Detecting Rumors from Microblogs with Recurrent Neural Networks
Authors: Jing Ma, Wei Gao, Prasenjit Mitra, Sejeong Kwon, Bernard J. Jansen, Kam-Fai Wong, Meeyoung Cha
IJCAI 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experimental results on datasets from two real-world microblog platforms demonstrate that (1) the RNN method outperforms state-of-the-art rumor detection models that use hand-crafted features; (2) performance of the RNN-based algorithm is further improved via sophisticated recurrent units and extra hidden layers; (3) RNN-based method detects rumors more quickly and accurately than existing techniques, including the leading online rumor debunking services. |
| Researcher Affiliation | Academia | Jing Ma,1 Wei Gao,2 Prasenjit Mitra,2 Sejeong Kwon,3 Bernard J. Jansen,2 Kam-Fai Wong,1 Meeyoung Cha3 1The Chinese University of Hong Kong, Hong Kong SAR 2Qatar Computing Research Institute, Hamad Bin Khalifa University, Qatar 3Graduate School of Culture Technology, Korea Advanced Institute of Science and Technology, Korea |
| Pseudocode | Yes | Algorithm 1: Algorithm for constructing variablelength time series given the set of relevant posts of an event and the reference length of RNN |
| Open Source Code | No | The paper states "We make this large rumor dataset fully public to be used for research purposes2." and provides a link to the dataset. However, it does not provide an explicit statement or link for the open-source code of the methodology described in the paper. |
| Open Datasets | Yes | We make this large rumor dataset fully public to be used for research purposes2. 2http://alt.qcri.org/~wgao/data/rumdect.zip |
| Dataset Splits | Yes | We hold out 10% of the events in each dataset for model tuning, and the rest of the events are split with a ratio of 3:1 for training and test. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., CPU, GPU models, or memory specifications) used for running the experiments. |
| Software Dependencies | No | The paper mentions using 'Weka4', 'Lib SVM5', and 'Theano6' for implementation, along with their general project URLs. However, these are not specific version numbers required for reproducible software dependencies (e.g., Weka 3.8.5, Theano 1.0.4). |
| Experiment Setup | Yes | We empirically set the vocabulary size K as 5,000, the embedding size as 100, the size of the hidden units as 100 and the learning rate as 0.5. |