Abstract:
Technology and ride-sharing services have become more accessible and convenient as a
result of the growth of the internet. Passengers increasingly focus on digital reviews to help
them make purchasing decisions. Online reviews are incredibly inaccurate, as we've seen
time and time again. False reviews were created to deceive customers for commercial
purposes. A misleading review might have major repercussions for any organization.
Providing good feedback to attract passengers and grow the market. It's possible that a bad
review of an app would reduce interest in it. These false reviews endanger the reputation
of a product. Because of this, it is critical to have a system in place for detecting fraudulent
reviews. The goal of this research is to improve the performance of machine learning
models that classify fake reviews. In this work Decision tree, Random Forest, Gradient
Boosting, AdaBoost, and Bi-LSTM these five machine learning approaches have been
implemented to get the best performance on our dataset. Data was collected from the
current Bangladesh ride-sharing applications review section. After creating & running the
model, Bidirectional Long Short-Term Memory (Bi-LSTM) achieved 85% best model
accuracy and 89.0 F1-macro scores with training data rather than other machine learning
algorithms.
