Spotting Collective Behaviour of Online Frauds in Customer Reviews
Authors: Sarthika Dhawan, Siva Charan Reddy Gangireddy, Shiv Kumar, Tanmoy Chakraborty
IJCAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experiments on four real-world labeled datasets (two of them were prepared by us) show that De Frauder significantly outperforms five baselines it beats the best baseline by 11.35% higher accuracy for detecting groups, and 17.11% higher NDCG@50 for ranking groups (averaged over all datasets). |
| Researcher Affiliation | Academia | Sarthika Dhawan1 , Siva Charan Reddy Gangireddy1 , Shiv Kumar2 and Tanmoy Chakraborty1 1Indraprastha Institute of Information Technology Delhi (IIITD), India 2Netaji Subhas University of Technology (NSUT), Delhi, India {sarthika15170, sivag}@iiitd.ac.in, shivk.it.16@nsit.net.in, tanmoy@iiitd.ac.in |
| Pseudocode | Yes | Algorithm 1 Extract Groups |
| Open Source Code | Yes | De Frauder: Detecting Fraud Reviewer Groups, Code is available in [Dhawan et al.2019]. |
| Open Datasets | Yes | We collected four real-world datasets Yelp NYC: hotel/restaurant reviews of New York city [Rayana and Akoglu2015]; Yelp Zip: aggregation of reviews on restaurants/hotels from a number of areas with continuous zip codes starting from New York city [Rayana and Akoglu2015]; Amazon: reviews on musical instruments [He and Mc Auley2016], and Playstore: reviews of different applications available on Google Playstore. |
| Dataset Splits | No | The paper describes the datasets used and evaluation metrics, but does not explicitly provide details about how the datasets were split into training, validation, and test sets for reproduction. |
| Hardware Specification | No | The paper does not provide specific details about the hardware (e.g., CPU, GPU models, memory, cloud instances) used to conduct the experiments. |
| Software Dependencies | No | The paper mentions using 'Word2Vec [Mikolov et al.2013]' and 'Node2Vec [Grover and Leskovec2016]' for embedding, but does not provide specific version numbers for these or any other software dependencies. |
| Experiment Setup | Yes | Extract Groups achieves best results with τt = 20 and τr = (max min)20% (see Sec. 5.3). |