| Journal: | Computación y sistemas |
| Database: | |
| System number: | 000560789 |
| ISSN: | 1405-5546 |
| Authors: | Bhagat, Pradnya1 Korkankar, Pratik D.1 Pawar, Jyoti D.1 |
| Institutions: | 1Goa University, Goa Business School, Goa. India 2Dnyanprassarak Mandal’s College and Research Centre, Goa. India |
| Year: | 2023 |
| Season: | Abr-Jun |
| Volumen: | 27 |
| Number: | 2 |
| Pages: | 389-399 |
| Country: | México |
| Language: | Inglés |
| English abstract | Most of the user-preferred products on e-commerce websites are accompanied by a massive number of product reviews and manually analyzing each review to understand the features and the user opinions associated with the products is an inconceivable task. A single domain of products can contain thousands of different products and an equally significant number of associated product features/aspects, thereby making the polarity of the sentiment words in the product reviews vary widely according to the aspect with which they are associated. The paper uses the Chi-square Test statistical measure to automatically calculate the aspect-based polarity of sentiment words in a given domain. The results of the method are tested on two different domains. The experimental results show that the method delivers an accuracy of more than 75% in both domains. The method also helps in discovering strong domain-specific polar adjectives that might be missing in universal sentiment lexicons. |
| Keyword: | Aspect/feature words, Sentiment words, Polar words, Universal sentiment lexicon, Chi-square test |
| Full text: | Texto completo (Ver HTML) Texto completo (Ver PDF) |
