An aspect-driven method for enriching product catalogs with user opinions
Abstract In this paper, we propose a method for enriching product catalogs, which traditionally include only objective data provided by manufacturers or retailers, with subjective information extracted from reviews written by customers. Our method was designed to associate opinions taken from review...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Sociedade Brasileira de Computação
2018-11-01
|
| Series: | Journal of the Brazilian Computer Society |
| Subjects: | |
| Online Access: | http://link.springer.com/article/10.1186/s13173-018-0080-4 |
| _version_ | 1818026461669359616 |
|---|---|
| author | Tiago de Melo Altigran da Silva Edleno S. de Moura |
| author_facet | Tiago de Melo Altigran da Silva Edleno S. de Moura |
| author_sort | Tiago de Melo |
| collection | DOAJ |
| description | Abstract In this paper, we propose a method for enriching product catalogs, which traditionally include only objective data provided by manufacturers or retailers, with subjective information extracted from reviews written by customers. Our method was designed to associate opinions taken from reviews with the product attributes they refer to. This is done by matching aspect expression identified in opinions with attributes from the product, which we model here as aspect classes. To verify the effectiveness of our method, we executed an extensive experimental evaluation that revealed that customers frequently mention aspects related to product attributes in their reviews. The attributes often receive more mentions than the product itself. Our method consistently reached almost 0.7 of F 1 measure in the task of associating the opinion with the correct attribute (or with the product as a whole), across four product categories, in two different scenarios. These results significantly improved the results achieved by a representative baseline. |
| first_indexed | 2024-12-10T04:32:23Z |
| format | Article |
| id | doaj.art-81915a1fc9e646e696389a50fc7479f3 |
| institution | Directory Open Access Journal |
| issn | 0104-6500 1678-4804 |
| language | English |
| last_indexed | 2024-12-10T04:32:23Z |
| publishDate | 2018-11-01 |
| publisher | Sociedade Brasileira de Computação |
| record_format | Article |
| series | Journal of the Brazilian Computer Society |
| spelling | doaj.art-81915a1fc9e646e696389a50fc7479f32022-12-22T02:02:06ZengSociedade Brasileira de ComputaçãoJournal of the Brazilian Computer Society0104-65001678-48042018-11-0124111910.1186/s13173-018-0080-4An aspect-driven method for enriching product catalogs with user opinionsTiago de Melo0Altigran da Silva1Edleno S. de Moura2Institute of Computing, Federal University of AmazonasInstitute of Computing, Federal University of AmazonasInstitute of Computing, Federal University of AmazonasAbstract In this paper, we propose a method for enriching product catalogs, which traditionally include only objective data provided by manufacturers or retailers, with subjective information extracted from reviews written by customers. Our method was designed to associate opinions taken from reviews with the product attributes they refer to. This is done by matching aspect expression identified in opinions with attributes from the product, which we model here as aspect classes. To verify the effectiveness of our method, we executed an extensive experimental evaluation that revealed that customers frequently mention aspects related to product attributes in their reviews. The attributes often receive more mentions than the product itself. Our method consistently reached almost 0.7 of F 1 measure in the task of associating the opinion with the correct attribute (or with the product as a whole), across four product categories, in two different scenarios. These results significantly improved the results achieved by a representative baseline.http://link.springer.com/article/10.1186/s13173-018-0080-4Product catalog enrichmentAspect-based summarizationOpinion miningSentiment analysise-CommerceOnline reviews |
| spellingShingle | Tiago de Melo Altigran da Silva Edleno S. de Moura An aspect-driven method for enriching product catalogs with user opinions Journal of the Brazilian Computer Society Product catalog enrichment Aspect-based summarization Opinion mining Sentiment analysis e-Commerce Online reviews |
| title | An aspect-driven method for enriching product catalogs with user opinions |
| title_full | An aspect-driven method for enriching product catalogs with user opinions |
| title_fullStr | An aspect-driven method for enriching product catalogs with user opinions |
| title_full_unstemmed | An aspect-driven method for enriching product catalogs with user opinions |
| title_short | An aspect-driven method for enriching product catalogs with user opinions |
| title_sort | aspect driven method for enriching product catalogs with user opinions |
| topic | Product catalog enrichment Aspect-based summarization Opinion mining Sentiment analysis e-Commerce Online reviews |
| url | http://link.springer.com/article/10.1186/s13173-018-0080-4 |
| work_keys_str_mv | AT tiagodemelo anaspectdrivenmethodforenrichingproductcatalogswithuseropinions AT altigrandasilva anaspectdrivenmethodforenrichingproductcatalogswithuseropinions AT edlenosdemoura anaspectdrivenmethodforenrichingproductcatalogswithuseropinions AT tiagodemelo aspectdrivenmethodforenrichingproductcatalogswithuseropinions AT altigrandasilva aspectdrivenmethodforenrichingproductcatalogswithuseropinions AT edlenosdemoura aspectdrivenmethodforenrichingproductcatalogswithuseropinions |