@Article{jai.2021.027590,
AUTHOR = {Yue Jiang, Xinyu Zhang, Wohuan Jia, Li Xu},
TITLE = {Answer Classification via Machine Learning in Community Question  Answering},
JOURNAL = {Journal on Artificial Intelligence},
VOLUME = {3},
YEAR = {2021},
NUMBER = {4},
PAGES = {163--169},
URL = {http://www.techscience.com/jai/v3n4/46713},
ISSN = {2579-003X},
ABSTRACT = {As a new type of knowledge sharing platform, the community question 
answer website realizes the acquisition and sharing of knowledge, and is loved and 
sought after by the majority of users. But for multi-answer questions, answer quality 
assessment becomes a challenge. The answer selection in CQA (Community 
Question Answer) was proposed as a challenge task in the SemEval competition, 
which gave a data set and proposed two subtasks. Task-A is to give a question 
(including short title and extended description) and its answers, and divide each 
answer into absolutely relevant (good), potentially relevant (potential) and bad or 
irrelevant (bad, dialog, non-English, other). Task-B is to give a YES/NO type
question (including short title and extended description) and some answers. Based 
on the answer of the absolute correlation type (good), judge whether the answer to 
the whole question should be yes, no or uncertain. This paper first preprocesses this 
data set, and then uses natural language processing technology to perform word 
segmentation, part-of-speech tagging and named entity recognition on the data set, 
and then perform feature extraction on the preprocessed data set. Finally, SVM and 
random forest are used to classify on the basis of feature extraction, and the 
classification results are analyzed and compared. The experiments in this paper show 
that SVM and random forest methods have good results on the data set, and exceed 
the multi-classifier ensemble learning method and hierarchical classification method 
proposed by the predecessors.},
DOI = {10.32604/jai.2021.027590}
}