Utilize este identificador para referenciar este registo:
https://hdl.handle.net/1822/62770
Título: | Social media cross-source and cross-domain sentiment classification |
Autor(es): | Zola, Paola Cortez, Paulo Ragno, Costantino Brentari, Eugenio |
Palavras-chave: | Convolutional neural network cross-domain data sentiment analysis social media |
Data: | 2019 |
Editora: | World Scientific |
Revista: | International Journal of Information Technology & Decision Making |
Citação: | World Scientific, 18(5): 1469-1499, September, 2019, ISSN 0219-6220. |
Resumo(s): | Due to the expansion of Internet and Web 2.0 phenomenon, there is a growing interest in the sentiment analysis of freely opinionated text. In this paper, we propose a novel cross-source cross-domain sentiment classification, in which cross-domain labeled Web sources (Amazon and Tripadvisor) are used to train supervised learning models (including two deep learning algorithms) that are tested on typically non labeled social media reviews (Facebook and Twitter). We explored a three step methodology, in which dis- tinct balanced training, text preprocessing and machine learning methods were tested, using two languages: English and Italian. The best results were achieved when using undersampling training and a Convolutional Neural Network. Interesting cross-source classification performances were achieved, in particular when using Amazon and Tripadvisor reviews to train a model that is tested on Facebook data for both English and Italian. |
Tipo: | Artigo |
URI: | https://hdl.handle.net/1822/62770 |
DOI: | 10.1142/S0219622019500305 |
ISSN: | 0219-6220 |
Versão da editora: | https://doi.org/10.1142/S0219622019500305 |
Arbitragem científica: | yes |
Acesso: | Acesso aberto |
Aparece nas coleções: | CAlg - Artigos em revistas internacionais / Papers in international journals |
Ficheiros deste registo:
Ficheiro | Descrição | Tamanho | Formato | |
---|---|---|---|---|
manuscript.pdf | Author's Accepted Manuscript | 1,49 MB | Adobe PDF | Ver/Abrir |
Este trabalho está licenciado sob uma Licença Creative Commons