Social Emotion Classification via Reader Perspective Weighted Model
Authors: Xin Li, Yanghui Rao, Yanjia Chen, Xuebo Liu, Huan Huang
AAAI 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experimental evaluations using different data sets validate the effectiveness of the proposed social emotion classification model. |
| Researcher Affiliation | Academia | Xin Li, Yanghui Rao , Yanjia Chen, Xuebo Liu, Huan Huang School of Mobile Information Engineering, Sun Yat-sen University Zhuhai Campus, Tang Jia Bay, Zhu Hai, Guang Dong, China |
| Pseudocode | No | The paper provides mathematical formulas and descriptions of the model but does not include pseudocode or clearly labeled algorithm blocks. |
| Open Source Code | No | The paper does not provide any statements about releasing source code or links to a code repository. |
| Open Datasets | Yes | To evaluate the effectiveness and adaptiveness on the proposed model, two data sets were employed: Sem Eval (Strapparava and Mihalcea 2007) and Sina News (Rao et al. 2014c). |
| Dataset Splits | Yes | The first data set contained 1250 real-world news headlines, and each headline was manually scored across 6 emotions. After pruning 4 items with the total scores equal to 0, we used the 246 headlines in the development set for training and the rest for testing. The second data set consisted of 4570 documents from Sina news, and reader ratings over 8 emotions. Due to that adjacent documents may have similar contexts, the 2342 documents published from January to February, 2012 were used for training, and the 2228 documents published from March to April, 2012 were used for testing. |
| Hardware Specification | No | The paper does not provide any specific details about the hardware used for running the experiments. |
| Software Dependencies | No | The paper states 'All parameters were set empirically.' but does not list any specific software dependencies with version numbers. |
| Experiment Setup | No | The paper states 'All parameters were set empirically.' but does not provide specific hyperparameter values or detailed training configurations for the experimental setup. |