using the dataset of the Geological Survey of Queensland, Department of Resources, Queensland Government, and understanding the contents to get the idea of how to organise them. Three TM methods, Latent Dirichlet Allocation (LDA), Nonnegative Matrix Factorization (NMF), and Nonnegative Tensor Factorization (NTF) are compared statistically and qualitatively. After the evaluation, we conclude that the LDA performs the best for the dataset; however, the possibility remains that the other methods could be adopted with some improvements.

show abstract

RETRACTED ARTICLE: Implementation and comparison of topic modeling techniques based on user reviews in e-commerce recommendations

Cited by 37 publications

References 50 publications

ERS: Latent Dirichlet Allocation Based E-Commerce Recommendation System Using Deep Neural Network

ERS: Latent Dirichlet Allocation Based E-Commerce Recommendation System Using Deep Neural Network

Modelagem Probabilística de Tópicos: Uma Comparação Empírica

Investigation of Topic Modelling Methods for Understanding the Reports of the Mining Projects in Queensland

Contact Info

Product

Resources

About