Random Forest and Support Vector Machine based Hybrid Approach to Sentiment Analysis
| Autor: | Mohamed Lazaar, Yassine Al Amrani, Kamal Eddine El Kadiri |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
Relation (database)
Computer science business.industry Sentiment analysis 010103 numerical & computational mathematics 02 engineering and technology Hybrid approach Machine learning computer.software_genre 01 natural sciences Random forest Support vector machine 0202 electrical engineering electronic engineering information engineering General Earth and Planetary Sciences 020201 artificial intelligence & image processing Artificial intelligence 0101 mathematics business computer General Environmental Science |
| Zdroj: | Procedia Computer Science. 127:511-520 |
| ISSN: | 1877-0509 |
| DOI: | 10.1016/j.procs.2018.01.150 |
| Popis: | Sentiment analysis becomes more popular in the research area. It allocates positive or negative polarity to an entity or items by using different natural language processing tools and also predicted high and low performance of various sentiment classifiers. Our work focuses on the Sentiment analysis resulting from the product reviews using original techniques of text’s search. These reviews can be classified as having a positive or negative feeling based on certain aspects in relation to a query based on terms. In this paper, we proposed hybrid approach to identify product reviews offered by Amazon. The results show that the proposed system approach outperforms these individual classifiers in this amazon dataset. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|