主题不平衡新闻文本数据集的主题识别方
法研究
王红斌
1,2
,王健雄
1,2
,张亚飞
1,2
,杨恒
3
1
(昆明理工大学信息工程与自动化学院 云南 昆明 650500)
2
(昆明理工大学云南省人工智能重点实验室 云南 昆明 650500)
3
(云南唯恒基业科技有限公司 云南 昆明 650000)
摘要:
[目的] 传统LDA模型因新闻文本数据集中不同主题间文本数量不均衡导致文本主题识别不
准确。[方法] 提出一种在主题不平衡新闻文本数据集上的主题识别方法,该方法基于传统
LDA模型,结合独立性检测、方差检测和信息熵检测三种不同的特征检测方法来识别出文
本的主题。[结果] 在10000篇新闻文本规模的数据集上实验验证,该方法相比传统的LDA主
题识别方法在查全率上提高了0.2121、查准率上提高了0.0407和F1值提高了0.152。[局限] 由
于新闻文本中新词较多,实验中使用的分词工具的分词准确率会降低,新闻文本主题识别的
效果因对分词准确率的依赖而受影响。[结论] 实验证明,本研究所提的方法能在一定程度
上解决了LDA对新闻文本数据集中不同主题间文本数量不均衡的主题识别问题。
关键词: 主题不平衡;新闻文本数据集;文本主题识别;潜在 Dirichlet 分配(LDA)
分类号: TP393,G250
DOI: 10.11925/infotech. 2020-0765.
Topic Recognition Research on Topic
Imbalanced News Text Data Set
Wang Hongbin
1,2
, Wang Jianxiong
1,2
, Zhang Yafei
1,2
, Yang Heng
3
1
(Faculty of Information Engineering and Automation, Kunming University of Science and
Technology, Kunming 650500, China)
2
(Yunnan Key Laboratory of Artificial Intelligence, Kunming University of Science
and Technology, Kunming 650500, China)
3
(Yunnan Weiheng Jiye Technology Co., Ltd., Kunming 650000, China)
Abstract:
[Objective] The traditional LDA model is not accurate for text topic recognition,because of the
number of different topic texts in news text dataset is not balanced. [Methods] This paper
proposes a topic recognition method based on the traditional LDA model on unbalanced news text
data sets, which combines three different feature detection methods: independence detection,
variance detection and information entropy detection. [Results] Experiments are conducted on
10000 news texts, the proposed method improves recall by 0.2121, precision by 0.0407 and F1
value by 0.152, compared with the traditional LDA topic recognition method. [Limitations]
Due to the large number of new words in news text, the segmentation accuracy of word
segmentation tools used in the experiment will be reduced, and the effect of news text topic
recognition is affected by the dependence on the accuracy of segmentation. [Conclusions]
Experimental results show that the proposed method can solve the problem of LDA topic
网络首发时间:2020-11-12 14:01:34
网络首发地址:https://kns.cnki.net/kcms/detail/10.1478.g2.20201112.1113.010.html
评论0