A Machine learning model to detect deceptive(fake) Hotel and Electronic reviews.
Link to report: Report.pdf
Boulder Lies and Truth dataset
- The project dependencies(python libraries) can be installed by running the following command:-
$ pip install -r requirements.txt- Run the below commands to start training and evaluating the network.
- You will need to provide the path to the dataset, and
- A flag(treat_F_as_deceptive) that tell the program whether to treat the 'F' label in the dataset as deceptive or to treat it as a unique class while training.
- More information - Paper.
$ python main.py --path_to_dataset "<path to the BLT dataset>" --treat_F_as_deceptive <True/False>- A Tangled Web: The Faint Signals of Deception in Text - Boulder Lies and Truth Corpus (BLT-C)
- V. Sandifer, Anna & Wilson, Casey & Olmsted, Aspen. (2017). Detection of fake online hotel reviews
- A. Mukherjee, V. Venkataraman, B. Liu and N. Glance, "Fake Review Detection: Classification and Analysis of Real and Pseudo Reviews
- Automatic detection of deceptive opinions using automatically identified specific details Nikolai Vogler
- Sentence classification using Bi-LSTM
- From Word Embeddings To Document Distances
- Gensim
- bidirectional LSTM + keras
- Evaluate the Performance Of Deep Learning Models in Keras