OpinionLink: Leveraging user opinions for product catalog enrichment

Melo, Tiago de; Silva, Altigran Soares da; Moura, Edleno Silva de; Calado, Pável

doi:10.1016/j.ipm.2019.01.004

Cited by 11 publications

(10 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Para a primeira tarefa foram propostos dois métodos alternativos. O primeiro método, chamado Aspec-tLink [de Melo et al 2018], adota uma estratégia não-supervisionada, enquanto o segundo, chamado OpinionLink [de Melo et al 2019a], adota uma estratégia supervisionada. O AspectLink [de Melo et al 2018] usa uma abordagem linguística não supervisionada onde funções de similaridade comparam as características lexicais de atributos dos produto com o texto das expressões de aspecto.…”

Section: Trabalhos Relacionadosunclassified

“…O AspectLink [de Melo et al 2018] usa uma abordagem linguística não supervisionada onde funções de similaridade comparam as características lexicais de atributos dos produto com o texto das expressões de aspecto. No OpinionLink [de Melo et al 2019a], foi desenvolvido um método que usa classificadores binários e um conjunto de características estatísticos extraídas das opiniões de usuários. Além disso, uma estratégia de bootstrapping foi proposta para treinar os classificadores a fim de reduzir a dependência dos dados de treinamento.…”

Section: Trabalhos Relacionadosunclassified

See 1 more Smart Citation

Integração de Dados Factuais e Subjetivos: Um Estudo de Caso em Comércio Eletrônico

Silva

2021

Anais Do X Brazilian Workshop on Social Network Analysis and Mining (BraSNAM 2021)

View full text Add to dashboard Cite

Ao longo das últimas décadas os bancos de dados (BDs) têm sido o principal recurso computacional utilizado para armazenamento e gerenciar dados dos mais variados tipos de aplicações. Tipicamente, BDs armazenam informações factuais e objetivas sobre entidades do mundo real, que são representadas como um conjunto de atributos. No entanto, tem havido recentemente uma grande demanda para representar em BDs conhecimento subjetivo sobre estas entidades, com objetivo final de permitir que usuários e aplicações possam lidar com informações subjetivas de forma mais eficaz. Neste artigo, discutimos o problema de integração de dados factuais e subjetivos em bancos de dados, utilizando para isso um estudo de caso em comércio eletrônico. Neste domínio, a integração de informações subjetivas fornecidas por usuários nas mídias sociais com dados factuais fornecidos por vendedores e fabricantes de produtos tem o potencial de gerar conhecimento relevante para uma variedade de aplicações. Especificamente, exploramos neste artigo essa ideia em um estudo realizado para entender os interesses dos consumidores de produtos eletrônicos em sites de comércio eletrônico.

show abstract

Section: Trabalhos Relacionadosunclassified

Integração de Dados Factuais e Subjetivos: Um Estudo de Caso em Comércio Eletrônico

Silva

2021

Anais Do X Brazilian Workshop on Social Network Analysis and Mining (BraSNAM 2021)

View full text Add to dashboard Cite

show abstract

“…The latest works on catalog segmentation are using preference techniques as used in recommender systems to automate allocating users to the most related sub taxonomy (sub catalog), e.g. in [36,37,39,52,63]. However, the sub taxonomies are semantically reduced, which means that concepts not included in the sub catalog are not shown.…”

Section: Introductionmentioning

confidence: 99%

TaxoMulti: Rule-Based Expert System to Customize Product Taxonomies for Multi-Channel E-commerce

Angermann

2022

SN COMPUT. SCI.

