TY - GEN
T1 - Opinion summarization for short texts based on BM25 and syntactic parsing
AU - Niu, Jianwei
AU - Zhao, Qingjuan
AU - Wang, Lei
AU - Chen, Huan
AU - Zheng, Shichao
N1 - Publisher Copyright:
© 2016 IEEE.
PY - 2016/7/2
Y1 - 2016/7/2
N2 - Online short texts of hot topics submitted to social media by users can provide valuable personal opinions, which are useful for service providers and individuals. However, it is difficult for readers to grasp the main opinions of massive short texts. In this paper, to cope with the summarization challenge of short texts, we proposed a novel approach, which makes full use of BM25 to weight each short text and syntactic parsing to generate important information of each opinion cluster. The approach also utilizes the feature pruning to reduce the dimensions of the vectors. We conduct our experiments on real datasets and evaluate the results by standard metrics and manual evaluation. The experimental results show that our proposed approach improves the accuracy when compared to the state-of-the-art method.
AB - Online short texts of hot topics submitted to social media by users can provide valuable personal opinions, which are useful for service providers and individuals. However, it is difficult for readers to grasp the main opinions of massive short texts. In this paper, to cope with the summarization challenge of short texts, we proposed a novel approach, which makes full use of BM25 to weight each short text and syntactic parsing to generate important information of each opinion cluster. The approach also utilizes the feature pruning to reduce the dimensions of the vectors. We conduct our experiments on real datasets and evaluate the results by standard metrics and manual evaluation. The experimental results show that our proposed approach improves the accuracy when compared to the state-of-the-art method.
KW - opinion clustering
KW - opinion summarization
KW - syntactic parsing
KW - vector space model (VSM)
UR - https://www.scopus.com/pages/publications/85012863974
U2 - 10.1109/INDIN.2016.7819344
DO - 10.1109/INDIN.2016.7819344
M3 - 会议稿件
AN - SCOPUS:85012863974
T3 - IEEE International Conference on Industrial Informatics (INDIN)
SP - 1177
EP - 1180
BT - Proceedings - 2016 IEEE 14th International Conference on Industrial Informatics, INDIN 2016
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 14th IEEE International Conference on Industrial Informatics, INDIN 2016
Y2 - 19 July 2016 through 21 July 2016
ER -