Emotion Classification in Microblog Texts Using Class Sequential Rules

Authors: Shiyang Wen, Xiaojun Wan

AAAI 2014 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results on a Chinese benchmark dataset show the superior performance of the proposed approach.
Researcher Affiliation Academia Shiyang Wen and Xiaojun Wan* Institute of Computer Science and Technology, Peking University, Beijing 100871, China The MOE Key Laboratory of Computational Linguistics, Peking University, Beijing 100871, China {wenshiyang, wanxiaojun}@pku.edu.cn
Pseudocode No The paper describes the CSR mining algorithm from (Liu 2007) and states details are omitted due to page limit, but it does not provide its own structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide concrete access to source code for the methodology described in this paper.
Open Datasets Yes We use the benchmark dataset from the 2013 Chinese Microblog Sentiment Analysis Evaluation (CMSAE)5. The task is to recognize the fine-grained emotion type of a Chinese microblog text. (Footnote 5: http://tcci.ccf.org.cn/conference/2013/pages/page04_eva.html)
Dataset Splits Yes In the experiments, the parameter values are set by a five-fold cross-validation process on the training set.
Hardware Specification No The paper does not provide specific hardware details (e.g., exact GPU/CPU models, processor types, or memory amounts) used for running its experiments.
Software Dependencies No We use a Chinese segmentation tool ICTCLAS 3 (http://www.ictclas.org) and the LIBSVM toolkit 4 (http://www.csie.ntu.edu.tw/~cjlin/libsvm/). The paper mentions software names but does not specify their version numbers.
Experiment Setup Yes The parameters in our method are set as minconf = 0.01 and W = 0.05.