View full text Add to dashboard Cite

Taxonomies are used as product categories to facilitate users navigating through an e-commerce portal with the help of hierarchically structured concepts. However, the identical taxonomy is shown to each customer regardless of the channel used. This is challenging for the customers in terms of user experience, as the screen size is rigid, and has not a flexible format like a printed catalog. Simply reducing the taxonomy as suggested in existing works is not sufficient, as it leads to semantic misrepresentation of the product domain. To overcome the inflexibility of product taxonomies, the rule-based expert system TaxoMulti is presented in this paper. The main objectives of our descriptive research are the formulation of the taxonomy over- and undersize problem in multi-channel context, before different types of flexible mediator concepts are discussed that allow overcoming these challenges. Using our novel method, marketing experts can now provide different taxonomies including the same semantics to be shown on different channels. The method is implemented using logic programming, allowing the integration of an inference engine utilizing background knowledge without changing the underlying logic of the used information (management) system. The comprehensive experiments on three public and private databases highlight the improvement when adding different types of mediator concepts for the adaption process. Compared to existing best performing works in related fields, TaxoMulti has achieved an improvement of + 26.31 % for the reduction of the taxonomy, + 60 % for the enlargement of the taxonomy, and + 21.21 % in terms of flexibility.

show abstract

“…The advantages of our SEOpinion system are: (i) it helps users to easily access a sentiment score about any preferred aspect and all sub-aspects thereof; (ii) the extracted aspects do not depend on a specific domain (e.g., Amazon and Flipkart) as long as these aspects are directly extracted from the site templates; (iii) the extracted hierarchy of aspects is constant and does not change with the change of reviews as in other methods [ 18 , 19 ] because they have been obtained from product details, not from the reviews (as shown in step 1 of Figure 1 ); (iv) some users might prefer to read the actual opinion sentences instead of reading the overall statistics, so these are displayed in a separate panel called the opinion sentence exploration (the details are shown in Section 3.5 ); (v) it allows users to easily compare people’s opinions on products of the same type (e.g., cameras) because they are all represented by the same aspects (e.g., Zoom, Lens, and Focus); and finally (vi) it helps in the polarity classification processes, which show the polarities of some sentiment words. For example, the sentence “In this laptop, the processor and battery-life are fast” contains a sentiment word “fast” and the two aspects “processor” and “battery-life.” The “fast” is positive under the “processor” aspect node, while it is negative under “battery-life.”…”

Section: Introductionmentioning

confidence: 99%

SEOpinion: Summarization and Exploration of Opinion from E-Commerce Websites

Mabrouk

Redondo

Kayed

2021

Sensors

View full text Add to dashboard Cite

Recently, it has been found that e-commerce (EC) websites provide a large amount of useful information that exceed the human cognitive processing capacity. In order to help customers in comparing alternatives when buying a product, previous research authors have designed opinion summarization systems based on customer reviews. They ignored the template information provided by manufacturers, although its descriptive information has the most useful product characteristics and texts are linguistically correct, unlike reviews. Therefore, this paper proposes a methodology coined as SEOpinion (summarization and exploration of opinions) to summarize aspects and spot opinion(s) regarding them using a combination of template information with customer reviews in two main phases. First, the hierarchical aspect extraction (HAE) phase creates a hierarchy of aspects from the template. Subsequently, the hierarchical aspect-based opinion summarization (HAOS) phase enriches this hierarchy with customers’ opinions to be shown to other potential buyers. To test the feasibility of using deep learning-based BERT techniques with our approach, we created a corpus by gathering information from the top five EC websites for laptops. The experimental results showed that recurrent neural network (RNN) achieved better results (77.4% and 82.6% in terms of F1-measure for the first and second phases, respectively) than the convolutional neural network (CNN) and the support vector machine (SVM) technique.

show abstract

OpinionLink: Leveraging user opinions for product catalog enrichment

Cited by 11 publications

References 15 publications

Integração de Dados Factuais e Subjetivos: Um Estudo de Caso em Comércio Eletrônico

Integração de Dados Factuais e Subjetivos: Um Estudo de Caso em Comércio Eletrônico

TaxoMulti: Rule-Based Expert System to Customize Product Taxonomies for Multi-Channel E-commerce

SEOpinion: Summarization and Exploration of Opinion from E-Commerce Websites

Contact Info

Product

Resources

About