Servicios Personalizados
Revista
Articulo
Indicadores
- Citado por SciELO
- Accesos
Links relacionados
- Similares en SciELO
Compartir
Journal of applied research and technology
versión On-line ISSN 2448-6736versión impresa ISSN 1665-6423
Resumen
NOFERESTI, S. y SHAMSFARD, M.. A semantic framework based on domain knowledge for opinion mining of drug reviews. J. appl. res. technol [online]. 2022, vol.20, n.6, pp.652-667. Epub 08-Mayo-2023. ISSN 2448-6736. https://doi.org/10.22201/icat.24486736e.2022.20.6.868.
Opinion mining has attracted increasing attention in recent years. Existing approaches that address general domains face two major challenges concerning polarity classification of drug reviews. Firstly, indirect opinions frequently occur in the drug domain, while the existing methods have mainly focused on direct opinions and ignored indirect ones. Secondly, previous works are not sufficient for polarity classification of ambiguous concepts in the drug domain. This paper proposed a semantic framework based on domain knowledge to construct and exploit resources for indirect opinion mining of drug reviews. Accordingly, some methods were introduced, developed, and compared for building and exploiting a combined knowledge base, polarity-tagged corpus, and context-aware resources to detect the polarity of drug reviews. The test results showed that the proposed methods reached a precision of 89.18% and 80.4% in the application of the combined knowledge base and the polarity-tagged corpus for polarity detection of indirect opinions, respectively. Also, a precision of 79.93% was achieved with the use of context-aware resources that were constructed for polarity detection of ambiguous concepts. Overall, the results demonstrated the greater performance of the proposed methods compared to the existing methods.
Palabras llave : Opinion mining; drug reviews; indirect opinions; domain knowledge; ambiguous concepts.