Text Emotion Distribution Learning via Multi-Task Convolutional Neural Network
Authors: Yuxiang Zhang, Jiamei Fu, Dongyu She, Ying Zhang, Senzhang Wang, Jufeng Yang
IJCAI 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experiments conducted on five public text datasets (i.e., Sem Eval, Fairy Tales, ISEAR, TEC, CBET) demonstrate that our proposed method performs favorably against the stateof-the-art approaches. |
| Researcher Affiliation | Academia | 1College of Computer Science and Technology, Civil Aviation University of China, Tianjin, China 2College of Computer and Control Engineering, Nankai University, Tianjin, China 3College of Comp. Sci.&Tech., Nanjing University of Aeronautics and Astronautics, Nanjing, China |
| Pseudocode | No | No pseudocode or algorithm blocks were found in the paper. |
| Open Source Code | No | The paper does not provide any explicit statement or link indicating that the source code for their methodology is publicly available. |
| Open Datasets | Yes | Dataset. Sem Eval [Strapparava and Mihalcea, 2007] is a distribution dataset that contains 1250 news headlines... ISEAR [Scherer and Wallbott, 1994] consists of 7666 sentences... Fairy Tales [Alm and Sproat, 2005] contains 185 children s stories... TEC [Mohammad, 2012] includes 21,051 emotional tweets... CBET [Shahraki, 2015] consists of 76,860 tweets... |
| Dataset Splits | Yes | For the Sem Eval, we adopt the standard 1000 headlines for training and 250 headlines for testing to run our experiments. We randomly choose 90% of train samples for training, the rest 10% for testing. ... we perform 10-fold cross validation on all the above datasets, and report the average results. |
| Hardware Specification | No | The paper does not provide specific details about the hardware used for running the experiments. |
| Software Dependencies | Yes | Our framework is implemented using Torch7. |
| Experiment Setup | Yes | For the CNN framework, we use filter windows of 3, 4, 5 with 100 feature maps each, dropout rate of 0.5, and minibatch size of 50 following the same routing in [Kim, 2014]. |