Abstract
Today, significant impacts of comments on the web affect people decisions while they are about to choose a product. Unfavorable effect of spam attacks in these reviews follows heavy damages for customers and organizations. The majority of methods so far classify reviews to spam and non-spam groups. Therefore, most researches are done on feature learning techniques to enhance the classification performance. From another point of view, presence of huge amount of features makes text classification overwhelming. Attention mechanism has lately been used to improve neural networks performance on sequence modeling. Instead of mining all existing features, attention can enables the model to concentrate on most important parts of the data. To these ends, we applied an attention based deep structure for detecting deceptive reviews. This model contributes distinguishing between truthful and fake reviews and benefits an attentional part to engineering better features. Our proposed model accuracy and scalability is comparable regard to the other common models.
Original language | English |
---|---|
Title of host publication | The Thirty-Second International Florida Artificial Intelligence Research Society Conference (FLAIRS-32) |
Place of Publication | Palo Alto, CA |
Publisher | AAAI Press |
Number of pages | 4 |
Publication status | Published - 19 May 2019 |